Merge pull request #2992 from open-webui/dev

0.3.2

.github/pull_request_template.md

@@ -11,7 +11,7 @@
 - [ ] **Dependencies:** Are there any new dependencies? Have you updated the dependency versions in the documentation?
 - [ ] **Testing:** Have you written and run sufficient tests for validating the changes?
 - [ ] **Code review:** Have you performed a self-review of your code, addressing any coding standard issues and ensuring adherence to the project's coding standards?
-- [ ] **Label:** To cleary categorize this pull request, assign a relevant label to the pull request title, using one of the following:
+- [ ] **Prefix:** To cleary categorize this pull request, prefix the pull request title, using one of the following:
   - **BREAKING CHANGE**: Significant changes that may affect compatibility
   - **build**: Changes that affect the build system or external dependencies
   - **ci**: Changes to our continuous integration processes or workflows

CHANGELOG.md

@@ -5,6 +5,72 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.3.2] - 2024-06-10
+
+### Added
+
+- **🔍 Web Search Query Status**: The web search query will now persist in the results section to aid in easier debugging and tracking of search queries.
+- **🌐 New Web Search Provider**: We have added Serply as a new option for web search providers, giving you more choices for your search needs.
+- **🌏 Improved Translations**: We've enhanced translations for Chinese and Portuguese.
+
+### Fixed
+
+- **🎤 Audio File Upload Issue**: The bug that prevented audio files from being uploaded in chat input has been fixed, ensuring smooth communication.
+- **💬 Message Input Handling**: Improved the handling of message inputs by instantly clearing images and text after sending, along with immediate visual indications when a response message is loading, enhancing user feedback.
+- **⚙️ Parameter Registration and Validation**: Fixed the issue where parameters were not registering in certain cases and addressed the problem where users were unable to save due to invalid input errors.
+
+## [0.3.1] - 2024-06-09
+
+### Fixed
+
+- **💬 Chat Functionality**: Resolved the issue where chat functionality was not working for specific models.
+
+## [0.3.0] - 2024-06-09
+
+### Added
+
+- **📚 Knowledge Support for Models**: Attach documents directly to models from the models workspace, enhancing the information available to each model.
+- **🎙️ Hands-Free Voice Call Feature**: Initiate voice calls without needing to use your hands, making interactions more seamless.
+- **📹 Video Call Feature**: Enable video calls with supported vision models like Llava and GPT-4o, adding a visual dimension to your communications.
+- **🎛️ Enhanced UI for Voice Recording**: Improved user interface for the voice recording feature, making it more intuitive and user-friendly.
+- **🌐 External STT Support**: Now support for external Speech-To-Text services, providing more flexibility in choosing your STT provider.
+- **⚙️ Unified Settings**: Consolidated settings including document settings under a new admin settings section for easier management.
+- **🌑 Dark Mode Splash Screen**: A new splash screen for dark mode, ensuring a consistent and visually appealing experience for dark mode users.
+- **📥 Upload Pipeline**: Directly upload pipelines from the admin settings > pipelines section, streamlining the pipeline management process.
+- **🌍 Improved Language Support**: Enhanced support for Chinese and Ukrainian languages, better catering to a global user base.
+
+### Fixed
+
+- **🛠️ Playground Issue**: Fixed the playground not functioning properly, ensuring a smoother user experience.
+- **🔥 Temperature Parameter Issue**: Corrected the issue where the temperature value '0' was not being passed correctly.
+- **📝 Prompt Input Clearing**: Resolved prompt input textarea not being cleared right away, ensuring a clean slate for new inputs.
+- **✨ Various UI Styling Issues**: Fixed numerous user interface styling problems for a more cohesive look.
+- **👥 Active Users Display**: Fixed active users showing active sessions instead of actual users, now reflecting accurate user activity.
+- **🌐 Community Platform Compatibility**: The Community Platform is back online and fully compatible with Open WebUI.
+
+### Changed
+
+- **📝 RAG Implementation**: Updated the RAG (Retrieval-Augmented Generation) implementation to use a system prompt for context, instead of overriding the user's prompt.
+- **🔄 Settings Relocation**: Moved Models, Connections, Audio, and Images settings to the admin settings for better organization.
+- **✍️ Improved Title Generation**: Enhanced the default prompt for title generation, yielding better results.
+- **🔧 Backend Task Management**: Tasks like title generation and search query generation are now managed on the backend side and controlled only by the admin.
+- **🔍 Editable Search Query Prompt**: You can now edit the search query generation prompt, offering more control over how queries are generated.
+- **📏 Prompt Length Threshold**: Set the prompt length threshold for search query generation from the admin settings, giving more customization options.
+- **📣 Settings Consolidation**: Merged the Banners admin setting with the Interface admin setting for a more streamlined settings area.
+
+## [0.2.5] - 2024-06-05
+
+### Added
+
+- **👥 Active Users Indicator**: Now you can see how many people are currently active and what they are running. This helps you gauge when performance might slow down due to a high number of users.
+- **🗂️ Create Ollama Modelfile**: The option to create a modelfile for Ollama has been reintroduced in the Settings > Models section, making it easier to manage your models.
+- **⚙️ Default Model Setting**: Added an option to set the default model from Settings > Interface. This feature is now easily accessible, especially convenient for mobile users as it was previously hidden.
+- **🌐 Enhanced Translations**: We've improved the Chinese translations and added support for Turkmen and Norwegian languages to make the interface more accessible globally.
+
+### Fixed
+
+- **📱 Mobile View Improvements**: The UI now uses dvh (dynamic viewport height) instead of vh (viewport height), providing a better and more responsive experience for mobile users.
+
 ## [0.2.4] - 2024-06-03
 
 ### Added

README.md

@@ -11,7 +11,7 @@
 [![Discord](https://img.shields.io/badge/Discord-Open_WebUI-blue?logo=discord&logoColor=white)](https://discord.gg/5rJgQTnV4s)
 [![](https://img.shields.io/static/v1?label=Sponsor&message=%E2%9D%A4&logo=GitHub&color=%23fe8e86)](https://github.com/sponsors/tjbck)
 
-Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
+Open WebUI is an [extensible](https://github.com/open-webui/pipelines), feature-rich, and user-friendly self-hosted WebUI designed to operate entirely offline. It supports various LLM runners, including Ollama and OpenAI-compatible APIs. For more information, be sure to check out our [Open WebUI Documentation](https://docs.openwebui.com/).
 
 ![Open WebUI Demo](./demo.gif)
 
@@ -33,7 +33,7 @@ Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI d
 
 - 📚 **Local RAG Integration**: Dive into the future of chat interactions with groundbreaking Retrieval Augmented Generation (RAG) support. This feature seamlessly integrates document interactions into your chat experience. You can load documents directly into the chat or add files to your document library, effortlessly accessing them using the `#` command before a query.
 
-- 🔍 **Web Search for RAG**: Perform web searches using providers like `SearXNG`, `Google PSE`, `Brave Search`, `serpstack`, and `serper`, and inject the results directly into your chat experience.
+- 🔍 **Web Search for RAG**: Perform web searches using providers like `SearXNG`, `Google PSE`, `Brave Search`, `serpstack`, `serper`, and `Serply` and inject the results directly into your chat experience.
 
 - 🌐 **Web Browsing Capability**: Seamlessly integrate websites into your chat experience using the `#` command followed by a URL. This feature allows you to incorporate web content directly into your conversations, enhancing the richness and depth of your interactions.
 
@@ -146,10 +146,19 @@ docker run --rm --volume /var/run/docker.sock:/var/run/docker.sock containrrr/wa
 
 In the last part of the command, replace `open-webui` with your container name if it is different.
 
-### Moving from Ollama WebUI to Open WebUI
-
 Check our Migration Guide available in our [Open WebUI Documentation](https://docs.openwebui.com/migration/).
 
+### Using the Dev Branch 🌙
+
+> [!WARNING]
+> The `:dev` branch contains the latest unstable features and changes. Use it at your own risk as it may have bugs or incomplete features.
+
+If you want to try out the latest bleeding-edge features and are okay with occasional instability, you can use the `:dev` tag like this:
+
+```bash
+docker run -d -p 3000:8080 -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:dev
+```
+
 ## What's Next? 🌟
 
 Discover upcoming features on our roadmap in the [Open WebUI Documentation](https://docs.openwebui.com/roadmap/).

backend/apps/audio/main.py

@@ -17,13 +17,12 @@ from fastapi.middleware.cors import CORSMiddleware
 from faster_whisper import WhisperModel
 from pydantic import BaseModel
 
-
+import uuid
 import requests
 import hashlib
 from pathlib import Path
 import json
 
-
 from constants import ERROR_MESSAGES
 from utils.utils import (
     decode_token,
@@ -41,10 +40,15 @@ from config import (
     WHISPER_MODEL_DIR,
     WHISPER_MODEL_AUTO_UPDATE,
     DEVICE_TYPE,
-    AUDIO_OPENAI_API_BASE_URL,
-    AUDIO_OPENAI_API_KEY,
-    AUDIO_OPENAI_API_MODEL,
-    AUDIO_OPENAI_API_VOICE,
+    AUDIO_STT_OPENAI_API_BASE_URL,
+    AUDIO_STT_OPENAI_API_KEY,
+    AUDIO_TTS_OPENAI_API_BASE_URL,
+    AUDIO_TTS_OPENAI_API_KEY,
+    AUDIO_STT_ENGINE,
+    AUDIO_STT_MODEL,
+    AUDIO_TTS_ENGINE,
+    AUDIO_TTS_MODEL,
+    AUDIO_TTS_VOICE,
     AppConfig,
 )
 
@@ -61,10 +65,17 @@ app.add_middleware(
 )
 
 app.state.config = AppConfig()
-app.state.config.OPENAI_API_BASE_URL = AUDIO_OPENAI_API_BASE_URL
-app.state.config.OPENAI_API_KEY = AUDIO_OPENAI_API_KEY
-app.state.config.OPENAI_API_MODEL = AUDIO_OPENAI_API_MODEL
-app.state.config.OPENAI_API_VOICE = AUDIO_OPENAI_API_VOICE
+
+app.state.config.STT_OPENAI_API_BASE_URL = AUDIO_STT_OPENAI_API_BASE_URL
+app.state.config.STT_OPENAI_API_KEY = AUDIO_STT_OPENAI_API_KEY
+app.state.config.STT_ENGINE = AUDIO_STT_ENGINE
+app.state.config.STT_MODEL = AUDIO_STT_MODEL
+
+app.state.config.TTS_OPENAI_API_BASE_URL = AUDIO_TTS_OPENAI_API_BASE_URL
+app.state.config.TTS_OPENAI_API_KEY = AUDIO_TTS_OPENAI_API_KEY
+app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE
+app.state.config.TTS_MODEL = AUDIO_TTS_MODEL
+app.state.config.TTS_VOICE = AUDIO_TTS_VOICE
 
 # setting device type for whisper model
 whisper_device_type = DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu"
@@ -74,41 +85,101 @@ SPEECH_CACHE_DIR = Path(CACHE_DIR).joinpath("./audio/speech/")
 SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 
 
-class OpenAIConfigUpdateForm(BaseModel):
-    url: str
-    key: str
-    model: str
-    speaker: str
+class TTSConfigForm(BaseModel):
+    OPENAI_API_BASE_URL: str
+    OPENAI_API_KEY: str
+    ENGINE: str
+    MODEL: str
+    VOICE: str
+
+
+class STTConfigForm(BaseModel):
+    OPENAI_API_BASE_URL: str
+    OPENAI_API_KEY: str
+    ENGINE: str
+    MODEL: str
+
+
+class AudioConfigUpdateForm(BaseModel):
+    tts: TTSConfigForm
+    stt: STTConfigForm
+
+
+from pydub import AudioSegment
+from pydub.utils import mediainfo
+
+
+def is_mp4_audio(file_path):
+    """Check if the given file is an MP4 audio file."""
+    if not os.path.isfile(file_path):
+        print(f"File not found: {file_path}")
+        return False
+
+    info = mediainfo(file_path)
+    if (
+        info.get("codec_name") == "aac"
+        and info.get("codec_type") == "audio"
+        and info.get("codec_tag_string") == "mp4a"
+    ):
+        return True
+    return False
+
+
+def convert_mp4_to_wav(file_path, output_path):
+    """Convert MP4 audio file to WAV format."""
+    audio = AudioSegment.from_file(file_path, format="mp4")
+    audio.export(output_path, format="wav")
+    print(f"Converted {file_path} to {output_path}")
 
 
 @app.get("/config")
-async def get_openai_config(user=Depends(get_admin_user)):
+async def get_audio_config(user=Depends(get_admin_user)):
     return {
-        "OPENAI_API_BASE_URL": app.state.config.OPENAI_API_BASE_URL,
-        "OPENAI_API_KEY": app.state.config.OPENAI_API_KEY,
-        "OPENAI_API_MODEL": app.state.config.OPENAI_API_MODEL,
-        "OPENAI_API_VOICE": app.state.config.OPENAI_API_VOICE,
+        "tts": {
+            "OPENAI_API_BASE_URL": app.state.config.TTS_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": app.state.config.TTS_OPENAI_API_KEY,
+            "ENGINE": app.state.config.TTS_ENGINE,
+            "MODEL": app.state.config.TTS_MODEL,
+            "VOICE": app.state.config.TTS_VOICE,
+        },
+        "stt": {
+            "OPENAI_API_BASE_URL": app.state.config.STT_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
+            "ENGINE": app.state.config.STT_ENGINE,
+            "MODEL": app.state.config.STT_MODEL,
+        },
     }
 
 
 @app.post("/config/update")
-async def update_openai_config(
-    form_data: OpenAIConfigUpdateForm, user=Depends(get_admin_user)
+async def update_audio_config(
+    form_data: AudioConfigUpdateForm, user=Depends(get_admin_user)
 ):
-    if form_data.key == "":
-        raise HTTPException(status_code=400, detail=ERROR_MESSAGES.API_KEY_NOT_FOUND)
+    app.state.config.TTS_OPENAI_API_BASE_URL = form_data.tts.OPENAI_API_BASE_URL
+    app.state.config.TTS_OPENAI_API_KEY = form_data.tts.OPENAI_API_KEY
+    app.state.config.TTS_ENGINE = form_data.tts.ENGINE
+    app.state.config.TTS_MODEL = form_data.tts.MODEL
+    app.state.config.TTS_VOICE = form_data.tts.VOICE
 
-    app.state.config.OPENAI_API_BASE_URL = form_data.url
-    app.state.config.OPENAI_API_KEY = form_data.key
-    app.state.config.OPENAI_API_MODEL = form_data.model
-    app.state.config.OPENAI_API_VOICE = form_data.speaker
+    app.state.config.STT_OPENAI_API_BASE_URL = form_data.stt.OPENAI_API_BASE_URL
+    app.state.config.STT_OPENAI_API_KEY = form_data.stt.OPENAI_API_KEY
+    app.state.config.STT_ENGINE = form_data.stt.ENGINE
+    app.state.config.STT_MODEL = form_data.stt.MODEL
 
     return {
-        "status": True,
-        "OPENAI_API_BASE_URL": app.state.config.OPENAI_API_BASE_URL,
-        "OPENAI_API_KEY": app.state.config.OPENAI_API_KEY,
-        "OPENAI_API_MODEL": app.state.config.OPENAI_API_MODEL,
-        "OPENAI_API_VOICE": app.state.config.OPENAI_API_VOICE,
+        "tts": {
+            "OPENAI_API_BASE_URL": app.state.config.TTS_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": app.state.config.TTS_OPENAI_API_KEY,
+            "ENGINE": app.state.config.TTS_ENGINE,
+            "MODEL": app.state.config.TTS_MODEL,
+            "VOICE": app.state.config.TTS_VOICE,
+        },
+        "stt": {
+            "OPENAI_API_BASE_URL": app.state.config.STT_OPENAI_API_BASE_URL,
+            "OPENAI_API_KEY": app.state.config.STT_OPENAI_API_KEY,
+            "ENGINE": app.state.config.STT_ENGINE,
+            "MODEL": app.state.config.STT_MODEL,
+        },
     }
 
 
@@ -125,13 +196,21 @@ async def speech(request: Request, user=Depends(get_verified_user)):
         return FileResponse(file_path)
 
     headers = {}
-    headers["Authorization"] = f"Bearer {app.state.config.OPENAI_API_KEY}"
+    headers["Authorization"] = f"Bearer {app.state.config.TTS_OPENAI_API_KEY}"
     headers["Content-Type"] = "application/json"
 
+    try:
+        body = body.decode("utf-8")
+        body = json.loads(body)
+        body["model"] = app.state.config.TTS_MODEL
+        body = json.dumps(body).encode("utf-8")
+    except Exception as e:
+        pass
+
     r = None
     try:
         r = requests.post(
-            url=f"{app.state.config.OPENAI_API_BASE_URL}/audio/speech",
+            url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
             data=body,
             headers=headers,
             stream=True,
@@ -181,41 +260,110 @@ def transcribe(
         )
 
     try:
-        filename = file.filename
-        file_path = f"{UPLOAD_DIR}/{filename}"
+        ext = file.filename.split(".")[-1]
+
+        id = uuid.uuid4()
+        filename = f"{id}.{ext}"
+
+        file_dir = f"{CACHE_DIR}/audio/transcriptions"
+        os.makedirs(file_dir, exist_ok=True)
+        file_path = f"{file_dir}/{filename}"
+
+        print(filename)
+
         contents = file.file.read()
         with open(file_path, "wb") as f:
             f.write(contents)
             f.close()
 
-        whisper_kwargs = {
-            "model_size_or_path": WHISPER_MODEL,
-            "device": whisper_device_type,
-            "compute_type": "int8",
-            "download_root": WHISPER_MODEL_DIR,
-            "local_files_only": not WHISPER_MODEL_AUTO_UPDATE,
-        }
+        if app.state.config.STT_ENGINE == "":
+            whisper_kwargs = {
+                "model_size_or_path": WHISPER_MODEL,
+                "device": whisper_device_type,
+                "compute_type": "int8",
+                "download_root": WHISPER_MODEL_DIR,
+                "local_files_only": not WHISPER_MODEL_AUTO_UPDATE,
+            }
 
-        log.debug(f"whisper_kwargs: {whisper_kwargs}")
+            log.debug(f"whisper_kwargs: {whisper_kwargs}")
 
-        try:
-            model = WhisperModel(**whisper_kwargs)
-        except:
-            log.warning(
-                "WhisperModel initialization failed, attempting download with local_files_only=False"
+            try:
+                model = WhisperModel(**whisper_kwargs)
+            except:
+                log.warning(
+                    "WhisperModel initialization failed, attempting download with local_files_only=False"
+                )
+                whisper_kwargs["local_files_only"] = False
+                model = WhisperModel(**whisper_kwargs)
+
+            segments, info = model.transcribe(file_path, beam_size=5)
+            log.info(
+                "Detected language '%s' with probability %f"
+                % (info.language, info.language_probability)
             )
-            whisper_kwargs["local_files_only"] = False
-            model = WhisperModel(**whisper_kwargs)
 
-        segments, info = model.transcribe(file_path, beam_size=5)
-        log.info(
-            "Detected language '%s' with probability %f"
-            % (info.language, info.language_probability)
-        )
+            transcript = "".join([segment.text for segment in list(segments)])
 
-        transcript = "".join([segment.text for segment in list(segments)])
+            data = {"text": transcript.strip()}
 
-        return {"text": transcript.strip()}
+            # save the transcript to a json file
+            transcript_file = f"{file_dir}/{id}.json"
+            with open(transcript_file, "w") as f:
+                json.dump(data, f)
+
+            print(data)
+
+            return data
+
+        elif app.state.config.STT_ENGINE == "openai":
+            if is_mp4_audio(file_path):
+                print("is_mp4_audio")
+                os.rename(file_path, file_path.replace(".wav", ".mp4"))
+                # Convert MP4 audio file to WAV format
+                convert_mp4_to_wav(file_path.replace(".wav", ".mp4"), file_path)
+
+            headers = {"Authorization": f"Bearer {app.state.config.STT_OPENAI_API_KEY}"}
+
+            files = {"file": (filename, open(file_path, "rb"))}
+            data = {"model": "whisper-1"}
+
+            print(files, data)
+
+            r = None
+            try:
+                r = requests.post(
+                    url=f"{app.state.config.STT_OPENAI_API_BASE_URL}/audio/transcriptions",
+                    headers=headers,
+                    files=files,
+                    data=data,
+                )
+
+                r.raise_for_status()
+
+                data = r.json()
+
+                # save the transcript to a json file
+                transcript_file = f"{file_dir}/{id}.json"
+                with open(transcript_file, "w") as f:
+                    json.dump(data, f)
+
+                print(data)
+                return data
+            except Exception as e:
+                log.exception(e)
+                error_detail = "Open WebUI: Server Connection Error"
+                if r is not None:
+                    try:
+                        res = r.json()
+                        if "error" in res:
+                            error_detail = f"External: {res['error']['message']}"
+                    except:
+                        error_detail = f"External: {e}"
+
+                raise HTTPException(
+                    status_code=r.status_code if r != None else 500,
+                    detail=error_detail,
+                )
 
     except Exception as e:
         log.exception(e)

backend/apps/ollama/main.py

@@ -41,8 +41,6 @@ from utils.utils import (
     get_admin_user,
 )
 
-from utils.models import get_model_id_from_custom_model_id
-
 
 from config import (
     SRC_LOG_LEVELS,
@@ -274,54 +272,57 @@ async def get_ollama_tags(
 @app.get("/api/version")
 @app.get("/api/version/{url_idx}")
 async def get_ollama_versions(url_idx: Optional[int] = None):
+    if app.state.config.ENABLE_OLLAMA_API:
+        if url_idx == None:
 
-    if url_idx == None:
+            # returns lowest version
+            tasks = [
+                fetch_url(f"{url}/api/version")
+                for url in app.state.config.OLLAMA_BASE_URLS
+            ]
+            responses = await asyncio.gather(*tasks)
+            responses = list(filter(lambda x: x is not None, responses))
 
-        # returns lowest version
-        tasks = [
-            fetch_url(f"{url}/api/version") for url in app.state.config.OLLAMA_BASE_URLS
-        ]
-        responses = await asyncio.gather(*tasks)
-        responses = list(filter(lambda x: x is not None, responses))
+            if len(responses) > 0:
+                lowest_version = min(
+                    responses,
+                    key=lambda x: tuple(
+                        map(int, re.sub(r"^v|-.*", "", x["version"]).split("."))
+                    ),
+                )
 
-        if len(responses) > 0:
-            lowest_version = min(
-                responses,
-                key=lambda x: tuple(
-                    map(int, re.sub(r"^v|-.*", "", x["version"]).split("."))
-                ),
-            )
-
-            return {"version": lowest_version["version"]}
+                return {"version": lowest_version["version"]}
+            else:
+                raise HTTPException(
+                    status_code=500,
+                    detail=ERROR_MESSAGES.OLLAMA_NOT_FOUND,
+                )
         else:
-            raise HTTPException(
-                status_code=500,
-                detail=ERROR_MESSAGES.OLLAMA_NOT_FOUND,
-            )
+            url = app.state.config.OLLAMA_BASE_URLS[url_idx]
+
+            r = None
+            try:
+                r = requests.request(method="GET", url=f"{url}/api/version")
+                r.raise_for_status()
+
+                return r.json()
+            except Exception as e:
+                log.exception(e)
+                error_detail = "Open WebUI: Server Connection Error"
+                if r is not None:
+                    try:
+                        res = r.json()
+                        if "error" in res:
+                            error_detail = f"Ollama: {res['error']}"
+                    except:
+                        error_detail = f"Ollama: {e}"
+
+                raise HTTPException(
+                    status_code=r.status_code if r else 500,
+                    detail=error_detail,
+                )
     else:
-        url = app.state.config.OLLAMA_BASE_URLS[url_idx]
-
-        r = None
-        try:
-            r = requests.request(method="GET", url=f"{url}/api/version")
-            r.raise_for_status()
-
-            return r.json()
-        except Exception as e:
-            log.exception(e)
-            error_detail = "Open WebUI: Server Connection Error"
-            if r is not None:
-                try:
-                    res = r.json()
-                    if "error" in res:
-                        error_detail = f"Ollama: {res['error']}"
-                except:
-                    error_detail = f"Ollama: {e}"
-
-            raise HTTPException(
-                status_code=r.status_code if r else 500,
-                detail=error_detail,
-            )
+        return {"version": False}
 
 
 class ModelNameForm(BaseModel):
@@ -725,7 +726,6 @@ async def generate_chat_completion(
     model_info = Models.get_model_by_id(model_id)
 
     if model_info:
-        print(model_info)
         if model_info.base_model_id:
             payload["model"] = model_info.base_model_id
 
@@ -761,7 +761,7 @@ async def generate_chat_completion(
                     "frequency_penalty", None
                 )
 
-            if model_info.params.get("temperature", None):
+            if model_info.params.get("temperature", None) is not None:
                 payload["options"]["temperature"] = model_info.params.get(
                     "temperature", None
                 )
@@ -846,9 +846,14 @@ async def generate_chat_completion(
 
 
 # TODO: we should update this part once Ollama supports other types
+class OpenAIChatMessageContent(BaseModel):
+    type: str
+    model_config = ConfigDict(extra="allow")
+
+
 class OpenAIChatMessage(BaseModel):
     role: str
-    content: str
+    content: Union[str, OpenAIChatMessageContent]
 
     model_config = ConfigDict(extra="allow")
 
@@ -876,7 +881,6 @@ async def generate_openai_chat_completion(
     model_info = Models.get_model_by_id(model_id)
 
     if model_info:
-        print(model_info)
         if model_info.base_model_id:
             payload["model"] = model_info.base_model_id
 

backend/apps/openai/main.py

@@ -345,113 +345,97 @@ async def get_models(url_idx: Optional[int] = None, user=Depends(get_current_use
             )
 
 
-@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
-async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
+@app.post("/chat/completions")
+@app.post("/chat/completions/{url_idx}")
+async def generate_chat_completion(
+    form_data: dict,
+    url_idx: Optional[int] = None,
+    user=Depends(get_verified_user),
+):
     idx = 0
+    payload = {**form_data}
 
-    body = await request.body()
-    # TODO: Remove below after gpt-4-vision fix from Open AI
-    # Try to decode the body of the request from bytes to a UTF-8 string (Require add max_token to fix gpt-4-vision)
+    model_id = form_data.get("model")
+    model_info = Models.get_model_by_id(model_id)
 
-    payload = None
+    if model_info:
+        if model_info.base_model_id:
+            payload["model"] = model_info.base_model_id
 
-    try:
-        if "chat/completions" in path:
-            body = body.decode("utf-8")
-            body = json.loads(body)
+        model_info.params = model_info.params.model_dump()
 
-            payload = {**body}
+        if model_info.params:
+            if model_info.params.get("temperature", None) is not None:
+                payload["temperature"] = float(model_info.params.get("temperature"))
 
-            model_id = body.get("model")
-            model_info = Models.get_model_by_id(model_id)
+            if model_info.params.get("top_p", None):
+                payload["top_p"] = int(model_info.params.get("top_p", None))
 
-            if model_info:
-                print(model_info)
-                if model_info.base_model_id:
-                    payload["model"] = model_info.base_model_id
+            if model_info.params.get("max_tokens", None):
+                payload["max_tokens"] = int(model_info.params.get("max_tokens", None))
 
-                model_info.params = model_info.params.model_dump()
+            if model_info.params.get("frequency_penalty", None):
+                payload["frequency_penalty"] = int(
+                    model_info.params.get("frequency_penalty", None)
+                )
 
-                if model_info.params:
-                    if model_info.params.get("temperature", None):
-                        payload["temperature"] = int(
-                            model_info.params.get("temperature")
+            if model_info.params.get("seed", None):
+                payload["seed"] = model_info.params.get("seed", None)
+
+            if model_info.params.get("stop", None):
+                payload["stop"] = (
+                    [
+                        bytes(stop, "utf-8").decode("unicode_escape")
+                        for stop in model_info.params["stop"]
+                    ]
+                    if model_info.params.get("stop", None)
+                    else None
+                )
+
+        if model_info.params.get("system", None):
+            # Check if the payload already has a system message
+            # If not, add a system message to the payload
+            if payload.get("messages"):
+                for message in payload["messages"]:
+                    if message.get("role") == "system":
+                        message["content"] = (
+                            model_info.params.get("system", None) + message["content"]
                         )
+                        break
+                else:
+                    payload["messages"].insert(
+                        0,
+                        {
+                            "role": "system",
+                            "content": model_info.params.get("system", None),
+                        },
+                    )
 
-                    if model_info.params.get("top_p", None):
-                        payload["top_p"] = int(model_info.params.get("top_p", None))
+    else:
+        pass
 
-                    if model_info.params.get("max_tokens", None):
-                        payload["max_tokens"] = int(
-                            model_info.params.get("max_tokens", None)
-                        )
+    model = app.state.MODELS[payload.get("model")]
+    idx = model["urlIdx"]
 
-                    if model_info.params.get("frequency_penalty", None):
-                        payload["frequency_penalty"] = int(
-                            model_info.params.get("frequency_penalty", None)
-                        )
+    if "pipeline" in model and model.get("pipeline"):
+        payload["user"] = {"name": user.name, "id": user.id}
 
-                    if model_info.params.get("seed", None):
-                        payload["seed"] = model_info.params.get("seed", None)
+    # Check if the model is "gpt-4-vision-preview" and set "max_tokens" to 4000
+    # This is a workaround until OpenAI fixes the issue with this model
+    if payload.get("model") == "gpt-4-vision-preview":
+        if "max_tokens" not in payload:
+            payload["max_tokens"] = 4000
+        log.debug("Modified payload:", payload)
 
-                    if model_info.params.get("stop", None):
-                        payload["stop"] = (
-                            [
-                                bytes(stop, "utf-8").decode("unicode_escape")
-                                for stop in model_info.params["stop"]
-                            ]
-                            if model_info.params.get("stop", None)
-                            else None
-                        )
-
-                if model_info.params.get("system", None):
-                    # Check if the payload already has a system message
-                    # If not, add a system message to the payload
-                    if payload.get("messages"):
-                        for message in payload["messages"]:
-                            if message.get("role") == "system":
-                                message["content"] = (
-                                    model_info.params.get("system", None)
-                                    + message["content"]
-                                )
-                                break
-                        else:
-                            payload["messages"].insert(
-                                0,
-                                {
-                                    "role": "system",
-                                    "content": model_info.params.get("system", None),
-                                },
-                            )
-            else:
-                pass
-
-            model = app.state.MODELS[payload.get("model")]
-
-            idx = model["urlIdx"]
-
-            if "pipeline" in model and model.get("pipeline"):
-                payload["user"] = {"name": user.name, "id": user.id}
-
-            # Check if the model is "gpt-4-vision-preview" and set "max_tokens" to 4000
-            # This is a workaround until OpenAI fixes the issue with this model
-            if payload.get("model") == "gpt-4-vision-preview":
-                if "max_tokens" not in payload:
-                    payload["max_tokens"] = 4000
-                log.debug("Modified payload:", payload)
-
-            # Convert the modified body back to JSON
-            payload = json.dumps(payload)
-
-    except json.JSONDecodeError as e:
-        log.error("Error loading request body into a dictionary:", e)
+    # Convert the modified body back to JSON
+    payload = json.dumps(payload)
 
     print(payload)
 
     url = app.state.config.OPENAI_API_BASE_URLS[idx]
     key = app.state.config.OPENAI_API_KEYS[idx]
 
-    target_url = f"{url}/{path}"
+    print(payload)
 
     headers = {}
     headers["Authorization"] = f"Bearer {key}"
@@ -464,9 +448,72 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
     try:
         session = aiohttp.ClientSession(trust_env=True)
         r = await session.request(
-            method=request.method,
-            url=target_url,
-            data=payload if payload else body,
+            method="POST",
+            url=f"{url}/chat/completions",
+            data=payload,
+            headers=headers,
+        )
+
+        r.raise_for_status()
+
+        # Check if response is SSE
+        if "text/event-stream" in r.headers.get("Content-Type", ""):
+            streaming = True
+            return StreamingResponse(
+                r.content,
+                status_code=r.status,
+                headers=dict(r.headers),
+                background=BackgroundTask(
+                    cleanup_response, response=r, session=session
+                ),
+            )
+        else:
+            response_data = await r.json()
+            return response_data
+    except Exception as e:
+        log.exception(e)
+        error_detail = "Open WebUI: Server Connection Error"
+        if r is not None:
+            try:
+                res = await r.json()
+                print(res)
+                if "error" in res:
+                    error_detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
+            except:
+                error_detail = f"External: {e}"
+        raise HTTPException(status_code=r.status if r else 500, detail=error_detail)
+    finally:
+        if not streaming and session:
+            if r:
+                r.close()
+            await session.close()
+
+
+@app.api_route("/{path:path}", methods=["GET", "POST", "PUT", "DELETE"])
+async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
+    idx = 0
+
+    body = await request.body()
+
+    url = app.state.config.OPENAI_API_BASE_URLS[idx]
+    key = app.state.config.OPENAI_API_KEYS[idx]
+
+    target_url = f"{url}/{path}"
+
+    headers = {}
+    headers["Authorization"] = f"Bearer {key}"
+    headers["Content-Type"] = "application/json"
+
+    r = None
+    session = None
+    streaming = False
+
+    try:
+        session = aiohttp.ClientSession(trust_env=True)
+        r = await session.request(
+            method=request.method,
+            url=target_url,
+            data=body,
             headers=headers,
         )
 

backend/apps/rag/main.py

@@ -9,6 +9,7 @@ from fastapi import (
 )
 from fastapi.middleware.cors import CORSMiddleware
 import os, shutil, logging, re
+from datetime import datetime
 
 from pathlib import Path
 from typing import List, Union, Sequence
@@ -30,6 +31,7 @@ from langchain_community.document_loaders import (
     UnstructuredExcelLoader,
     UnstructuredPowerPointLoader,
     YoutubeLoader,
+    OutlookMessageLoader,
 )
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 
@@ -67,7 +69,7 @@ from apps.rag.search.main import SearchResult
 from apps.rag.search.searxng import search_searxng
 from apps.rag.search.serper import search_serper
 from apps.rag.search.serpstack import search_serpstack
-
+from apps.rag.search.serply import search_serply
 
 from utils.misc import (
     calculate_sha256,
@@ -113,6 +115,7 @@ from config import (
     SERPSTACK_API_KEY,
     SERPSTACK_HTTPS,
     SERPER_API_KEY,
+    SERPLY_API_KEY,
     RAG_WEB_SEARCH_RESULT_COUNT,
     RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
     RAG_EMBEDDING_OPENAI_BATCH_SIZE,
@@ -165,6 +168,7 @@ app.state.config.BRAVE_SEARCH_API_KEY = BRAVE_SEARCH_API_KEY
 app.state.config.SERPSTACK_API_KEY = SERPSTACK_API_KEY
 app.state.config.SERPSTACK_HTTPS = SERPSTACK_HTTPS
 app.state.config.SERPER_API_KEY = SERPER_API_KEY
+app.state.config.SERPLY_API_KEY = SERPLY_API_KEY
 app.state.config.RAG_WEB_SEARCH_RESULT_COUNT = RAG_WEB_SEARCH_RESULT_COUNT
 app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS = RAG_WEB_SEARCH_CONCURRENT_REQUESTS
 
@@ -392,6 +396,7 @@ async def get_rag_config(user=Depends(get_admin_user)):
                 "serpstack_api_key": app.state.config.SERPSTACK_API_KEY,
                 "serpstack_https": app.state.config.SERPSTACK_HTTPS,
                 "serper_api_key": app.state.config.SERPER_API_KEY,
+                "serply_api_key": app.state.config.SERPLY_API_KEY,
                 "result_count": app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
                 "concurrent_requests": app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
             },
@@ -419,6 +424,7 @@ class WebSearchConfig(BaseModel):
     serpstack_api_key: Optional[str] = None
     serpstack_https: Optional[bool] = None
     serper_api_key: Optional[str] = None
+    serply_api_key: Optional[str] = None
     result_count: Optional[int] = None
     concurrent_requests: Optional[int] = None
 
@@ -469,6 +475,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
         app.state.config.SERPSTACK_API_KEY = form_data.web.search.serpstack_api_key
         app.state.config.SERPSTACK_HTTPS = form_data.web.search.serpstack_https
         app.state.config.SERPER_API_KEY = form_data.web.search.serper_api_key
+        app.state.config.SERPLY_API_KEY = form_data.web.search.serply_api_key
         app.state.config.RAG_WEB_SEARCH_RESULT_COUNT = form_data.web.search.result_count
         app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS = (
             form_data.web.search.concurrent_requests
@@ -497,6 +504,7 @@ async def update_rag_config(form_data: ConfigUpdateForm, user=Depends(get_admin_
                 "serpstack_api_key": app.state.config.SERPSTACK_API_KEY,
                 "serpstack_https": app.state.config.SERPSTACK_HTTPS,
                 "serper_api_key": app.state.config.SERPER_API_KEY,
+                "serply_api_key": app.state.config.SERPLY_API_KEY,
                 "result_count": app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
                 "concurrent_requests": app.state.config.RAG_WEB_SEARCH_CONCURRENT_REQUESTS,
             },
@@ -744,6 +752,7 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
     - BRAVE_SEARCH_API_KEY
     - SERPSTACK_API_KEY
     - SERPER_API_KEY
+    - SERPLY_API_KEY
 
     Args:
         query (str): The query to search for
@@ -802,6 +811,15 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
             )
         else:
             raise Exception("No SERPER_API_KEY found in environment variables")
+    elif engine == "serply":
+        if app.state.config.SERPLY_API_KEY:
+            return search_serply(
+                app.state.config.SERPLY_API_KEY,
+                query,
+                app.state.config.RAG_WEB_SEARCH_RESULT_COUNT,
+            )
+        else:
+            raise Exception("No SERPLY_API_KEY found in environment variables")
     else:
         raise Exception("No search engine API key found in environment variables")
 
@@ -809,6 +827,7 @@ def search_web(engine: str, query: str) -> list[SearchResult]:
 @app.post("/web/search")
 def store_web_search(form_data: SearchForm, user=Depends(get_current_user)):
     try:
+        logging.info(f"trying to web search with {app.state.config.RAG_WEB_SEARCH_ENGINE, form_data.query}")
         web_results = search_web(
             app.state.config.RAG_WEB_SEARCH_ENGINE, form_data.query
         )
@@ -879,6 +898,13 @@ def store_docs_in_vector_db(docs, collection_name, overwrite: bool = False) -> b
     texts = [doc.page_content for doc in docs]
     metadatas = [doc.metadata for doc in docs]
 
+    # ChromaDB does not like datetime formats
+    # for meta-data so convert them to string.
+    for metadata in metadatas:
+        for key, value in metadata.items():
+            if isinstance(value, datetime):
+                metadata[key] = str(value)
+
     try:
         if overwrite:
             for collection in CHROMA_CLIENT.list_collections():
@@ -965,6 +991,7 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
         "swift",
         "vue",
         "svelte",
+        "msg",
     ]
 
     if file_ext == "pdf":
@@ -999,6 +1026,8 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
         "application/vnd.openxmlformats-officedocument.presentationml.presentation",
     ] or file_ext in ["ppt", "pptx"]:
         loader = UnstructuredPowerPointLoader(file_path)
+    elif file_ext == "msg":
+        loader = OutlookMessageLoader(file_path)
     elif file_ext in known_source_ext or (
         file_content_type and file_content_type.find("text/") >= 0
     ):
@@ -1164,6 +1193,30 @@ def reset_vector_db(user=Depends(get_admin_user)):
     CHROMA_CLIENT.reset()
 
 
+@app.get("/reset/uploads")
+def reset_upload_dir(user=Depends(get_admin_user)) -> bool:
+    folder = f"{UPLOAD_DIR}"
+    try:
+        # Check if the directory exists
+        if os.path.exists(folder):
+            # Iterate over all the files and directories in the specified directory
+            for filename in os.listdir(folder):
+                file_path = os.path.join(folder, filename)
+                try:
+                    if os.path.isfile(file_path) or os.path.islink(file_path):
+                        os.unlink(file_path)  # Remove the file or link
+                    elif os.path.isdir(file_path):
+                        shutil.rmtree(file_path)  # Remove the directory
+                except Exception as e:
+                    print(f"Failed to delete {file_path}. Reason: {e}")
+        else:
+            print(f"The directory {folder} does not exist")
+    except Exception as e:
+        print(f"Failed to process the directory {folder}. Reason: {e}")
+
+    return True
+
+
 @app.get("/reset")
 def reset(user=Depends(get_admin_user)) -> bool:
     folder = f"{UPLOAD_DIR}"

backend/apps/rag/search/serply.py

@@ -0,0 +1,68 @@
+import json
+import logging
+
+import requests
+from urllib.parse import urlencode
+
+from apps.rag.search.main import SearchResult
+from config import SRC_LOG_LEVELS
+
+log = logging.getLogger(__name__)
+log.setLevel(SRC_LOG_LEVELS["RAG"])
+
+
+def search_serply(
+        api_key: str,
+        query: str,
+        count: int,
+        hl: str = "us",
+        limit: int = 10,
+        device_type: str = "desktop",
+        proxy_location: str = "US"
+    ) -> list[SearchResult]:
+    """Search using serper.dev's API and return the results as a list of SearchResult objects.
+
+    Args:
+        api_key (str): A serply.io API key
+        query (str): The query to search for
+        hl (str): Host Language code to display results in (reference https://developers.google.com/custom-search/docs/xml_results?hl=en#wsInterfaceLanguages)
+        limit (int): The maximum number of results to return [10-100, defaults to 10]
+    """
+    log.info("Searching with Serply")
+
+    url = "https://api.serply.io/v1/search/"
+
+    query_payload = {
+        "q": query,
+        "language": "en",
+        "num": limit,
+        "gl": proxy_location.upper(),
+        "hl": hl.lower()
+    }
+
+    url = f"{url}{urlencode(query_payload)}"
+    headers = {
+        "X-API-KEY": api_key,
+        "X-User-Agent": device_type,
+        "User-Agent": "open-webui",
+        "X-Proxy-Location": proxy_location
+    }
+
+    response = requests.request("GET", url, headers=headers)
+    response.raise_for_status()
+
+    json_response = response.json()
+    log.info(f"results from serply search: {json_response}")
+
+    results = sorted(
+        json_response.get("results", []), key=lambda x: x.get("realPosition", 0)
+    )
+
+    return [
+        SearchResult(
+            link=result["link"],
+            title=result.get("title"),
+            snippet=result.get("description"),
+        )
+        for result in results[:count]
+    ]

backend/apps/rag/search/testdata/serply.json

@@ -0,0 +1,206 @@
+{
+	"ads": [],
+	"ads_count": 0,
+	"answers": [],
+	"results": [
+		{
+			"title": "Apple",
+			"link": "https://www.apple.com/",
+			"description": "Discover the innovative world of Apple and shop everything iPhone, iPad, Apple Watch, Mac, and Apple TV, plus explore accessories, entertainment, ...",
+			"additional_links": [
+				{
+					"text": "AppleApplehttps://www.apple.com",
+					"href": "https://www.apple.com/"
+				}
+			],
+			"cite": {},
+			"subdomains": [
+				{
+					"title": "Support",
+					"link": "https://support.apple.com/",
+					"description": "SupportContact - iPhone Support - Billing and Subscriptions - Apple Repair"
+				},
+				{
+					"title": "Store",
+					"link": "https://www.apple.com/store",
+					"description": "StoreShop iPhone - Shop iPad - App Store - Shop Mac - ..."
+				},
+				{
+					"title": "Mac",
+					"link": "https://www.apple.com/mac/",
+					"description": "MacMacBook Air - MacBook Pro - iMac - Compare Mac models - Mac mini"
+				},
+				{
+					"title": "iPad",
+					"link": "https://www.apple.com/ipad/",
+					"description": "iPadShop iPad - iPad Pro - iPad Air - Compare iPad models - ..."
+				},
+				{
+					"title": "Watch",
+					"link": "https://www.apple.com/watch/",
+					"description": "WatchShop Apple Watch - Series 9 - SE - Ultra 2 - Nike - Hermès - ..."
+				}
+			],
+			"realPosition": 1
+		},
+		{
+			"title": "Apple",
+			"link": "https://www.apple.com/",
+			"description": "Discover the innovative world of Apple and shop everything iPhone, iPad, Apple Watch, Mac, and Apple TV, plus explore accessories, entertainment, ...",
+			"additional_links": [
+				{
+					"text": "AppleApplehttps://www.apple.com",
+					"href": "https://www.apple.com/"
+				}
+			],
+			"cite": {},
+			"realPosition": 2
+		},
+		{
+			"title": "Apple Inc.",
+			"link": "https://en.wikipedia.org/wiki/Apple_Inc.",
+			"description": "Apple Inc. (formerly Apple Computer, Inc.) is an American multinational corporation and technology company headquartered in Cupertino, California, ...",
+			"additional_links": [
+				{
+					"text": "Apple Inc.Wikipediahttps://en.wikipedia.org › wiki › Apple_Inc",
+					"href": "https://en.wikipedia.org/wiki/Apple_Inc."
+				},
+				{
+					"text": "",
+					"href": "https://en.wikipedia.org/wiki/Apple_Inc."
+				},
+				{
+					"text": "History",
+					"href": "https://en.wikipedia.org/wiki/History_of_Apple_Inc."
+				},
+				{
+					"text": "List of Apple products",
+					"href": "https://en.wikipedia.org/wiki/List_of_Apple_products"
+				},
+				{
+					"text": "Litigation involving Apple Inc.",
+					"href": "https://en.wikipedia.org/wiki/Litigation_involving_Apple_Inc."
+				},
+				{
+					"text": "Apple Park",
+					"href": "https://en.wikipedia.org/wiki/Apple_Park"
+				}
+			],
+			"cite": {
+				"domain": "https://en.wikipedia.org › wiki › Apple_Inc",
+				"span": " › wiki › Apple_Inc"
+			},
+			"realPosition": 3
+		},
+		{
+			"title": "Apple Inc. (AAPL) Company Profile & Facts",
+			"link": "https://finance.yahoo.com/quote/AAPL/profile/",
+			"description": "Apple Inc. designs, manufactures, and markets smartphones, personal computers, tablets, wearables, and accessories worldwide. The company offers iPhone, a line ...",
+			"additional_links": [
+				{
+					"text": "Apple Inc. (AAPL) Company Profile & FactsYahoo Financehttps://finance.yahoo.com › quote › AAPL › profile",
+					"href": "https://finance.yahoo.com/quote/AAPL/profile/"
+				}
+			],
+			"cite": {
+				"domain": "https://finance.yahoo.com › quote › AAPL › profile",
+				"span": " › quote › AAPL › profile"
+			},
+			"realPosition": 4
+		},
+		{
+			"title": "Apple Inc - Company Profile and News",
+			"link": "https://www.bloomberg.com/profile/company/AAPL:US",
+			"description": "Apple Inc. Apple Inc. designs, manufactures, and markets smartphones, personal computers, tablets, wearables and accessories, and sells a variety of related ...",
+			"additional_links": [
+				{
+					"text": "Apple Inc - Company Profile and NewsBloomberghttps://www.bloomberg.com › company › AAPL:US",
+					"href": "https://www.bloomberg.com/profile/company/AAPL:US"
+				},
+				{
+					"text": "",
+					"href": "https://www.bloomberg.com/profile/company/AAPL:US"
+				}
+			],
+			"cite": {
+				"domain": "https://www.bloomberg.com › company › AAPL:US",
+				"span": " › company › AAPL:US"
+			},
+			"realPosition": 5
+		},
+		{
+			"title": "Apple Inc. | History, Products, Headquarters, & Facts",
+			"link": "https://www.britannica.com/money/Apple-Inc",
+			"description": "May 22, 2024 — Apple Inc. is an American multinational technology company that revolutionized the technology sector through its innovation of computer ...",
+			"additional_links": [
+				{
+					"text": "Apple Inc. | History, Products, Headquarters, & FactsBritannicahttps://www.britannica.com › money › Apple-Inc",
+					"href": "https://www.britannica.com/money/Apple-Inc"
+				},
+				{
+					"text": "",
+					"href": "https://www.britannica.com/money/Apple-Inc"
+				}
+			],
+			"cite": {
+				"domain": "https://www.britannica.com › money › Apple-Inc",
+				"span": " › money › Apple-Inc"
+			},
+			"realPosition": 6
+		}
+	],
+	"shopping_ads": [],
+	"places": [
+		{
+			"title": "Apple Inc."
+		},
+		{
+			"title": "Apple Inc"
+		},
+		{
+			"title": "Apple Inc"
+		}
+	],
+	"related_searches": {
+		"images": [],
+		"text": [
+			{
+				"title": "apple inc full form",
+				"link": "https://www.google.com/search?sca_esv=6b6df170a5c9891b&sca_upv=1&q=Apple+Inc+full+form&sa=X&ved=2ahUKEwjLxuSJwM-GAxUHODQIHYuJBhgQ1QJ6BAhPEAE"
+			},
+			{
+				"title": "apple company history",
+				"link": "https://www.google.com/search?sca_esv=6b6df170a5c9891b&sca_upv=1&q=Apple+company+history&sa=X&ved=2ahUKEwjLxuSJwM-GAxUHODQIHYuJBhgQ1QJ6BAhOEAE"
+			},
+			{
+				"title": "apple store",
+				"link": "https://www.google.com/search?sca_esv=6b6df170a5c9891b&sca_upv=1&q=Apple+Store&sa=X&ved=2ahUKEwjLxuSJwM-GAxUHODQIHYuJBhgQ1QJ6BAhQEAE"
+			},
+			{
+				"title": "apple id",
+				"link": "https://www.google.com/search?sca_esv=6b6df170a5c9891b&sca_upv=1&q=Apple+id&sa=X&ved=2ahUKEwjLxuSJwM-GAxUHODQIHYuJBhgQ1QJ6BAhSEAE"
+			},
+			{
+				"title": "apple inc industry",
+				"link": "https://www.google.com/search?sca_esv=6b6df170a5c9891b&sca_upv=1&q=Apple+Inc+industry&sa=X&ved=2ahUKEwjLxuSJwM-GAxUHODQIHYuJBhgQ1QJ6BAhREAE"
+			},
+			{
+				"title": "apple login",
+				"link": "https://www.google.com/search?sca_esv=6b6df170a5c9891b&sca_upv=1&q=Apple+login&sa=X&ved=2ahUKEwjLxuSJwM-GAxUHODQIHYuJBhgQ1QJ6BAhTEAE"
+			}
+		]
+	},
+	"image_results": [],
+	"carousel": [],
+	"total": 2450000000,
+	"knowledge_graph": "",
+	"related_questions": [
+		"What does the Apple Inc do?",
+		"Why did Apple change to Apple Inc?",
+		"Who owns Apple Inc.?",
+		"What is Apple Inc best known for?"
+	],
+	"carousel_count": 0,
+	"ts": 2.491065263748169,
+	"device_type": null
+}

backend/apps/rag/utils.py

@@ -20,7 +20,7 @@ from langchain.retrievers import (
 
 from typing import Optional
 
-
+from utils.misc import get_last_user_message, add_or_update_system_message
 from config import SRC_LOG_LEVELS, CHROMA_CLIENT
 
 log = logging.getLogger(__name__)
@@ -247,31 +247,7 @@ def rag_messages(
     hybrid_search,
 ):
     log.debug(f"docs: {docs} {messages} {embedding_function} {reranking_function}")
-
-    last_user_message_idx = None
-    for i in range(len(messages) - 1, -1, -1):
-        if messages[i]["role"] == "user":
-            last_user_message_idx = i
-            break
-
-    user_message = messages[last_user_message_idx]
-
-    if isinstance(user_message["content"], list):
-        # Handle list content input
-        content_type = "list"
-        query = ""
-        for content_item in user_message["content"]:
-            if content_item["type"] == "text":
-                query = content_item["text"]
-                break
-    elif isinstance(user_message["content"], str):
-        # Handle text content input
-        content_type = "text"
-        query = user_message["content"]
-    else:
-        # Fallback in case the input does not match expected types
-        content_type = None
-        query = ""
+    query = get_last_user_message(messages)
 
     extracted_collections = []
     relevant_contexts = []
@@ -349,24 +325,7 @@ def rag_messages(
     )
 
     log.debug(f"ra_content: {ra_content}")
-
-    if content_type == "list":
-        new_content = []
-        for content_item in user_message["content"]:
-            if content_item["type"] == "text":
-                # Update the text item's content with ra_content
-                new_content.append({"type": "text", "text": ra_content})
-            else:
-                # Keep other types of content as they are
-                new_content.append(content_item)
-        new_user_message = {**user_message, "content": new_content}
-    else:
-        new_user_message = {
-            **user_message,
-            "content": ra_content,
-        }
-
-    messages[last_user_message_idx] = new_user_message
+    messages = add_or_update_system_message(ra_content, messages)
 
     return messages, citations
 

backend/apps/socket/main.py

@@ -0,0 +1,151 @@
+import socketio
+import asyncio
+
+
+from apps.webui.models.users import Users
+from utils.utils import decode_token
+
+sio = socketio.AsyncServer(cors_allowed_origins=[], async_mode="asgi")
+app = socketio.ASGIApp(sio, socketio_path="/ws/socket.io")
+
+# Dictionary to maintain the user pool
+
+SESSION_POOL = {}
+USER_POOL = {}
+USAGE_POOL = {}
+# Timeout duration in seconds
+TIMEOUT_DURATION = 3
+
+
+@sio.event
+async def connect(sid, environ, auth):
+    print("connect ", sid)
+
+    user = None
+    if auth and "token" in auth:
+        data = decode_token(auth["token"])
+
+        if data is not None and "id" in data:
+            user = Users.get_user_by_id(data["id"])
+
+        if user:
+            SESSION_POOL[sid] = user.id
+            if user.id in USER_POOL:
+                USER_POOL[user.id].append(sid)
+            else:
+                USER_POOL[user.id] = [sid]
+
+            print(f"user {user.name}({user.id}) connected with session ID {sid}")
+
+            print(len(set(USER_POOL)))
+            await sio.emit("user-count", {"count": len(set(USER_POOL))})
+            await sio.emit("usage", {"models": get_models_in_use()})
+
+
+@sio.on("user-join")
+async def user_join(sid, data):
+    print("user-join", sid, data)
+
+    auth = data["auth"] if "auth" in data else None
+
+    if auth and "token" in auth:
+        data = decode_token(auth["token"])
+
+        if data is not None and "id" in data:
+            user = Users.get_user_by_id(data["id"])
+
+        if user:
+
+            SESSION_POOL[sid] = user.id
+            if user.id in USER_POOL:
+                USER_POOL[user.id].append(sid)
+            else:
+                USER_POOL[user.id] = [sid]
+
+            print(f"user {user.name}({user.id}) connected with session ID {sid}")
+
+            print(len(set(USER_POOL)))
+            await sio.emit("user-count", {"count": len(set(USER_POOL))})
+
+
+@sio.on("user-count")
+async def user_count(sid):
+    print("user-count", sid)
+    await sio.emit("user-count", {"count": len(set(USER_POOL))})
+
+
+def get_models_in_use():
+    # Aggregate all models in use
+    models_in_use = []
+    for model_id, data in USAGE_POOL.items():
+        models_in_use.append(model_id)
+    print(f"Models in use: {models_in_use}")
+
+    return models_in_use
+
+
+@sio.on("usage")
+async def usage(sid, data):
+    print(f'Received "usage" event from {sid}: {data}')
+
+    model_id = data["model"]
+
+    # Cancel previous callback if there is one
+    if model_id in USAGE_POOL:
+        USAGE_POOL[model_id]["callback"].cancel()
+
+    # Store the new usage data and task
+
+    if model_id in USAGE_POOL:
+        USAGE_POOL[model_id]["sids"].append(sid)
+        USAGE_POOL[model_id]["sids"] = list(set(USAGE_POOL[model_id]["sids"]))
+
+    else:
+        USAGE_POOL[model_id] = {"sids": [sid]}
+
+    # Schedule a task to remove the usage data after TIMEOUT_DURATION
+    USAGE_POOL[model_id]["callback"] = asyncio.create_task(
+        remove_after_timeout(sid, model_id)
+    )
+
+    # Broadcast the usage data to all clients
+    await sio.emit("usage", {"models": get_models_in_use()})
+
+
+async def remove_after_timeout(sid, model_id):
+    try:
+        print("remove_after_timeout", sid, model_id)
+        await asyncio.sleep(TIMEOUT_DURATION)
+        if model_id in USAGE_POOL:
+            print(USAGE_POOL[model_id]["sids"])
+            USAGE_POOL[model_id]["sids"].remove(sid)
+            USAGE_POOL[model_id]["sids"] = list(set(USAGE_POOL[model_id]["sids"]))
+
+            if len(USAGE_POOL[model_id]["sids"]) == 0:
+                del USAGE_POOL[model_id]
+
+            print(f"Removed usage data for {model_id} due to timeout")
+            # Broadcast the usage data to all clients
+            await sio.emit("usage", {"models": get_models_in_use()})
+    except asyncio.CancelledError:
+        # Task was cancelled due to new 'usage' event
+        pass
+
+
+@sio.event
+async def disconnect(sid):
+    if sid in SESSION_POOL:
+        user_id = SESSION_POOL[sid]
+        del SESSION_POOL[sid]
+
+        USER_POOL[user_id].remove(sid)
+
+        if len(USER_POOL[user_id]) == 0:
+            del USER_POOL[user_id]
+
+        print(f"user {user_id} disconnected with session ID {sid}")
+        print(USER_POOL)
+
+        await sio.emit("user-count", {"count": len(USER_POOL)})
+    else:
+        print(f"Unknown session ID {sid} disconnected")

backend/config.py

@@ -306,7 +306,11 @@ STATIC_DIR = Path(os.getenv("STATIC_DIR", BACKEND_DIR / "static")).resolve()
 
 frontend_favicon = FRONTEND_BUILD_DIR / "favicon.png"
 if frontend_favicon.exists():
-    shutil.copyfile(frontend_favicon, STATIC_DIR / "favicon.png")
+    try:
+        shutil.copyfile(frontend_favicon, STATIC_DIR / "favicon.png")
+    except Exception as e:
+        logging.error(f"An error occurred: {e}")
+
 else:
     logging.warning(f"Frontend favicon not found at {frontend_favicon}")
 
@@ -615,6 +619,66 @@ ADMIN_EMAIL = PersistentConfig(
 )
 
 
+####################################
+# TASKS
+####################################
+
+
+TASK_MODEL = PersistentConfig(
+    "TASK_MODEL",
+    "task.model.default",
+    os.environ.get("TASK_MODEL", ""),
+)
+
+TASK_MODEL_EXTERNAL = PersistentConfig(
+    "TASK_MODEL_EXTERNAL",
+    "task.model.external",
+    os.environ.get("TASK_MODEL_EXTERNAL", ""),
+)
+
+TITLE_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
+    "TITLE_GENERATION_PROMPT_TEMPLATE",
+    "task.title.prompt_template",
+    os.environ.get(
+        "TITLE_GENERATION_PROMPT_TEMPLATE",
+        """Here is the query:
+{{prompt:middletruncate:8000}}
+
+Create a concise, 3-5 word phrase with an emoji as a title for the previous query. Suitable Emojis for the summary can be used to enhance understanding but avoid quotation marks or special formatting. RESPOND ONLY WITH THE TITLE TEXT.
+
+Examples of titles:
+📉 Stock Market Trends
+🍪 Perfect Chocolate Chip Recipe
+Evolution of Music Streaming
+Remote Work Productivity Tips
+Artificial Intelligence in Healthcare
+🎮 Video Game Development Insights""",
+    ),
+)
+
+
+SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE = PersistentConfig(
+    "SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE",
+    "task.search.prompt_template",
+    os.environ.get(
+        "SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE",
+        """You are tasked with generating web search queries. Give me an appropriate query to answer my question for google search. Answer with only the query. Today is {{CURRENT_DATE}}.
+        
+Question:
+{{prompt:end:4000}}""",
+    ),
+)
+
+
+SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD = PersistentConfig(
+    "SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD",
+    "task.search.prompt_length_threshold",
+    os.environ.get(
+        "SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD",
+        100,
+    ),
+)
+
 ####################################
 # WEBUI_SECRET_KEY
 ####################################
@@ -852,6 +916,12 @@ SERPER_API_KEY = PersistentConfig(
     os.getenv("SERPER_API_KEY", ""),
 )
 
+SERPLY_API_KEY = PersistentConfig(
+    "SERPLY_API_KEY",
+    "rag.web.search.serply_api_key",
+    os.getenv("SERPLY_API_KEY", ""),
+)
+
 
 RAG_WEB_SEARCH_RESULT_COUNT = PersistentConfig(
     "RAG_WEB_SEARCH_RESULT_COUNT",
@@ -933,25 +1003,59 @@ IMAGE_GENERATION_MODEL = PersistentConfig(
 # Audio
 ####################################
 
-AUDIO_OPENAI_API_BASE_URL = PersistentConfig(
-    "AUDIO_OPENAI_API_BASE_URL",
-    "audio.openai.api_base_url",
-    os.getenv("AUDIO_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL),
+AUDIO_STT_OPENAI_API_BASE_URL = PersistentConfig(
+    "AUDIO_STT_OPENAI_API_BASE_URL",
+    "audio.stt.openai.api_base_url",
+    os.getenv("AUDIO_STT_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL),
 )
-AUDIO_OPENAI_API_KEY = PersistentConfig(
-    "AUDIO_OPENAI_API_KEY",
-    "audio.openai.api_key",
-    os.getenv("AUDIO_OPENAI_API_KEY", OPENAI_API_KEY),
+
+AUDIO_STT_OPENAI_API_KEY = PersistentConfig(
+    "AUDIO_STT_OPENAI_API_KEY",
+    "audio.stt.openai.api_key",
+    os.getenv("AUDIO_STT_OPENAI_API_KEY", OPENAI_API_KEY),
 )
-AUDIO_OPENAI_API_MODEL = PersistentConfig(
-    "AUDIO_OPENAI_API_MODEL",
-    "audio.openai.api_model",
-    os.getenv("AUDIO_OPENAI_API_MODEL", "tts-1"),
+
+AUDIO_STT_ENGINE = PersistentConfig(
+    "AUDIO_STT_ENGINE",
+    "audio.stt.engine",
+    os.getenv("AUDIO_STT_ENGINE", ""),
 )
-AUDIO_OPENAI_API_VOICE = PersistentConfig(
-    "AUDIO_OPENAI_API_VOICE",
-    "audio.openai.api_voice",
-    os.getenv("AUDIO_OPENAI_API_VOICE", "alloy"),
+
+AUDIO_STT_MODEL = PersistentConfig(
+    "AUDIO_STT_MODEL",
+    "audio.stt.model",
+    os.getenv("AUDIO_STT_MODEL", "whisper-1"),
+)
+
+AUDIO_TTS_OPENAI_API_BASE_URL = PersistentConfig(
+    "AUDIO_TTS_OPENAI_API_BASE_URL",
+    "audio.tts.openai.api_base_url",
+    os.getenv("AUDIO_TTS_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL),
+)
+AUDIO_TTS_OPENAI_API_KEY = PersistentConfig(
+    "AUDIO_TTS_OPENAI_API_KEY",
+    "audio.tts.openai.api_key",
+    os.getenv("AUDIO_TTS_OPENAI_API_KEY", OPENAI_API_KEY),
+)
+
+
+AUDIO_TTS_ENGINE = PersistentConfig(
+    "AUDIO_TTS_ENGINE",
+    "audio.tts.engine",
+    os.getenv("AUDIO_TTS_ENGINE", ""),
+)
+
+
+AUDIO_TTS_MODEL = PersistentConfig(
+    "AUDIO_TTS_MODEL",
+    "audio.tts.model",
+    os.getenv("AUDIO_TTS_MODEL", "tts-1"),
+)
+
+AUDIO_TTS_VOICE = PersistentConfig(
+    "AUDIO_TTS_VOICE",
+    "audio.tts.voice",
+    os.getenv("AUDIO_TTS_VOICE", "alloy"),
 )
 
 

backend/constants.py

@@ -84,3 +84,7 @@ class ERROR_MESSAGES(str, Enum):
     WEB_SEARCH_ERROR = (
         lambda err="": f"{err if err else 'Oops! Something went wrong while searching the web.'}"
     )
+
+    OLLAMA_API_DISABLED = (
+        "The Ollama API is disabled. Please enable it to use this feature."
+    )

backend/main.py

@@ -9,8 +9,11 @@ import logging
 import aiohttp
 import requests
 import mimetypes
+import shutil
+import os
+import asyncio
 
-from fastapi import FastAPI, Request, Depends, status
+from fastapi import FastAPI, Request, Depends, status, UploadFile, File, Form
 from fastapi.staticfiles import StaticFiles
 from fastapi.responses import JSONResponse
 from fastapi import HTTPException
@@ -20,15 +23,26 @@ from starlette.exceptions import HTTPException as StarletteHTTPException
 from starlette.middleware.base import BaseHTTPMiddleware
 from starlette.responses import StreamingResponse, Response
 
-from apps.ollama.main import app as ollama_app, get_all_models as get_ollama_models
-from apps.openai.main import app as openai_app, get_all_models as get_openai_models
+
+from apps.socket.main import app as socket_app
+from apps.ollama.main import (
+    app as ollama_app,
+    OpenAIChatCompletionForm,
+    get_all_models as get_ollama_models,
+    generate_openai_chat_completion as generate_ollama_chat_completion,
+)
+from apps.openai.main import (
+    app as openai_app,
+    get_all_models as get_openai_models,
+    generate_chat_completion as generate_openai_chat_completion,
+)
 
 from apps.audio.main import app as audio_app
 from apps.images.main import app as images_app
 from apps.rag.main import app as rag_app
 from apps.webui.main import app as webui_app
 
-import asyncio
+
 from pydantic import BaseModel
 from typing import List, Optional
 
@@ -39,6 +53,8 @@ from utils.utils import (
     get_current_user,
     get_http_authorization_cred,
 )
+from utils.task import title_generation_template, search_query_generation_template
+
 from apps.rag.utils import rag_messages
 
 from config import (
@@ -60,8 +76,13 @@ from config import (
     SRC_LOG_LEVELS,
     WEBHOOK_URL,
     ENABLE_ADMIN_EXPORT,
-    AppConfig,
     WEBUI_BUILD_HASH,
+    TASK_MODEL,
+    TASK_MODEL_EXTERNAL,
+    TITLE_GENERATION_PROMPT_TEMPLATE,
+    SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE,
+    SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD,
+    AppConfig,
 )
 from constants import ERROR_MESSAGES
 
@@ -115,10 +136,19 @@ app.state.config.ENABLE_OLLAMA_API = ENABLE_OLLAMA_API
 app.state.config.ENABLE_MODEL_FILTER = ENABLE_MODEL_FILTER
 app.state.config.MODEL_FILTER_LIST = MODEL_FILTER_LIST
 
-
 app.state.config.WEBHOOK_URL = WEBHOOK_URL
 
 
+app.state.config.TASK_MODEL = TASK_MODEL
+app.state.config.TASK_MODEL_EXTERNAL = TASK_MODEL_EXTERNAL
+app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE = TITLE_GENERATION_PROMPT_TEMPLATE
+app.state.config.SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE = (
+    SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE
+)
+app.state.config.SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD = (
+    SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD
+)
+
 app.state.MODELS = {}
 
 origins = ["*"]
@@ -226,6 +256,78 @@ class RAGMiddleware(BaseHTTPMiddleware):
 app.add_middleware(RAGMiddleware)
 
 
+def filter_pipeline(payload, user):
+    user = {"id": user.id, "name": user.name, "role": user.role}
+    model_id = payload["model"]
+    filters = [
+        model
+        for model in app.state.MODELS.values()
+        if "pipeline" in model
+        and "type" in model["pipeline"]
+        and model["pipeline"]["type"] == "filter"
+        and (
+            model["pipeline"]["pipelines"] == ["*"]
+            or any(
+                model_id == target_model_id
+                for target_model_id in model["pipeline"]["pipelines"]
+            )
+        )
+    ]
+    sorted_filters = sorted(filters, key=lambda x: x["pipeline"]["priority"])
+
+    model = app.state.MODELS[model_id]
+
+    if "pipeline" in model:
+        sorted_filters.append(model)
+
+    for filter in sorted_filters:
+        r = None
+        try:
+            urlIdx = filter["urlIdx"]
+
+            url = openai_app.state.config.OPENAI_API_BASE_URLS[urlIdx]
+            key = openai_app.state.config.OPENAI_API_KEYS[urlIdx]
+
+            if key != "":
+                headers = {"Authorization": f"Bearer {key}"}
+                r = requests.post(
+                    f"{url}/{filter['id']}/filter/inlet",
+                    headers=headers,
+                    json={
+                        "user": user,
+                        "body": payload,
+                    },
+                )
+
+                r.raise_for_status()
+                payload = r.json()
+        except Exception as e:
+            # Handle connection error here
+            print(f"Connection error: {e}")
+
+            if r is not None:
+                try:
+                    res = r.json()
+                    if "detail" in res:
+                        return JSONResponse(
+                            status_code=r.status_code,
+                            content=res,
+                        )
+                except:
+                    pass
+
+            else:
+                pass
+
+    if "pipeline" not in app.state.MODELS[model_id]:
+        if "chat_id" in payload:
+            del payload["chat_id"]
+
+        if "title" in payload:
+            del payload["title"]
+    return payload
+
+
 class PipelineMiddleware(BaseHTTPMiddleware):
     async def dispatch(self, request: Request, call_next):
         if request.method == "POST" and (
@@ -241,85 +343,10 @@ class PipelineMiddleware(BaseHTTPMiddleware):
             # Parse string to JSON
             data = json.loads(body_str) if body_str else {}
 
-            model_id = data["model"]
-            filters = [
-                model
-                for model in app.state.MODELS.values()
-                if "pipeline" in model
-                and "type" in model["pipeline"]
-                and model["pipeline"]["type"] == "filter"
-                and (
-                    model["pipeline"]["pipelines"] == ["*"]
-                    or any(
-                        model_id == target_model_id
-                        for target_model_id in model["pipeline"]["pipelines"]
-                    )
-                )
-            ]
-            sorted_filters = sorted(filters, key=lambda x: x["pipeline"]["priority"])
-
-            user = None
-            if len(sorted_filters) > 0:
-                try:
-                    user = get_current_user(
-                        get_http_authorization_cred(
-                            request.headers.get("Authorization")
-                        )
-                    )
-                    user = {"id": user.id, "name": user.name, "role": user.role}
-                except:
-                    pass
-
-            model = app.state.MODELS[model_id]
-
-            if "pipeline" in model:
-                sorted_filters.append(model)
-
-            for filter in sorted_filters:
-                r = None
-                try:
-                    urlIdx = filter["urlIdx"]
-
-                    url = openai_app.state.config.OPENAI_API_BASE_URLS[urlIdx]
-                    key = openai_app.state.config.OPENAI_API_KEYS[urlIdx]
-
-                    if key != "":
-                        headers = {"Authorization": f"Bearer {key}"}
-                        r = requests.post(
-                            f"{url}/{filter['id']}/filter/inlet",
-                            headers=headers,
-                            json={
-                                "user": user,
-                                "body": data,
-                            },
-                        )
-
-                        r.raise_for_status()
-                        data = r.json()
-                except Exception as e:
-                    # Handle connection error here
-                    print(f"Connection error: {e}")
-
-                    if r is not None:
-                        try:
-                            res = r.json()
-                            if "detail" in res:
-                                return JSONResponse(
-                                    status_code=r.status_code,
-                                    content=res,
-                                )
-                        except:
-                            pass
-
-                    else:
-                        pass
-
-            if "pipeline" not in app.state.MODELS[model_id]:
-                if "chat_id" in data:
-                    del data["chat_id"]
-
-                if "title" in data:
-                    del data["title"]
+            user = get_current_user(
+                get_http_authorization_cred(request.headers.get("Authorization"))
+            )
+            data = filter_pipeline(data, user)
 
             modified_body_bytes = json.dumps(data).encode("utf-8")
             # Replace the request body with the modified one
@@ -376,6 +403,9 @@ async def update_embedding_function(request: Request, call_next):
     return response
 
 
+app.mount("/ws", socket_app)
+
+
 app.mount("/ollama", ollama_app)
 app.mount("/openai", openai_app)
 
@@ -477,6 +507,178 @@ async def get_models(user=Depends(get_verified_user)):
     return {"data": models}
 
 
+@app.get("/api/task/config")
+async def get_task_config(user=Depends(get_verified_user)):
+    return {
+        "TASK_MODEL": app.state.config.TASK_MODEL,
+        "TASK_MODEL_EXTERNAL": app.state.config.TASK_MODEL_EXTERNAL,
+        "TITLE_GENERATION_PROMPT_TEMPLATE": app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE,
+        "SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE": app.state.config.SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE,
+        "SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD": app.state.config.SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD,
+    }
+
+
+class TaskConfigForm(BaseModel):
+    TASK_MODEL: Optional[str]
+    TASK_MODEL_EXTERNAL: Optional[str]
+    TITLE_GENERATION_PROMPT_TEMPLATE: str
+    SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE: str
+    SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD: int
+
+
+@app.post("/api/task/config/update")
+async def update_task_config(form_data: TaskConfigForm, user=Depends(get_admin_user)):
+    app.state.config.TASK_MODEL = form_data.TASK_MODEL
+    app.state.config.TASK_MODEL_EXTERNAL = form_data.TASK_MODEL_EXTERNAL
+    app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE = (
+        form_data.TITLE_GENERATION_PROMPT_TEMPLATE
+    )
+    app.state.config.SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE = (
+        form_data.SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE
+    )
+    app.state.config.SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD = (
+        form_data.SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD
+    )
+
+    return {
+        "TASK_MODEL": app.state.config.TASK_MODEL,
+        "TASK_MODEL_EXTERNAL": app.state.config.TASK_MODEL_EXTERNAL,
+        "TITLE_GENERATION_PROMPT_TEMPLATE": app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE,
+        "SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE": app.state.config.SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE,
+        "SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD": app.state.config.SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD,
+    }
+
+
+@app.post("/api/task/title/completions")
+async def generate_title(form_data: dict, user=Depends(get_verified_user)):
+    print("generate_title")
+
+    model_id = form_data["model"]
+    if model_id not in app.state.MODELS:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail="Model not found",
+        )
+
+    # Check if the user has a custom task model
+    # If the user has a custom task model, use that model
+    if app.state.MODELS[model_id]["owned_by"] == "ollama":
+        if app.state.config.TASK_MODEL:
+            task_model_id = app.state.config.TASK_MODEL
+            if task_model_id in app.state.MODELS:
+                model_id = task_model_id
+    else:
+        if app.state.config.TASK_MODEL_EXTERNAL:
+            task_model_id = app.state.config.TASK_MODEL_EXTERNAL
+            if task_model_id in app.state.MODELS:
+                model_id = task_model_id
+
+    print(model_id)
+    model = app.state.MODELS[model_id]
+
+    template = app.state.config.TITLE_GENERATION_PROMPT_TEMPLATE
+
+    content = title_generation_template(
+        template, form_data["prompt"], user.model_dump()
+    )
+
+    payload = {
+        "model": model_id,
+        "messages": [{"role": "user", "content": content}],
+        "stream": False,
+        "max_tokens": 50,
+        "chat_id": form_data.get("chat_id", None),
+        "title": True,
+    }
+
+    print(payload)
+    payload = filter_pipeline(payload, user)
+
+    if model["owned_by"] == "ollama":
+        return await generate_ollama_chat_completion(
+            OpenAIChatCompletionForm(**payload), user=user
+        )
+    else:
+        return await generate_openai_chat_completion(payload, user=user)
+
+
+@app.post("/api/task/query/completions")
+async def generate_search_query(form_data: dict, user=Depends(get_verified_user)):
+    print("generate_search_query")
+
+    if len(form_data["prompt"]) < app.state.config.SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=f"Skip search query generation for short prompts (< {app.state.config.SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD} characters)",
+        )
+
+    model_id = form_data["model"]
+    if model_id not in app.state.MODELS:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail="Model not found",
+        )
+
+    # Check if the user has a custom task model
+    # If the user has a custom task model, use that model
+    if app.state.MODELS[model_id]["owned_by"] == "ollama":
+        if app.state.config.TASK_MODEL:
+            task_model_id = app.state.config.TASK_MODEL
+            if task_model_id in app.state.MODELS:
+                model_id = task_model_id
+    else:
+        if app.state.config.TASK_MODEL_EXTERNAL:
+            task_model_id = app.state.config.TASK_MODEL_EXTERNAL
+            if task_model_id in app.state.MODELS:
+                model_id = task_model_id
+
+    print(model_id)
+    model = app.state.MODELS[model_id]
+
+    template = app.state.config.SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE
+
+    content = search_query_generation_template(
+        template, form_data["prompt"], user.model_dump()
+    )
+
+    payload = {
+        "model": model_id,
+        "messages": [{"role": "user", "content": content}],
+        "stream": False,
+        "max_tokens": 30,
+    }
+
+    print(payload)
+    payload = filter_pipeline(payload, user)
+
+    if model["owned_by"] == "ollama":
+        return await generate_ollama_chat_completion(
+            OpenAIChatCompletionForm(**payload), user=user
+        )
+    else:
+        return await generate_openai_chat_completion(payload, user=user)
+
+
+@app.post("/api/chat/completions")
+async def generate_chat_completions(form_data: dict, user=Depends(get_verified_user)):
+    model_id = form_data["model"]
+    if model_id not in app.state.MODELS:
+        raise HTTPException(
+            status_code=status.HTTP_404_NOT_FOUND,
+            detail="Model not found",
+        )
+
+    model = app.state.MODELS[model_id]
+    print(model)
+
+    if model["owned_by"] == "ollama":
+        return await generate_ollama_chat_completion(
+            OpenAIChatCompletionForm(**form_data), user=user
+        )
+    else:
+        return await generate_openai_chat_completion(form_data, user=user)
+
+
 @app.post("/api/chat/completed")
 async def chat_completed(form_data: dict, user=Depends(get_verified_user)):
     data = form_data
@@ -569,6 +771,63 @@ async def get_pipelines_list(user=Depends(get_admin_user)):
     }
 
 
+@app.post("/api/pipelines/upload")
+async def upload_pipeline(
+    urlIdx: int = Form(...), file: UploadFile = File(...), user=Depends(get_admin_user)
+):
+    print("upload_pipeline", urlIdx, file.filename)
+    # Check if the uploaded file is a python file
+    if not file.filename.endswith(".py"):
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail="Only Python (.py) files are allowed.",
+        )
+
+    upload_folder = f"{CACHE_DIR}/pipelines"
+    os.makedirs(upload_folder, exist_ok=True)
+    file_path = os.path.join(upload_folder, file.filename)
+
+    try:
+        # Save the uploaded file
+        with open(file_path, "wb") as buffer:
+            shutil.copyfileobj(file.file, buffer)
+
+        url = openai_app.state.config.OPENAI_API_BASE_URLS[urlIdx]
+        key = openai_app.state.config.OPENAI_API_KEYS[urlIdx]
+
+        headers = {"Authorization": f"Bearer {key}"}
+
+        with open(file_path, "rb") as f:
+            files = {"file": f}
+            r = requests.post(f"{url}/pipelines/upload", headers=headers, files=files)
+
+        r.raise_for_status()
+        data = r.json()
+
+        return {**data}
+    except Exception as e:
+        # Handle connection error here
+        print(f"Connection error: {e}")
+
+        detail = "Pipeline not found"
+        if r is not None:
+            try:
+                res = r.json()
+                if "detail" in res:
+                    detail = res["detail"]
+            except:
+                pass
+
+        raise HTTPException(
+            status_code=(r.status_code if r is not None else status.HTTP_404_NOT_FOUND),
+            detail=detail,
+        )
+    finally:
+        # Ensure the file is deleted after the upload is completed or on failure
+        if os.path.exists(file_path):
+            os.remove(file_path)
+
+
 class AddPipelineForm(BaseModel):
     url: str
     urlIdx: int
@@ -835,6 +1094,15 @@ async def get_app_config():
             "enable_community_sharing": webui_app.state.config.ENABLE_COMMUNITY_SHARING,
             "enable_admin_export": ENABLE_ADMIN_EXPORT,
         },
+        "audio": {
+            "tts": {
+                "engine": audio_app.state.config.TTS_ENGINE,
+                "voice": audio_app.state.config.TTS_VOICE,
+            },
+            "stt": {
+                "engine": audio_app.state.config.STT_ENGINE,
+            },
+        },
     }
 
 
@@ -897,7 +1165,7 @@ async def get_app_changelog():
 @app.get("/api/version/updates")
 async def get_app_latest_release_version():
     try:
-        async with aiohttp.ClientSession() as session:
+        async with aiohttp.ClientSession(trust_env=True) as session:
             async with session.get(
                 "https://api.github.com/repos/open-webui/open-webui/releases/latest"
             ) as response:

backend/requirements.txt

@@ -56,4 +56,7 @@ PyJWT[crypto]==2.8.0
 black==24.4.2
 langfuse==2.33.0
 youtube-transcript-api==0.6.2
-pytube==15.0.0
+pytube==15.0.0
+
+extract_msg
+pydub

backend/start.sh

@@ -20,12 +20,12 @@ if test "$WEBUI_SECRET_KEY $WEBUI_JWT_SECRET_KEY" = " "; then
   WEBUI_SECRET_KEY=$(cat "$KEY_FILE")
 fi
 
-if [ "$USE_OLLAMA_DOCKER" = "true" ]; then
+if [[ "${USE_OLLAMA_DOCKER,,}" == "true" ]]; then
     echo "USE_OLLAMA is set to true, starting ollama serve."
     ollama serve &
 fi
 
-if [ "$USE_CUDA_DOCKER" = "true" ]; then
+if [[ "${USE_CUDA_DOCKER,,}" == "true" ]]; then
   echo "CUDA is enabled, appending LD_LIBRARY_PATH to include torch/cudnn & cublas libraries."
   export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.11/site-packages/torch/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib"
 fi

backend/utils/misc.py

@@ -3,7 +3,48 @@ import hashlib
 import json
 import re
 from datetime import timedelta
-from typing import Optional
+from typing import Optional, List
+
+
+def get_last_user_message(messages: List[dict]) -> str:
+    for message in reversed(messages):
+        if message["role"] == "user":
+            if isinstance(message["content"], list):
+                for item in message["content"]:
+                    if item["type"] == "text":
+                        return item["text"]
+            return message["content"]
+    return None
+
+
+def get_last_assistant_message(messages: List[dict]) -> str:
+    for message in reversed(messages):
+        if message["role"] == "assistant":
+            if isinstance(message["content"], list):
+                for item in message["content"]:
+                    if item["type"] == "text":
+                        return item["text"]
+            return message["content"]
+    return None
+
+
+def add_or_update_system_message(content: str, messages: List[dict]):
+    """
+    Adds a new system message at the beginning of the messages list
+    or updates the existing system message at the beginning.
+
+    :param msg: The message to be added or appended.
+    :param messages: The list of message dictionaries.
+    :return: The updated list of message dictionaries.
+    """
+
+    if messages and messages[0].get("role") == "system":
+        messages[0]["content"] += f"{content}\n{messages[0]['content']}"
+    else:
+        # Insert at the beginning
+        messages.insert(0, {"role": "system", "content": content})
+
+    return messages
 
 
 def get_gravatar_url(email):
@@ -193,8 +234,14 @@ def parse_ollama_modelfile(model_text):
     system_desc_match = re.search(
         r'SYSTEM\s+"""(.+?)"""', model_text, re.DOTALL | re.IGNORECASE
     )
+    system_desc_match_single = re.search(
+        r"SYSTEM\s+([^\n]+)", model_text, re.IGNORECASE
+    )
+
     if system_desc_match:
         data["params"]["system"] = system_desc_match.group(1).strip()
+    elif system_desc_match_single:
+        data["params"]["system"] = system_desc_match_single.group(1).strip()
 
     # Parse messages
     messages = []

backend/utils/models.py

@@ -1,10 +0,0 @@
-from apps.webui.models.models import Models, ModelModel, ModelForm, ModelResponse
-
-
-def get_model_id_from_custom_model_id(id: str):
-    model = Models.get_model_by_id(id)
-
-    if model:
-        return model.id
-    else:
-        return id

backend/utils/task.py

@@ -0,0 +1,112 @@
+import re
+import math
+
+from datetime import datetime
+from typing import Optional
+
+
+def prompt_template(
+    template: str, user_name: str = None, current_location: str = None
+) -> str:
+    # Get the current date
+    current_date = datetime.now()
+
+    # Format the date to YYYY-MM-DD
+    formatted_date = current_date.strftime("%Y-%m-%d")
+
+    # Replace {{CURRENT_DATE}} in the template with the formatted date
+    template = template.replace("{{CURRENT_DATE}}", formatted_date)
+
+    if user_name:
+        # Replace {{USER_NAME}} in the template with the user's name
+        template = template.replace("{{USER_NAME}}", user_name)
+
+    if current_location:
+        # Replace {{CURRENT_LOCATION}} in the template with the current location
+        template = template.replace("{{CURRENT_LOCATION}}", current_location)
+
+    return template
+
+
+def title_generation_template(
+    template: str, prompt: str, user: Optional[dict] = None
+) -> str:
+    def replacement_function(match):
+        full_match = match.group(0)
+        start_length = match.group(1)
+        end_length = match.group(2)
+        middle_length = match.group(3)
+
+        if full_match == "{{prompt}}":
+            return prompt
+        elif start_length is not None:
+            return prompt[: int(start_length)]
+        elif end_length is not None:
+            return prompt[-int(end_length) :]
+        elif middle_length is not None:
+            middle_length = int(middle_length)
+            if len(prompt) <= middle_length:
+                return prompt
+            start = prompt[: math.ceil(middle_length / 2)]
+            end = prompt[-math.floor(middle_length / 2) :]
+            return f"{start}...{end}"
+        return ""
+
+    template = re.sub(
+        r"{{prompt}}|{{prompt:start:(\d+)}}|{{prompt:end:(\d+)}}|{{prompt:middletruncate:(\d+)}}",
+        replacement_function,
+        template,
+    )
+
+    template = prompt_template(
+        template,
+        **(
+            {"user_name": user.get("name"), "current_location": user.get("location")}
+            if user
+            else {}
+        ),
+    )
+
+    return template
+
+
+def search_query_generation_template(
+    template: str, prompt: str, user: Optional[dict] = None
+) -> str:
+
+    def replacement_function(match):
+        full_match = match.group(0)
+        start_length = match.group(1)
+        end_length = match.group(2)
+        middle_length = match.group(3)
+
+        if full_match == "{{prompt}}":
+            return prompt
+        elif start_length is not None:
+            return prompt[: int(start_length)]
+        elif end_length is not None:
+            return prompt[-int(end_length) :]
+        elif middle_length is not None:
+            middle_length = int(middle_length)
+            if len(prompt) <= middle_length:
+                return prompt
+            start = prompt[: math.ceil(middle_length / 2)]
+            end = prompt[-math.floor(middle_length / 2) :]
+            return f"{start}...{end}"
+        return ""
+
+    template = re.sub(
+        r"{{prompt}}|{{prompt:start:(\d+)}}|{{prompt:end:(\d+)}}|{{prompt:middletruncate:(\d+)}}",
+        replacement_function,
+        template,
+    )
+
+    template = prompt_template(
+        template,
+        **(
+            {"user_name": user.get("name"), "current_location": user.get("location")}
+            if user
+            else {}
+        ),
+    )
+    return template

docs/CONTRIBUTING.md

@@ -41,7 +41,7 @@ Looking to contribute? Great! Here's how you can help:
 
 We welcome pull requests. Before submitting one, please:
 
-1. Discuss your idea or issue in the [issues section](https://github.com/open-webui/open-webui/issues).
+1. Open a discussion regarding your ideas [here](https://github.com/open-webui/open-webui/discussions/new/choose).
 2. Follow the project's coding standards and include tests for new features.
 3. Update documentation as necessary.
 4. Write clear, descriptive commit messages.

package-lock.json

@@ -1,12 +1,12 @@
 {
 	"name": "open-webui",
-	"version": "0.2.4",
+	"version": "0.3.2",
 	"lockfileVersion": 3,
 	"requires": true,
 	"packages": {
 		"": {
 			"name": "open-webui",
-			"version": "0.2.4",
+			"version": "0.3.2",
 			"dependencies": {
 				"@pyscript/core": "^0.4.32",
 				"@sveltejs/adapter-node": "^1.3.1",
@@ -25,6 +25,7 @@
 				"marked": "^9.1.0",
 				"mermaid": "^10.9.1",
 				"pyodide": "^0.26.0-alpha.4",
+				"socket.io-client": "^4.7.5",
 				"sortablejs": "^1.15.2",
 				"svelte-sonner": "^0.3.19",
 				"tippy.js": "^6.3.7",
@@ -1214,6 +1215,11 @@
 			"integrity": "sha512-+Fj43pSMwJs4KRrH/938Uf+uAELIgVBmQzg/q1YG10djyfA3TnrU8N8XzqCh/okZdszqBQTZf96idMfE5lnwTA==",
 			"dev": true
 		},
+		"node_modules/@socket.io/component-emitter": {
+			"version": "3.1.2",
+			"resolved": "https://registry.npmjs.org/@socket.io/component-emitter/-/component-emitter-3.1.2.tgz",
+			"integrity": "sha512-9BCxFwvbGg/RsZK9tjXd8s4UcwR0MWeFQ1XEKIQVVvAGJyINdrqKMcTRyLoK8Rse1GjzLV9cwjWV1olXRWEXVA=="
+		},
 		"node_modules/@sveltejs/adapter-auto": {
 			"version": "2.1.1",
 			"resolved": "https://registry.npmjs.org/@sveltejs/adapter-auto/-/adapter-auto-2.1.1.tgz",
@@ -3800,6 +3806,46 @@
 				"once": "^1.4.0"
 			}
 		},
+		"node_modules/engine.io-client": {
+			"version": "6.5.3",
+			"resolved": "https://registry.npmjs.org/engine.io-client/-/engine.io-client-6.5.3.tgz",
+			"integrity": "sha512-9Z0qLB0NIisTRt1DZ/8U2k12RJn8yls/nXMZLn+/N8hANT3TcYjKFKcwbw5zFQiN4NTde3TSY9zb79e1ij6j9Q==",
+			"dependencies": {
+				"@socket.io/component-emitter": "~3.1.0",
+				"debug": "~4.3.1",
+				"engine.io-parser": "~5.2.1",
+				"ws": "~8.11.0",
+				"xmlhttprequest-ssl": "~2.0.0"
+			}
+		},
+		"node_modules/engine.io-client/node_modules/ws": {
+			"version": "8.11.0",
+			"resolved": "https://registry.npmjs.org/ws/-/ws-8.11.0.tgz",
+			"integrity": "sha512-HPG3wQd9sNQoT9xHyNCXoDUa+Xw/VevmY9FoHyQ+g+rrMn4j6FB4np7Z0OhdTgjx6MgQLK7jwSy1YecU1+4Asg==",
+			"engines": {
+				"node": ">=10.0.0"
+			},
+			"peerDependencies": {
+				"bufferutil": "^4.0.1",
+				"utf-8-validate": "^5.0.2"
+			},
+			"peerDependenciesMeta": {
+				"bufferutil": {
+					"optional": true
+				},
+				"utf-8-validate": {
+					"optional": true
+				}
+			}
+		},
+		"node_modules/engine.io-parser": {
+			"version": "5.2.2",
+			"resolved": "https://registry.npmjs.org/engine.io-parser/-/engine.io-parser-5.2.2.tgz",
+			"integrity": "sha512-RcyUFKA93/CXH20l4SoVvzZfrSDMOTUS3bWVpTt2FuFP+XYrL8i8oonHP7WInRyVHXh0n/ORtoeiE1os+8qkSw==",
+			"engines": {
+				"node": ">=10.0.0"
+			}
+		},
 		"node_modules/enquirer": {
 			"version": "2.4.1",
 			"resolved": "https://registry.npmjs.org/enquirer/-/enquirer-2.4.1.tgz",
@@ -7949,6 +7995,32 @@
 				"node": ">=8"
 			}
 		},
+		"node_modules/socket.io-client": {
+			"version": "4.7.5",
+			"resolved": "https://registry.npmjs.org/socket.io-client/-/socket.io-client-4.7.5.tgz",
+			"integrity": "sha512-sJ/tqHOCe7Z50JCBCXrsY3I2k03iOiUe+tj1OmKeD2lXPiGH/RUCdTZFoqVyN7l1MnpIzPrGtLcijffmeouNlQ==",
+			"dependencies": {
+				"@socket.io/component-emitter": "~3.1.0",
+				"debug": "~4.3.2",
+				"engine.io-client": "~6.5.2",
+				"socket.io-parser": "~4.2.4"
+			},
+			"engines": {
+				"node": ">=10.0.0"
+			}
+		},
+		"node_modules/socket.io-parser": {
+			"version": "4.2.4",
+			"resolved": "https://registry.npmjs.org/socket.io-parser/-/socket.io-parser-4.2.4.tgz",
+			"integrity": "sha512-/GbIKmo8ioc+NIWIhwdecY0ge+qVBSMdgxGygevmdHj24bsfgtCmcUUcQ5ZzcylGFHsN3k4HB4Cgkl96KVnuew==",
+			"dependencies": {
+				"@socket.io/component-emitter": "~3.1.0",
+				"debug": "~4.3.1"
+			},
+			"engines": {
+				"node": ">=10.0.0"
+			}
+		},
 		"node_modules/sorcery": {
 			"version": "0.11.0",
 			"resolved": "https://registry.npmjs.org/sorcery/-/sorcery-0.11.0.tgz",
@@ -10142,6 +10214,14 @@
 				}
 			}
 		},
+		"node_modules/xmlhttprequest-ssl": {
+			"version": "2.0.0",
+			"resolved": "https://registry.npmjs.org/xmlhttprequest-ssl/-/xmlhttprequest-ssl-2.0.0.tgz",
+			"integrity": "sha512-QKxVRxiRACQcVuQEYFsI1hhkrMlrXHPegbbd1yn9UHOmRxY+si12nQYzri3vbzt8VdTTRviqcKxcyllFas5z2A==",
+			"engines": {
+				"node": ">=0.4.0"
+			}
+		},
 		"node_modules/xtend": {
 			"version": "4.0.2",
 			"resolved": "https://registry.npmjs.org/xtend/-/xtend-4.0.2.tgz",

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.2.4",
+	"version": "0.3.2",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -65,6 +65,7 @@
 		"marked": "^9.1.0",
 		"mermaid": "^10.9.1",
 		"pyodide": "^0.26.0-alpha.4",
+		"socket.io-client": "^4.7.5",
 		"sortablejs": "^1.15.2",
 		"svelte-sonner": "^0.3.19",
 		"tippy.js": "^6.3.7",

src/app.html

@@ -59,15 +59,7 @@
 
 		<div
 			id="splash-screen"
-			style="
-				position: fixed;
-				z-index: 100;
-				background: #fff;
-				top: 0;
-				left: 0;
-				width: 100%;
-				height: 100%;
-			"
+			style="position: fixed; z-index: 100; top: 0; left: 0; width: 100%; height: 100%"
 		>
 			<style type="text/css" nonce="">
 				html {
@@ -93,3 +85,20 @@
 		</div>
 	</body>
 </html>
+
+<style type="text/css" nonce="">
+	html {
+		overflow-y: hidden !important;
+	}
+
+	#splash-screen {
+		background: #fff;
+	}
+	html.dark #splash-screen {
+		background: #000;
+	}
+
+	html.dark #splash-screen img {
+		filter: invert(1);
+	}
+</style>

src/lib/apis/audio/index.ts

@@ -98,7 +98,7 @@ export const synthesizeOpenAISpeech = async (
 	token: string = '',
 	speaker: string = 'alloy',
 	text: string = '',
-	model: string = 'tts-1'
+	model?: string
 ) => {
 	let error = null;
 
@@ -109,9 +109,9 @@ export const synthesizeOpenAISpeech = async (
 			'Content-Type': 'application/json'
 		},
 		body: JSON.stringify({
-			model: model,
 			input: text,
-			voice: speaker
+			voice: speaker,
+			...(model && { model })
 		})
 	})
 		.then(async (res) => {

src/lib/apis/index.ts

@@ -104,6 +104,147 @@ export const chatCompleted = async (token: string, body: ChatCompletedForm) => {
 	return res;
 };
 
+export const getTaskConfig = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/task/config`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			error = err;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const updateTaskConfig = async (token: string, config: object) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/task/config/update`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			...(token && { authorization: `Bearer ${token}` })
+		},
+		body: JSON.stringify(config)
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = err;
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const generateTitle = async (
+	token: string = '',
+	model: string,
+	prompt: string,
+	chat_id?: string
+) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/task/title/completions`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			model: model,
+			prompt: prompt,
+			...(chat_id && { chat_id: chat_id })
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res?.choices[0]?.message?.content.replace(/["']/g, '') ?? 'New Chat';
+};
+
+export const generateSearchQuery = async (
+	token: string = '',
+	model: string,
+	messages: object[],
+	prompt: string
+) => {
+	let error = null;
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/task/query/completions`, {
+		method: 'POST',
+		headers: {
+			Accept: 'application/json',
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		},
+		body: JSON.stringify({
+			model: model,
+			messages: messages,
+			prompt: prompt
+		})
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res?.choices[0]?.message?.content.replace(/["']/g, '') ?? prompt;
+};
+
 export const getPipelinesList = async (token: string = '') => {
 	let error = null;
 
@@ -133,6 +274,43 @@ export const getPipelinesList = async (token: string = '') => {
 	return pipelines;
 };
 
+export const uploadPipeline = async (token: string, file: File, urlIdx: string) => {
+	let error = null;
+
+	// Create a new FormData object to handle the file upload
+	const formData = new FormData();
+	formData.append('file', file);
+	formData.append('urlIdx', urlIdx);
+
+	const res = await fetch(`${WEBUI_BASE_URL}/api/pipelines/upload`, {
+		method: 'POST',
+		headers: {
+			...(token && { authorization: `Bearer ${token}` })
+			// 'Content-Type': 'multipart/form-data' is not needed as Fetch API will set it automatically
+		},
+		body: formData
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			console.log(err);
+			if ('detail' in err) {
+				error = err.detail;
+			} else {
+				error = err;
+			}
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const downloadPipeline = async (token: string, url: string, urlIdx: string) => {
 	let error = null;
 

src/lib/apis/ollama/index.ts

@@ -369,21 +369,29 @@ export const generateChatCompletion = async (token: string = '', body: object) =
 	return [res, controller];
 };
 
-export const createModel = async (token: string, tagName: string, content: string) => {
+export const createModel = async (
+	token: string,
+	tagName: string,
+	content: string,
+	urlIdx: string | null = null
+) => {
 	let error = null;
 
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/create`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			name: tagName,
-			modelfile: content
-		})
-	}).catch((err) => {
+	const res = await fetch(
+		`${OLLAMA_API_BASE_URL}/api/create${urlIdx !== null ? `/${urlIdx}` : ''}`,
+		{
+			method: 'POST',
+			headers: {
+				Accept: 'application/json',
+				'Content-Type': 'application/json',
+				Authorization: `Bearer ${token}`
+			},
+			body: JSON.stringify({
+				name: tagName,
+				modelfile: content
+			})
+		}
+	).catch((err) => {
 		error = err;
 		return null;
 	});

src/lib/apis/rag/index.ts

@@ -359,6 +359,32 @@ export const scanDocs = async (token: string) => {
 	return res;
 };
 
+export const resetUploadDir = async (token: string) => {
+	let error = null;
+
+	const res = await fetch(`${RAG_API_BASE_URL}/reset/uploads`, {
+		method: 'GET',
+		headers: {
+			Accept: 'application/json',
+			authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err.detail;
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
 export const resetVectorDB = async (token: string) => {
 	let error = null;
 

src/lib/components/admin/Settings.svelte

@@ -0,0 +1,390 @@
+<script>
+	import { getContext, tick } from 'svelte';
+	import { toast } from 'svelte-sonner';
+
+	import Database from './Settings/Database.svelte';
+
+	import General from './Settings/General.svelte';
+	import Users from './Settings/Users.svelte';
+
+	import Pipelines from './Settings/Pipelines.svelte';
+	import Audio from './Settings/Audio.svelte';
+	import Images from './Settings/Images.svelte';
+	import Interface from './Settings/Interface.svelte';
+	import Models from './Settings/Models.svelte';
+	import Connections from './Settings/Connections.svelte';
+	import Documents from './Settings/Documents.svelte';
+	import WebSearch from './Settings/WebSearch.svelte';
+	import { config } from '$lib/stores';
+	import { getBackendConfig } from '$lib/apis';
+
+	const i18n = getContext('i18n');
+
+	let selectedTab = 'general';
+</script>
+
+<div class="flex flex-col lg:flex-row w-full h-full py-2 lg:space-x-4">
+	<div
+		class="tabs flex flex-row overflow-x-auto space-x-1 max-w-full lg:space-x-0 lg:space-y-1 lg:flex-col lg:flex-none lg:w-44 dark:text-gray-200 text-xs text-left scrollbar-none"
+	>
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 lg:flex-none flex text-right transition {selectedTab ===
+			'general'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'general';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						fill-rule="evenodd"
+						d="M6.955 1.45A.5.5 0 0 1 7.452 1h1.096a.5.5 0 0 1 .497.45l.17 1.699c.484.12.94.312 1.356.562l1.321-1.081a.5.5 0 0 1 .67.033l.774.775a.5.5 0 0 1 .034.67l-1.08 1.32c.25.417.44.873.561 1.357l1.699.17a.5.5 0 0 1 .45.497v1.096a.5.5 0 0 1-.45.497l-1.699.17c-.12.484-.312.94-.562 1.356l1.082 1.322a.5.5 0 0 1-.034.67l-.774.774a.5.5 0 0 1-.67.033l-1.322-1.08c-.416.25-.872.44-1.356.561l-.17 1.699a.5.5 0 0 1-.497.45H7.452a.5.5 0 0 1-.497-.45l-.17-1.699a4.973 4.973 0 0 1-1.356-.562L4.108 13.37a.5.5 0 0 1-.67-.033l-.774-.775a.5.5 0 0 1-.034-.67l1.08-1.32a4.971 4.971 0 0 1-.561-1.357l-1.699-.17A.5.5 0 0 1 1 8.548V7.452a.5.5 0 0 1 .45-.497l1.699-.17c.12-.484.312-.94.562-1.356L2.629 4.107a.5.5 0 0 1 .034-.67l.774-.774a.5.5 0 0 1 .67-.033L5.43 3.71a4.97 4.97 0 0 1 1.356-.561l.17-1.699ZM6 8c0 .538.212 1.026.558 1.385l.057.057a2 2 0 0 0 2.828-2.828l-.058-.056A2 2 0 0 0 6 8Z"
+						clip-rule="evenodd"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('General')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'users'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'users';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						d="M8 8a2.5 2.5 0 1 0 0-5 2.5 2.5 0 0 0 0 5ZM3.156 11.763c.16-.629.44-1.21.813-1.72a2.5 2.5 0 0 0-2.725 1.377c-.136.287.102.58.418.58h1.449c.01-.077.025-.156.045-.237ZM12.847 11.763c.02.08.036.16.046.237h1.446c.316 0 .554-.293.417-.579a2.5 2.5 0 0 0-2.722-1.378c.374.51.653 1.09.813 1.72ZM14 7.5a1.5 1.5 0 1 1-3 0 1.5 1.5 0 0 1 3 0ZM3.5 9a1.5 1.5 0 1 0 0-3 1.5 1.5 0 0 0 0 3ZM5 13c-.552 0-1.013-.455-.876-.99a4.002 4.002 0 0 1 7.753 0c.136.535-.324.99-.877.99H5Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Users')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'connections'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'connections';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						d="M1 9.5A3.5 3.5 0 0 0 4.5 13H12a3 3 0 0 0 .917-5.857 2.503 2.503 0 0 0-3.198-3.019 3.5 3.5 0 0 0-6.628 2.171A3.5 3.5 0 0 0 1 9.5Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Connections')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'models'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'models';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 20 20"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						fill-rule="evenodd"
+						d="M10 1c3.866 0 7 1.79 7 4s-3.134 4-7 4-7-1.79-7-4 3.134-4 7-4zm5.694 8.13c.464-.264.91-.583 1.306-.952V10c0 2.21-3.134 4-7 4s-7-1.79-7-4V8.178c.396.37.842.688 1.306.953C5.838 10.006 7.854 10.5 10 10.5s4.162-.494 5.694-1.37zM3 13.179V15c0 2.21 3.134 4 7 4s7-1.79 7-4v-1.822c-.396.37-.842.688-1.306.953-1.532.875-3.548 1.369-5.694 1.369s-4.162-.494-5.694-1.37A7.009 7.009 0 013 13.179z"
+						clip-rule="evenodd"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Models')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'documents'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'documents';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 24 24"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path d="M11.625 16.5a1.875 1.875 0 1 0 0-3.75 1.875 1.875 0 0 0 0 3.75Z" />
+					<path
+						fill-rule="evenodd"
+						d="M5.625 1.5H9a3.75 3.75 0 0 1 3.75 3.75v1.875c0 1.036.84 1.875 1.875 1.875H16.5a3.75 3.75 0 0 1 3.75 3.75v7.875c0 1.035-.84 1.875-1.875 1.875H5.625a1.875 1.875 0 0 1-1.875-1.875V3.375c0-1.036.84-1.875 1.875-1.875Zm6 16.5c.66 0 1.277-.19 1.797-.518l1.048 1.048a.75.75 0 0 0 1.06-1.06l-1.047-1.048A3.375 3.375 0 1 0 11.625 18Z"
+						clip-rule="evenodd"
+					/>
+					<path
+						d="M14.25 5.25a5.23 5.23 0 0 0-1.279-3.434 9.768 9.768 0 0 1 6.963 6.963A5.23 5.23 0 0 0 16.5 7.5h-1.875a.375.375 0 0 1-.375-.375V5.25Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Documents')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'web'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'web';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 24 24"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						d="M21.721 12.752a9.711 9.711 0 0 0-.945-5.003 12.754 12.754 0 0 1-4.339 2.708 18.991 18.991 0 0 1-.214 4.772 17.165 17.165 0 0 0 5.498-2.477ZM14.634 15.55a17.324 17.324 0 0 0 .332-4.647c-.952.227-1.945.347-2.966.347-1.021 0-2.014-.12-2.966-.347a17.515 17.515 0 0 0 .332 4.647 17.385 17.385 0 0 0 5.268 0ZM9.772 17.119a18.963 18.963 0 0 0 4.456 0A17.182 17.182 0 0 1 12 21.724a17.18 17.18 0 0 1-2.228-4.605ZM7.777 15.23a18.87 18.87 0 0 1-.214-4.774 12.753 12.753 0 0 1-4.34-2.708 9.711 9.711 0 0 0-.944 5.004 17.165 17.165 0 0 0 5.498 2.477ZM21.356 14.752a9.765 9.765 0 0 1-7.478 6.817 18.64 18.64 0 0 0 1.988-4.718 18.627 18.627 0 0 0 5.49-2.098ZM2.644 14.752c1.682.971 3.53 1.688 5.49 2.099a18.64 18.64 0 0 0 1.988 4.718 9.765 9.765 0 0 1-7.478-6.816ZM13.878 2.43a9.755 9.755 0 0 1 6.116 3.986 11.267 11.267 0 0 1-3.746 2.504 18.63 18.63 0 0 0-2.37-6.49ZM12 2.276a17.152 17.152 0 0 1 2.805 7.121c-.897.23-1.837.353-2.805.353-.968 0-1.908-.122-2.805-.353A17.151 17.151 0 0 1 12 2.276ZM10.122 2.43a18.629 18.629 0 0 0-2.37 6.49 11.266 11.266 0 0 1-3.746-2.504 9.754 9.754 0 0 1 6.116-3.985Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Web Search')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'interface'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'interface';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						fill-rule="evenodd"
+						d="M2 4.25A2.25 2.25 0 0 1 4.25 2h7.5A2.25 2.25 0 0 1 14 4.25v5.5A2.25 2.25 0 0 1 11.75 12h-1.312c.1.128.21.248.328.36a.75.75 0 0 1 .234.545v.345a.75.75 0 0 1-.75.75h-4.5a.75.75 0 0 1-.75-.75v-.345a.75.75 0 0 1 .234-.545c.118-.111.228-.232.328-.36H4.25A2.25 2.25 0 0 1 2 9.75v-5.5Zm2.25-.75a.75.75 0 0 0-.75.75v4.5c0 .414.336.75.75.75h7.5a.75.75 0 0 0 .75-.75v-4.5a.75.75 0 0 0-.75-.75h-7.5Z"
+						clip-rule="evenodd"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Interface')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'audio'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'audio';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						d="M7.557 2.066A.75.75 0 0 1 8 2.75v10.5a.75.75 0 0 1-1.248.56L3.59 11H2a1 1 0 0 1-1-1V6a1 1 0 0 1 1-1h1.59l3.162-2.81a.75.75 0 0 1 .805-.124ZM12.95 3.05a.75.75 0 1 0-1.06 1.06 5.5 5.5 0 0 1 0 7.78.75.75 0 1 0 1.06 1.06 7 7 0 0 0 0-9.9Z"
+					/>
+					<path
+						d="M10.828 5.172a.75.75 0 1 0-1.06 1.06 2.5 2.5 0 0 1 0 3.536.75.75 0 1 0 1.06 1.06 4 4 0 0 0 0-5.656Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Audio')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'images'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'images';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path
+						fill-rule="evenodd"
+						d="M2 4a2 2 0 0 1 2-2h8a2 2 0 0 1 2 2v8a2 2 0 0 1-2 2H4a2 2 0 0 1-2-2V4Zm10.5 5.707a.5.5 0 0 0-.146-.353l-1-1a.5.5 0 0 0-.708 0L9.354 9.646a.5.5 0 0 1-.708 0L6.354 7.354a.5.5 0 0 0-.708 0l-2 2a.5.5 0 0 0-.146.353V12a.5.5 0 0 0 .5.5h8a.5.5 0 0 0 .5-.5V9.707ZM12 5a1 1 0 1 1-2 0 1 1 0 0 1 2 0Z"
+						clip-rule="evenodd"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Images')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'pipelines'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'pipelines';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 24 24"
+					fill="currentColor"
+					class="size-4"
+				>
+					<path
+						d="M11.644 1.59a.75.75 0 0 1 .712 0l9.75 5.25a.75.75 0 0 1 0 1.32l-9.75 5.25a.75.75 0 0 1-.712 0l-9.75-5.25a.75.75 0 0 1 0-1.32l9.75-5.25Z"
+					/>
+					<path
+						d="m3.265 10.602 7.668 4.129a2.25 2.25 0 0 0 2.134 0l7.668-4.13 1.37.739a.75.75 0 0 1 0 1.32l-9.75 5.25a.75.75 0 0 1-.71 0l-9.75-5.25a.75.75 0 0 1 0-1.32l1.37-.738Z"
+					/>
+					<path
+						d="m10.933 19.231-7.668-4.13-1.37.739a.75.75 0 0 0 0 1.32l9.75 5.25c.221.12.489.12.71 0l9.75-5.25a.75.75 0 0 0 0-1.32l-1.37-.738-7.668 4.13a2.25 2.25 0 0 1-2.134-.001Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Pipelines')}</div>
+		</button>
+
+		<button
+			class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
+			'db'
+				? 'bg-gray-200 dark:bg-gray-800'
+				: ' hover:bg-gray-300 dark:hover:bg-gray-850'}"
+			on:click={() => {
+				selectedTab = 'db';
+			}}
+		>
+			<div class=" self-center mr-2">
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					viewBox="0 0 16 16"
+					fill="currentColor"
+					class="w-4 h-4"
+				>
+					<path d="M8 7c3.314 0 6-1.343 6-3s-2.686-3-6-3-6 1.343-6 3 2.686 3 6 3Z" />
+					<path
+						d="M8 8.5c1.84 0 3.579-.37 4.914-1.037A6.33 6.33 0 0 0 14 6.78V8c0 1.657-2.686 3-6 3S2 9.657 2 8V6.78c.346.273.72.5 1.087.683C4.42 8.131 6.16 8.5 8 8.5Z"
+					/>
+					<path
+						d="M8 12.5c1.84 0 3.579-.37 4.914-1.037.366-.183.74-.41 1.086-.684V12c0 1.657-2.686 3-6 3s-6-1.343-6-3v-1.22c.346.273.72.5 1.087.683C4.42 12.131 6.16 12.5 8 12.5Z"
+					/>
+				</svg>
+			</div>
+			<div class=" self-center">{$i18n.t('Database')}</div>
+		</button>
+	</div>
+
+	<div class="flex-1 mt-3 lg:mt-0 overflow-y-scroll">
+		{#if selectedTab === 'general'}
+			<General
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'users'}
+			<Users
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'connections'}
+			<Connections
+				on:save={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'models'}
+			<Models />
+		{:else if selectedTab === 'documents'}
+			<Documents
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'web'}
+			<WebSearch
+				saveHandler={async () => {
+					toast.success($i18n.t('Settings saved successfully!'));
+
+					await tick();
+					await config.set(await getBackendConfig());
+				}}
+			/>
+		{:else if selectedTab === 'interface'}
+			<Interface
+				on:save={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'audio'}
+			<Audio
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'images'}
+			<Images
+				on:save={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'db'}
+			<Database
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{:else if selectedTab === 'pipelines'}
+			<Pipelines
+				saveHandler={() => {
+					toast.success($i18n.t('Settings saved successfully!'));
+				}}
+			/>
+		{/if}
+	</div>
+</div>

src/lib/components/admin/Settings/Audio.svelte

@@ -0,0 +1,302 @@
+<script lang="ts">
+	import { getAudioConfig, updateAudioConfig } from '$lib/apis/audio';
+	import { user, settings, config } from '$lib/stores';
+	import { createEventDispatcher, onMount, getContext } from 'svelte';
+	import { toast } from 'svelte-sonner';
+	import Switch from '$lib/components/common/Switch.svelte';
+	import { getBackendConfig } from '$lib/apis';
+	const dispatch = createEventDispatcher();
+
+	const i18n = getContext('i18n');
+
+	export let saveHandler: Function;
+
+	// Audio
+
+	let TTS_OPENAI_API_BASE_URL = '';
+	let TTS_OPENAI_API_KEY = '';
+	let TTS_ENGINE = '';
+	let TTS_MODEL = '';
+	let TTS_VOICE = '';
+
+	let STT_OPENAI_API_BASE_URL = '';
+	let STT_OPENAI_API_KEY = '';
+	let STT_ENGINE = '';
+	let STT_MODEL = '';
+
+	let voices = [];
+	let models = [];
+	let nonLocalVoices = false;
+
+	const getOpenAIVoices = () => {
+		voices = [
+			{ name: 'alloy' },
+			{ name: 'echo' },
+			{ name: 'fable' },
+			{ name: 'onyx' },
+			{ name: 'nova' },
+			{ name: 'shimmer' }
+		];
+	};
+
+	const getOpenAIModels = () => {
+		models = [{ name: 'tts-1' }, { name: 'tts-1-hd' }];
+	};
+
+	const getWebAPIVoices = () => {
+		const getVoicesLoop = setInterval(async () => {
+			voices = await speechSynthesis.getVoices();
+
+			// do your loop
+			if (voices.length > 0) {
+				clearInterval(getVoicesLoop);
+			}
+		}, 100);
+	};
+
+	const updateConfigHandler = async () => {
+		const res = await updateAudioConfig(localStorage.token, {
+			tts: {
+				OPENAI_API_BASE_URL: TTS_OPENAI_API_BASE_URL,
+				OPENAI_API_KEY: TTS_OPENAI_API_KEY,
+				ENGINE: TTS_ENGINE,
+				MODEL: TTS_MODEL,
+				VOICE: TTS_VOICE
+			},
+			stt: {
+				OPENAI_API_BASE_URL: STT_OPENAI_API_BASE_URL,
+				OPENAI_API_KEY: STT_OPENAI_API_KEY,
+				ENGINE: STT_ENGINE,
+				MODEL: STT_MODEL
+			}
+		});
+
+		if (res) {
+			toast.success('Audio settings updated successfully');
+
+			config.set(await getBackendConfig());
+		}
+	};
+
+	onMount(async () => {
+		const res = await getAudioConfig(localStorage.token);
+
+		if (res) {
+			console.log(res);
+			TTS_OPENAI_API_BASE_URL = res.tts.OPENAI_API_BASE_URL;
+			TTS_OPENAI_API_KEY = res.tts.OPENAI_API_KEY;
+
+			TTS_ENGINE = res.tts.ENGINE;
+			TTS_MODEL = res.tts.MODEL;
+			TTS_VOICE = res.tts.VOICE;
+
+			STT_OPENAI_API_BASE_URL = res.stt.OPENAI_API_BASE_URL;
+			STT_OPENAI_API_KEY = res.stt.OPENAI_API_KEY;
+
+			STT_ENGINE = res.stt.ENGINE;
+			STT_MODEL = res.stt.MODEL;
+		}
+
+		if (TTS_ENGINE === 'openai') {
+			getOpenAIVoices();
+			getOpenAIModels();
+		} else {
+			getWebAPIVoices();
+		}
+	});
+</script>
+
+<form
+	class="flex flex-col h-full justify-between space-y-3 text-sm"
+	on:submit|preventDefault={async () => {
+		await updateConfigHandler();
+		dispatch('save');
+	}}
+>
+	<div class=" space-y-3 overflow-y-scroll scrollbar-hidden h-full">
+		<div class="flex flex-col gap-3">
+			<div>
+				<div class=" mb-1 text-sm font-medium">{$i18n.t('STT Settings')}</div>
+
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs font-medium">{$i18n.t('Speech-to-Text Engine')}</div>
+					<div class="flex items-center relative">
+						<select
+							class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
+							bind:value={STT_ENGINE}
+							placeholder="Select an engine"
+						>
+							<option value="">{$i18n.t('Whisper (Local)')}</option>
+							<option value="openai">OpenAI</option>
+							<option value="web">{$i18n.t('Web API')}</option>
+						</select>
+					</div>
+				</div>
+
+				{#if STT_ENGINE === 'openai'}
+					<div>
+						<div class="mt-1 flex gap-2 mb-1">
+							<input
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								placeholder={$i18n.t('API Base URL')}
+								bind:value={STT_OPENAI_API_BASE_URL}
+								required
+							/>
+
+							<input
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								placeholder={$i18n.t('API Key')}
+								bind:value={STT_OPENAI_API_KEY}
+								required
+							/>
+						</div>
+					</div>
+
+					<hr class=" dark:border-gray-850 my-2" />
+
+					<div>
+						<div class=" mb-1.5 text-sm font-medium">{$i18n.t('STT Model')}</div>
+						<div class="flex w-full">
+							<div class="flex-1">
+								<input
+									list="model-list"
+									class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+									bind:value={STT_MODEL}
+									placeholder="Select a model"
+								/>
+
+								<datalist id="model-list">
+									<option value="whisper-1" />
+								</datalist>
+							</div>
+						</div>
+					</div>
+				{/if}
+			</div>
+
+			<hr class=" dark:border-gray-800" />
+
+			<div>
+				<div class=" mb-1 text-sm font-medium">{$i18n.t('TTS Settings')}</div>
+
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs font-medium">{$i18n.t('Text-to-Speech Engine')}</div>
+					<div class="flex items-center relative">
+						<select
+							class=" dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
+							bind:value={TTS_ENGINE}
+							placeholder="Select a mode"
+							on:change={(e) => {
+								if (e.target.value === 'openai') {
+									getOpenAIVoices();
+									TTS_VOICE = 'alloy';
+									TTS_MODEL = 'tts-1';
+								} else {
+									getWebAPIVoices();
+									TTS_VOICE = '';
+								}
+							}}
+						>
+							<option value="">{$i18n.t('Web API')}</option>
+							<option value="openai">{$i18n.t('Open AI')}</option>
+						</select>
+					</div>
+				</div>
+
+				{#if TTS_ENGINE === 'openai'}
+					<div>
+						<div class="mt-1 flex gap-2 mb-1">
+							<input
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								placeholder={$i18n.t('API Base URL')}
+								bind:value={TTS_OPENAI_API_BASE_URL}
+								required
+							/>
+
+							<input
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								placeholder={$i18n.t('API Key')}
+								bind:value={TTS_OPENAI_API_KEY}
+								required
+							/>
+						</div>
+					</div>
+				{/if}
+
+				<hr class=" dark:border-gray-850 my-2" />
+
+				{#if TTS_ENGINE === ''}
+					<div>
+						<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
+						<div class="flex w-full">
+							<div class="flex-1">
+								<select
+									class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+									bind:value={TTS_VOICE}
+								>
+									<option value="" selected={TTS_VOICE !== ''}>{$i18n.t('Default')}</option>
+									{#each voices as voice}
+										<option
+											value={voice.voiceURI}
+											class="bg-gray-100 dark:bg-gray-700"
+											selected={TTS_VOICE === voice.voiceURI}>{voice.name}</option
+										>
+									{/each}
+								</select>
+							</div>
+						</div>
+					</div>
+				{:else if TTS_ENGINE === 'openai'}
+					<div class=" flex gap-2">
+						<div class="w-full">
+							<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
+							<div class="flex w-full">
+								<div class="flex-1">
+									<input
+										list="voice-list"
+										class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+										bind:value={TTS_VOICE}
+										placeholder="Select a voice"
+									/>
+
+									<datalist id="voice-list">
+										{#each voices as voice}
+											<option value={voice.name} />
+										{/each}
+									</datalist>
+								</div>
+							</div>
+						</div>
+						<div class="w-full">
+							<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Model')}</div>
+							<div class="flex w-full">
+								<div class="flex-1">
+									<input
+										list="model-list"
+										class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+										bind:value={TTS_MODEL}
+										placeholder="Select a model"
+									/>
+
+									<datalist id="model-list">
+										{#each models as model}
+											<option value={model.name} />
+										{/each}
+									</datalist>
+								</div>
+							</div>
+						</div>
+					</div>
+				{/if}
+			</div>
+		</div>
+	</div>
+	<div class="flex justify-end text-sm font-medium">
+		<button
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
+			type="submit"
+		>
+			{$i18n.t('Save')}
+		</button>
+	</div>
+</form>

src/lib/components/admin/Settings/Banners.svelte

@@ -1,137 +0,0 @@
-<script lang="ts">
-	import { v4 as uuidv4 } from 'uuid';
-
-	import { getContext, onMount } from 'svelte';
-	import { banners as _banners } from '$lib/stores';
-	import type { Banner } from '$lib/types';
-
-	import { getBanners, setBanners } from '$lib/apis/configs';
-
-	import type { Writable } from 'svelte/store';
-	import type { i18n as i18nType } from 'i18next';
-	import Tooltip from '$lib/components/common/Tooltip.svelte';
-	import Switch from '$lib/components/common/Switch.svelte';
-	const i18n: Writable<i18nType> = getContext('i18n');
-
-	export let saveHandler: Function;
-
-	let banners: Banner[] = [];
-
-	onMount(async () => {
-		banners = await getBanners(localStorage.token);
-	});
-
-	const updateBanners = async () => {
-		_banners.set(await setBanners(localStorage.token, banners));
-	};
-</script>
-
-<form
-	class="flex flex-col h-full justify-between space-y-3 text-sm"
-	on:submit|preventDefault={async () => {
-		updateBanners();
-		saveHandler();
-	}}
->
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80 h-full">
-		<div class=" space-y-3 pr-1.5">
-			<div class="flex w-full justify-between mb-2">
-				<div class=" self-center text-sm font-semibold">
-					{$i18n.t('Banners')}
-				</div>
-
-				<button
-					class="p-1 px-3 text-xs flex rounded transition"
-					type="button"
-					on:click={() => {
-						if (banners.length === 0 || banners.at(-1).content !== '') {
-							banners = [
-								...banners,
-								{
-									id: uuidv4(),
-									type: '',
-									title: '',
-									content: '',
-									dismissible: true,
-									timestamp: Math.floor(Date.now() / 1000)
-								}
-							];
-						}
-					}}
-				>
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						viewBox="0 0 20 20"
-						fill="currentColor"
-						class="w-4 h-4"
-					>
-						<path
-							d="M10.75 4.75a.75.75 0 00-1.5 0v4.5h-4.5a.75.75 0 000 1.5h4.5v4.5a.75.75 0 001.5 0v-4.5h4.5a.75.75 0 000-1.5h-4.5v-4.5z"
-						/>
-					</svg>
-				</button>
-			</div>
-			<div class="flex flex-col space-y-1">
-				{#each banners as banner, bannerIdx}
-					<div class=" flex justify-between">
-						<div class="flex flex-row flex-1 border rounded-xl dark:border-gray-800">
-							<select
-								class="w-fit capitalize rounded-xl py-2 px-4 text-xs bg-transparent outline-none"
-								bind:value={banner.type}
-							>
-								{#if banner.type == ''}
-									<option value="" selected disabled class="text-gray-900">{$i18n.t('Type')}</option
-									>
-								{/if}
-								<option value="info" class="text-gray-900">{$i18n.t('Info')}</option>
-								<option value="warning" class="text-gray-900">{$i18n.t('Warning')}</option>
-								<option value="error" class="text-gray-900">{$i18n.t('Error')}</option>
-								<option value="success" class="text-gray-900">{$i18n.t('Success')}</option>
-							</select>
-
-							<input
-								class="pr-5 py-1.5 text-xs w-full bg-transparent outline-none"
-								placeholder={$i18n.t('Content')}
-								bind:value={banner.content}
-							/>
-
-							<div class="relative top-1.5 -left-2">
-								<Tooltip content="Dismissible" className="flex h-fit items-center">
-									<Switch bind:state={banner.dismissible} />
-								</Tooltip>
-							</div>
-						</div>
-
-						<button
-							class="px-2"
-							type="button"
-							on:click={() => {
-								banners.splice(bannerIdx, 1);
-								banners = banners;
-							}}
-						>
-							<svg
-								xmlns="http://www.w3.org/2000/svg"
-								viewBox="0 0 20 20"
-								fill="currentColor"
-								class="w-4 h-4"
-							>
-								<path
-									d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
-								/>
-							</svg>
-						</button>
-					</div>
-				{/each}
-			</div>
-		</div>
-	</div>
-	<div class="flex justify-end pt-3 text-sm font-medium">
-		<button
-			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
-			type="submit"
-		>
-			Save
-		</button>
-	</div>
-</form>

src/lib/components/admin/Settings/Connections.svelte

@@ -23,10 +23,14 @@
 	import Switch from '$lib/components/common/Switch.svelte';
 	import Spinner from '$lib/components/common/Spinner.svelte';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import { getModels as _getModels } from '$lib/apis';
 
 	const i18n = getContext('i18n');
 
-	export let getModels: Function;
+	const getModels = async () => {
+		const models = await _getModels(localStorage.token);
+		return models;
+	};
 
 	// External
 	let OLLAMA_BASE_URLS = [''];
@@ -158,7 +162,7 @@
 		dispatch('save');
 	}}
 >
-	<div class="space-y-3 pr-1.5 overflow-y-scroll h-[24rem] max-h-[25rem]">
+	<div class="space-y-3 overflow-y-scroll scrollbar-hidden h-full">
 		{#if ENABLE_OPENAI_API !== null && ENABLE_OLLAMA_API !== null}
 			<div class=" space-y-3">
 				<div class="mt-2 space-y-2 pr-1.5">
@@ -300,7 +304,7 @@
 				</div>
 			</div>
 
-			<hr class=" dark:border-gray-700" />
+			<hr class=" dark:border-gray-850" />
 
 			<div class="pr-1.5 space-y-2">
 				<div class="flex justify-between items-center text-sm">

src/lib/components/admin/Settings/Database.svelte

@@ -30,7 +30,7 @@
 		saveHandler();
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
+	<div class=" space-y-3 overflow-y-scroll scrollbar-hidden h-full">
 		<div>
 			<div class=" mb-2 text-sm font-medium">{$i18n.t('Database')}</div>
 

src/lib/components/admin/Settings/Documents.svelte

@@ -8,7 +8,10 @@
 		getEmbeddingConfig,
 		updateEmbeddingConfig,
 		getRerankingConfig,
-		updateRerankingConfig
+		updateRerankingConfig,
+		resetUploadDir,
+		getRAGConfig,
+		updateRAGConfig
 	} from '$lib/apis/rag';
 
 	import { documents, models } from '$lib/stores';
@@ -24,11 +27,16 @@
 	let updateRerankingModelLoading = false;
 
 	let showResetConfirm = false;
+	let showResetUploadDirConfirm = false;
 
 	let embeddingEngine = '';
 	let embeddingModel = '';
 	let rerankingModel = '';
 
+	let chunkSize = 0;
+	let chunkOverlap = 0;
+	let pdfExtractImages = true;
+
 	let OpenAIKey = '';
 	let OpenAIUrl = '';
 	let OpenAIBatchSize = 1;
@@ -150,6 +158,14 @@
 		if (querySettings.hybrid) {
 			rerankingModelUpdateHandler();
 		}
+
+		const res = await updateRAGConfig(localStorage.token, {
+			pdf_extract_images: pdfExtractImages,
+			chunk: {
+				chunk_overlap: chunkOverlap,
+				chunk_size: chunkSize
+			}
+		});
 	};
 
 	const setEmbeddingConfig = async () => {
@@ -183,6 +199,15 @@
 		await setRerankingConfig();
 
 		querySettings = await getQuerySettings(localStorage.token);
+
+		const res = await getRAGConfig(localStorage.token);
+
+		if (res) {
+			pdfExtractImages = res.pdf_extract_images;
+
+			chunkSize = res.chunk.chunk_size;
+			chunkOverlap = res.chunk.chunk_overlap;
+		}
 	});
 </script>
 
@@ -193,7 +218,7 @@
 		saveHandler();
 	}}
 >
-	<div class=" space-y-2.5 pr-1.5 overflow-y-scroll max-h-[28rem]">
+	<div class=" space-y-2.5 overflow-y-scroll scrollbar-hidden h-full">
 		<div class="flex flex-col gap-0.5">
 			<div class=" mb-0.5 text-sm font-medium">{$i18n.t('General Settings')}</div>
 
@@ -330,7 +355,7 @@
 			</div>
 		</div>
 
-		<hr class=" dark:border-gray-700 my-1" />
+		<hr class=" dark:border-gray-850 my-1" />
 
 		<div class="space-y-2" />
 		<div>
@@ -348,10 +373,8 @@
 							{#if !embeddingModel}
 								<option value="" disabled selected>{$i18n.t('Select a model')}</option>
 							{/if}
-							{#each $models.filter((m) => m.id && !m.external) as model}
-								<option value={model.name} class="bg-gray-100 dark:bg-gray-700"
-									>{model.name + ' (' + (model.size / 1024 ** 3).toFixed(1) + ' GB)'}</option
-								>
+							{#each $models.filter((m) => m.id && m.ollama && !(m?.preset ?? false)) as model}
+								<option value={model.id} class="bg-gray-100 dark:bg-gray-700">{model.name}</option>
 							{/each}
 						</select>
 					</div>
@@ -496,99 +519,319 @@
 			{/if}
 		</div>
 
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
 
-		{#if showResetConfirm}
-			<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
-				<div class="flex items-center space-x-3">
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						viewBox="0 0 16 16"
-						fill="currentColor"
-						class="w-4 h-4"
-					>
-						<path d="M2 3a1 1 0 0 1 1-1h10a1 1 0 0 1 1 1v1a1 1 0 0 1-1 1H3a1 1 0 0 1-1-1V3Z" />
-						<path
-							fill-rule="evenodd"
-							d="M13 6H3v6a2 2 0 0 0 2 2h6a2 2 0 0 0 2-2V6ZM5.72 7.47a.75.75 0 0 1 1.06 0L8 8.69l1.22-1.22a.75.75 0 1 1 1.06 1.06L9.06 9.75l1.22 1.22a.75.75 0 1 1-1.06 1.06L8 10.81l-1.22 1.22a.75.75 0 0 1-1.06-1.06l1.22-1.22-1.22-1.22a.75.75 0 0 1 0-1.06Z"
-							clip-rule="evenodd"
+		<div class=" ">
+			<div class=" text-sm font-medium">{$i18n.t('Query Params')}</div>
+
+			<div class=" flex">
+				<div class="  flex w-full justify-between">
+					<div class="self-center text-xs font-medium min-w-fit">{$i18n.t('Top K')}</div>
+
+					<div class="self-center p-3">
+						<input
+							class=" w-full rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							type="number"
+							placeholder={$i18n.t('Enter Top K')}
+							bind:value={querySettings.k}
+							autocomplete="off"
+							min="0"
 						/>
-					</svg>
-					<span>{$i18n.t('Are you sure?')}</span>
+					</div>
 				</div>
 
-				<div class="flex space-x-1.5 items-center">
+				{#if querySettings.hybrid === true}
+					<div class="flex w-full">
+						<div class=" self-center text-xs font-medium min-w-fit">
+							{$i18n.t('Minimum Score')}
+						</div>
+
+						<div class="self-center p-3">
+							<input
+								class=" w-full rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								type="number"
+								step="0.01"
+								placeholder={$i18n.t('Enter Score')}
+								bind:value={querySettings.r}
+								autocomplete="off"
+								min="0.0"
+								title={$i18n.t('The score should be a value between 0.0 (0%) and 1.0 (100%).')}
+							/>
+						</div>
+					</div>
+				{/if}
+			</div>
+
+			{#if querySettings.hybrid === true}
+				<div class="mt-2 mb-1 text-xs text-gray-400 dark:text-gray-500">
+					{$i18n.t(
+						'Note: If you set a minimum score, the search will only return documents with a score greater than or equal to the minimum score.'
+					)}
+				</div>
+
+				<hr class=" dark:border-gray-850 my-3" />
+			{/if}
+
+			<div>
+				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('RAG Template')}</div>
+				<textarea
+					bind:value={querySettings.template}
+					class="w-full rounded-lg px-4 py-3 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none resize-none"
+					rows="4"
+				/>
+			</div>
+		</div>
+
+		<hr class=" dark:border-gray-850" />
+
+		<div class=" ">
+			<div class=" text-sm font-medium">{$i18n.t('Chunk Params')}</div>
+
+			<div class=" my-2 flex gap-1.5">
+				<div class="  w-full justify-between">
+					<div class="self-center text-xs font-medium min-w-fit mb-1">{$i18n.t('Chunk Size')}</div>
+					<div class="self-center">
+						<input
+							class=" w-full rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							type="number"
+							placeholder={$i18n.t('Enter Chunk Size')}
+							bind:value={chunkSize}
+							autocomplete="off"
+							min="0"
+						/>
+					</div>
+				</div>
+
+				<div class="w-full">
+					<div class=" self-center text-xs font-medium min-w-fit mb-1">
+						{$i18n.t('Chunk Overlap')}
+					</div>
+
+					<div class="self-center">
+						<input
+							class="w-full rounded-lg py-1.5 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+							type="number"
+							placeholder={$i18n.t('Enter Chunk Overlap')}
+							bind:value={chunkOverlap}
+							autocomplete="off"
+							min="0"
+						/>
+					</div>
+				</div>
+			</div>
+
+			<div class="my-3">
+				<div class="flex justify-between items-center text-xs">
+					<div class=" text-xs font-medium">{$i18n.t('PDF Extract Images (OCR)')}</div>
+
 					<button
-						class="hover:text-white transition"
+						class=" text-xs font-medium text-gray-500"
+						type="button"
 						on:click={() => {
-							const res = resetVectorDB(localStorage.token).catch((error) => {
-								toast.error(error);
-								return null;
-							});
-
-							if (res) {
-								toast.success($i18n.t('Success'));
-							}
-
-							showResetConfirm = false;
-						}}
+							pdfExtractImages = !pdfExtractImages;
+						}}>{pdfExtractImages ? $i18n.t('On') : $i18n.t('Off')}</button
 					>
+				</div>
+			</div>
+		</div>
+
+		<hr class=" dark:border-gray-850" />
+
+		<div>
+			{#if showResetUploadDirConfirm}
+				<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
+					<div class="flex items-center space-x-3">
 						<svg
 							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 20 20"
+							viewBox="0 0 24 24"
+							fill="currentColor"
+							class="size-4"
+						>
+							<path
+								fill-rule="evenodd"
+								d="M5.625 1.5H9a3.75 3.75 0 0 1 3.75 3.75v1.875c0 1.036.84 1.875 1.875 1.875H16.5a3.75 3.75 0 0 1 3.75 3.75v7.875c0 1.035-.84 1.875-1.875 1.875H5.625a1.875 1.875 0 0 1-1.875-1.875V3.375c0-1.036.84-1.875 1.875-1.875ZM9.75 14.25a.75.75 0 0 0 0 1.5H15a.75.75 0 0 0 0-1.5H9.75Z"
+								clip-rule="evenodd"
+							/>
+							<path
+								d="M14.25 5.25a5.23 5.23 0 0 0-1.279-3.434 9.768 9.768 0 0 1 6.963 6.963A5.23 5.23 0 0 0 16.5 7.5h-1.875a.375.375 0 0 1-.375-.375V5.25Z"
+							/>
+						</svg>
+						<span>{$i18n.t('Are you sure?')}</span>
+					</div>
+
+					<div class="flex space-x-1.5 items-center">
+						<button
+							class="hover:text-white transition"
+							on:click={() => {
+								const res = resetUploadDir(localStorage.token).catch((error) => {
+									toast.error(error);
+									return null;
+								});
+
+								if (res) {
+									toast.success($i18n.t('Success'));
+								}
+
+								showResetUploadDirConfirm = false;
+							}}
+							type="button"
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									fill-rule="evenodd"
+									d="M16.704 4.153a.75.75 0 01.143 1.052l-8 10.5a.75.75 0 01-1.127.075l-4.5-4.5a.75.75 0 011.06-1.06l3.894 3.893 7.48-9.817a.75.75 0 011.05-.143z"
+									clip-rule="evenodd"
+								/>
+							</svg>
+						</button>
+						<button
+							class="hover:text-white transition"
+							type="button"
+							on:click={() => {
+								showResetUploadDirConfirm = false;
+							}}
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+								/>
+							</svg>
+						</button>
+					</div>
+				</div>
+			{:else}
+				<button
+					class=" flex rounded-xl py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
+					on:click={() => {
+						showResetUploadDirConfirm = true;
+					}}
+					type="button"
+				>
+					<div class=" self-center mr-3">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 24 24"
+							fill="currentColor"
+							class="size-4"
+						>
+							<path
+								fill-rule="evenodd"
+								d="M5.625 1.5H9a3.75 3.75 0 0 1 3.75 3.75v1.875c0 1.036.84 1.875 1.875 1.875H16.5a3.75 3.75 0 0 1 3.75 3.75v7.875c0 1.035-.84 1.875-1.875 1.875H5.625a1.875 1.875 0 0 1-1.875-1.875V3.375c0-1.036.84-1.875 1.875-1.875ZM9.75 14.25a.75.75 0 0 0 0 1.5H15a.75.75 0 0 0 0-1.5H9.75Z"
+								clip-rule="evenodd"
+							/>
+							<path
+								d="M14.25 5.25a5.23 5.23 0 0 0-1.279-3.434 9.768 9.768 0 0 1 6.963 6.963A5.23 5.23 0 0 0 16.5 7.5h-1.875a.375.375 0 0 1-.375-.375V5.25Z"
+							/>
+						</svg>
+					</div>
+					<div class=" self-center text-sm font-medium">{$i18n.t('Reset Upload Directory')}</div>
+				</button>
+			{/if}
+
+			{#if showResetConfirm}
+				<div class="flex justify-between rounded-md items-center py-2 px-3.5 w-full transition">
+					<div class="flex items-center space-x-3">
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 16 16"
 							fill="currentColor"
 							class="w-4 h-4"
 						>
 							<path
 								fill-rule="evenodd"
-								d="M16.704 4.153a.75.75 0 01.143 1.052l-8 10.5a.75.75 0 01-1.127.075l-4.5-4.5a.75.75 0 011.06-1.06l3.894 3.893 7.48-9.817a.75.75 0 011.05-.143z"
+								d="M3.5 2A1.5 1.5 0 0 0 2 3.5v9A1.5 1.5 0 0 0 3.5 14h9a1.5 1.5 0 0 0 1.5-1.5v-7A1.5 1.5 0 0 0 12.5 4H9.621a1.5 1.5 0 0 1-1.06-.44L7.439 2.44A1.5 1.5 0 0 0 6.38 2H3.5Zm6.75 7.75a.75.75 0 0 0 0-1.5h-4.5a.75.75 0 0 0 0 1.5h4.5Z"
 								clip-rule="evenodd"
 							/>
 						</svg>
-					</button>
-					<button
-						class="hover:text-white transition"
-						on:click={() => {
-							showResetConfirm = false;
-						}}
-					>
+						<span>{$i18n.t('Are you sure?')}</span>
+					</div>
+
+					<div class="flex space-x-1.5 items-center">
+						<button
+							class="hover:text-white transition"
+							on:click={() => {
+								const res = resetVectorDB(localStorage.token).catch((error) => {
+									toast.error(error);
+									return null;
+								});
+
+								if (res) {
+									toast.success($i18n.t('Success'));
+								}
+
+								showResetConfirm = false;
+							}}
+							type="button"
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									fill-rule="evenodd"
+									d="M16.704 4.153a.75.75 0 01.143 1.052l-8 10.5a.75.75 0 01-1.127.075l-4.5-4.5a.75.75 0 011.06-1.06l3.894 3.893 7.48-9.817a.75.75 0 011.05-.143z"
+									clip-rule="evenodd"
+								/>
+							</svg>
+						</button>
+						<button
+							class="hover:text-white transition"
+							on:click={() => {
+								showResetConfirm = false;
+							}}
+							type="button"
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+								/>
+							</svg>
+						</button>
+					</div>
+				</div>
+			{:else}
+				<button
+					class=" flex rounded-xl py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
+					on:click={() => {
+						showResetConfirm = true;
+					}}
+					type="button"
+				>
+					<div class=" self-center mr-3">
 						<svg
 							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 20 20"
+							viewBox="0 0 16 16"
 							fill="currentColor"
 							class="w-4 h-4"
 						>
 							<path
-								d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+								fill-rule="evenodd"
+								d="M3.5 2A1.5 1.5 0 0 0 2 3.5v9A1.5 1.5 0 0 0 3.5 14h9a1.5 1.5 0 0 0 1.5-1.5v-7A1.5 1.5 0 0 0 12.5 4H9.621a1.5 1.5 0 0 1-1.06-.44L7.439 2.44A1.5 1.5 0 0 0 6.38 2H3.5Zm6.75 7.75a.75.75 0 0 0 0-1.5h-4.5a.75.75 0 0 0 0 1.5h4.5Z"
+								clip-rule="evenodd"
 							/>
 						</svg>
-					</button>
-				</div>
-			</div>
-		{:else}
-			<button
-				class=" flex rounded-md py-2 px-3.5 w-full hover:bg-gray-200 dark:hover:bg-gray-800 transition"
-				on:click={() => {
-					showResetConfirm = true;
-				}}
-			>
-				<div class=" self-center mr-3">
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						viewBox="0 0 16 16"
-						fill="currentColor"
-						class="w-4 h-4"
-					>
-						<path
-							fill-rule="evenodd"
-							d="M3.5 2A1.5 1.5 0 0 0 2 3.5v9A1.5 1.5 0 0 0 3.5 14h9a1.5 1.5 0 0 0 1.5-1.5v-7A1.5 1.5 0 0 0 12.5 4H9.621a1.5 1.5 0 0 1-1.06-.44L7.439 2.44A1.5 1.5 0 0 0 6.38 2H3.5Zm6.75 7.75a.75.75 0 0 0 0-1.5h-4.5a.75.75 0 0 0 0 1.5h4.5Z"
-							clip-rule="evenodd"
-						/>
-					</svg>
-				</div>
-				<div class=" self-center text-sm font-medium">{$i18n.t('Reset Vector Storage')}</div>
-			</button>
-		{/if}
+					</div>
+					<div class=" self-center text-sm font-medium">{$i18n.t('Reset Vector Storage')}</div>
+				</button>
+			{/if}
+		</div>
 	</div>
 	<div class="flex justify-end pt-3 text-sm font-medium">
 		<button

src/lib/components/admin/Settings/General.svelte

@@ -56,7 +56,7 @@
 		saveHandler();
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-[22rem]">
+	<div class=" space-y-3 overflow-y-scroll scrollbar-hidden h-full">
 		{#if adminConfig !== null}
 			<div>
 				<div class=" mb-3 text-sm font-medium">{$i18n.t('General Settings')}</div>

src/lib/components/admin/Settings/Images.svelte

@@ -23,8 +23,6 @@
 
 	const i18n = getContext('i18n');
 
-	export let saveSettings: Function;
-
 	let loading = false;
 
 	let imageGenerationEngine = '';
@@ -171,7 +169,7 @@
 		loading = false;
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-[24rem]">
+	<div class=" space-y-3 overflow-y-scroll scrollbar-hidden">
 		<div>
 			<div class=" mb-1 text-sm font-medium">{$i18n.t('Image Settings')}</div>
 
@@ -228,7 +226,7 @@
 				</div>
 			</div>
 		</div>
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
 
 		{#if imageGenerationEngine === ''}
 			<div class=" mb-2.5 text-sm font-medium">{$i18n.t('AUTOMATIC1111 Base URL')}</div>
@@ -326,7 +324,7 @@
 		{/if}
 
 		{#if enableImageGeneration}
-			<hr class=" dark:border-gray-700" />
+			<hr class=" dark:border-gray-850" />
 
 			<div>
 				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Default Model')}</div>

src/lib/components/admin/Settings/Interface.svelte

@@ -0,0 +1,339 @@
+<script lang="ts">
+	import { v4 as uuidv4 } from 'uuid';
+	import { toast } from 'svelte-sonner';
+
+	import { getBackendConfig, getTaskConfig, updateTaskConfig } from '$lib/apis';
+	import { setDefaultPromptSuggestions } from '$lib/apis/configs';
+	import { config, models, settings, user } from '$lib/stores';
+	import { createEventDispatcher, onMount, getContext } from 'svelte';
+
+	import { banners as _banners } from '$lib/stores';
+	import type { Banner } from '$lib/types';
+
+	import { getBanners, setBanners } from '$lib/apis/configs';
+
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import Switch from '$lib/components/common/Switch.svelte';
+
+	const dispatch = createEventDispatcher();
+
+	const i18n = getContext('i18n');
+
+	let taskConfig = {
+		TASK_MODEL: '',
+		TASK_MODEL_EXTERNAL: '',
+		TITLE_GENERATION_PROMPT_TEMPLATE: '',
+		SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE: '',
+		SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD: 0
+	};
+
+	let promptSuggestions = [];
+	let banners: Banner[] = [];
+
+	const updateInterfaceHandler = async () => {
+		taskConfig = await updateTaskConfig(localStorage.token, taskConfig);
+
+		promptSuggestions = await setDefaultPromptSuggestions(localStorage.token, promptSuggestions);
+		await updateBanners();
+
+		await config.set(await getBackendConfig());
+	};
+
+	onMount(async () => {
+		taskConfig = await getTaskConfig(localStorage.token);
+
+		promptSuggestions = $config?.default_prompt_suggestions;
+
+		banners = await getBanners(localStorage.token);
+	});
+
+	const updateBanners = async () => {
+		_banners.set(await setBanners(localStorage.token, banners));
+	};
+</script>
+
+<form
+	class="flex flex-col h-full justify-between space-y-3 text-sm"
+	on:submit|preventDefault={() => {
+		updateInterfaceHandler();
+		dispatch('save');
+	}}
+>
+	<div class="  overflow-y-scroll scrollbar-hidden h-full pr-1.5">
+		<div>
+			<div class=" mb-2.5 text-sm font-medium flex">
+				<div class=" mr-1">{$i18n.t('Set Task Model')}</div>
+				<Tooltip
+					content={$i18n.t(
+						'A task model is used when performing tasks such as generating titles for chats and web search queries'
+					)}
+				>
+					<svg
+						xmlns="http://www.w3.org/2000/svg"
+						fill="none"
+						viewBox="0 0 24 24"
+						stroke-width="1.5"
+						stroke="currentColor"
+						class="w-5 h-5"
+					>
+						<path
+							stroke-linecap="round"
+							stroke-linejoin="round"
+							d="m11.25 11.25.041-.02a.75.75 0 0 1 1.063.852l-.708 2.836a.75.75 0 0 0 1.063.853l.041-.021M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Zm-9-3.75h.008v.008H12V8.25Z"
+						/>
+					</svg>
+				</Tooltip>
+			</div>
+			<div class="flex w-full gap-2">
+				<div class="flex-1">
+					<div class=" text-xs mb-1">{$i18n.t('Local Models')}</div>
+					<select
+						class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+						bind:value={taskConfig.TASK_MODEL}
+						placeholder={$i18n.t('Select a model')}
+					>
+						<option value="" selected>{$i18n.t('Current Model')}</option>
+						{#each $models.filter((m) => m.owned_by === 'ollama') as model}
+							<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
+								{model.name}
+							</option>
+						{/each}
+					</select>
+				</div>
+
+				<div class="flex-1">
+					<div class=" text-xs mb-1">{$i18n.t('External Models')}</div>
+					<select
+						class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+						bind:value={taskConfig.TASK_MODEL_EXTERNAL}
+						placeholder={$i18n.t('Select a model')}
+					>
+						<option value="" selected>{$i18n.t('Current Model')}</option>
+						{#each $models as model}
+							<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
+								{model.name}
+							</option>
+						{/each}
+					</select>
+				</div>
+			</div>
+
+			<div class="mt-3">
+				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Title Generation Prompt')}</div>
+				<textarea
+					bind:value={taskConfig.TITLE_GENERATION_PROMPT_TEMPLATE}
+					class="w-full rounded-lg py-3 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none resize-none"
+					rows="6"
+				/>
+			</div>
+
+			<div class="mt-3">
+				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Search Query Generation Prompt')}</div>
+				<textarea
+					bind:value={taskConfig.SEARCH_QUERY_GENERATION_PROMPT_TEMPLATE}
+					class="w-full rounded-lg py-3 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none resize-none"
+					rows="6"
+				/>
+			</div>
+
+			<div class="mt-3">
+				<div class=" mb-2.5 text-sm font-medium">
+					{$i18n.t('Search Query Generation Prompt Length Threshold')}
+				</div>
+				<input
+					bind:value={taskConfig.SEARCH_QUERY_PROMPT_LENGTH_THRESHOLD}
+					class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none resize-none"
+					type="number"
+				/>
+			</div>
+		</div>
+
+		<hr class=" dark:border-gray-850 my-3" />
+
+		<div class=" space-y-3 {banners.length > 0 ? ' mb-3' : ''}">
+			<div class="flex w-full justify-between">
+				<div class=" self-center text-sm font-semibold">
+					{$i18n.t('Banners')}
+				</div>
+
+				<button
+					class="p-1 px-3 text-xs flex rounded transition"
+					type="button"
+					on:click={() => {
+						if (banners.length === 0 || banners.at(-1).content !== '') {
+							banners = [
+								...banners,
+								{
+									id: uuidv4(),
+									type: '',
+									title: '',
+									content: '',
+									dismissible: true,
+									timestamp: Math.floor(Date.now() / 1000)
+								}
+							];
+						}
+					}}
+				>
+					<svg
+						xmlns="http://www.w3.org/2000/svg"
+						viewBox="0 0 20 20"
+						fill="currentColor"
+						class="w-4 h-4"
+					>
+						<path
+							d="M10.75 4.75a.75.75 0 00-1.5 0v4.5h-4.5a.75.75 0 000 1.5h4.5v4.5a.75.75 0 001.5 0v-4.5h4.5a.75.75 0 000-1.5h-4.5v-4.5z"
+						/>
+					</svg>
+				</button>
+			</div>
+			<div class="flex flex-col space-y-1">
+				{#each banners as banner, bannerIdx}
+					<div class=" flex justify-between">
+						<div class="flex flex-row flex-1 border rounded-xl dark:border-gray-800">
+							<select
+								class="w-fit capitalize rounded-xl py-2 px-4 text-xs bg-transparent outline-none"
+								bind:value={banner.type}
+								required
+							>
+								{#if banner.type == ''}
+									<option value="" selected disabled class="text-gray-900">{$i18n.t('Type')}</option
+									>
+								{/if}
+								<option value="info" class="text-gray-900">{$i18n.t('Info')}</option>
+								<option value="warning" class="text-gray-900">{$i18n.t('Warning')}</option>
+								<option value="error" class="text-gray-900">{$i18n.t('Error')}</option>
+								<option value="success" class="text-gray-900">{$i18n.t('Success')}</option>
+							</select>
+
+							<input
+								class="pr-5 py-1.5 text-xs w-full bg-transparent outline-none"
+								placeholder={$i18n.t('Content')}
+								bind:value={banner.content}
+							/>
+
+							<div class="relative top-1.5 -left-2">
+								<Tooltip content={$i18n.t('Dismissible')} className="flex h-fit items-center">
+									<Switch bind:state={banner.dismissible} />
+								</Tooltip>
+							</div>
+						</div>
+
+						<button
+							class="px-2"
+							type="button"
+							on:click={() => {
+								banners.splice(bannerIdx, 1);
+								banners = banners;
+							}}
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="w-4 h-4"
+							>
+								<path
+									d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+								/>
+							</svg>
+						</button>
+					</div>
+				{/each}
+			</div>
+		</div>
+
+		{#if $user.role === 'admin'}
+			<div class=" space-y-3">
+				<div class="flex w-full justify-between mb-2">
+					<div class=" self-center text-sm font-semibold">
+						{$i18n.t('Default Prompt Suggestions')}
+					</div>
+
+					<button
+						class="p-1 px-3 text-xs flex rounded transition"
+						type="button"
+						on:click={() => {
+							if (promptSuggestions.length === 0 || promptSuggestions.at(-1).content !== '') {
+								promptSuggestions = [...promptSuggestions, { content: '', title: ['', ''] }];
+							}
+						}}
+					>
+						<svg
+							xmlns="http://www.w3.org/2000/svg"
+							viewBox="0 0 20 20"
+							fill="currentColor"
+							class="w-4 h-4"
+						>
+							<path
+								d="M10.75 4.75a.75.75 0 00-1.5 0v4.5h-4.5a.75.75 0 000 1.5h4.5v4.5a.75.75 0 001.5 0v-4.5h4.5a.75.75 0 000-1.5h-4.5v-4.5z"
+							/>
+						</svg>
+					</button>
+				</div>
+				<div class="grid lg:grid-cols-2 flex-col gap-1.5">
+					{#each promptSuggestions as prompt, promptIdx}
+						<div class=" flex dark:bg-gray-850 rounded-xl py-1.5">
+							<div class="flex flex-col flex-1 pl-1">
+								<div class="flex border-b dark:border-gray-800 w-full">
+									<input
+										class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r dark:border-gray-800"
+										placeholder={$i18n.t('Title (e.g. Tell me a fun fact)')}
+										bind:value={prompt.title[0]}
+									/>
+
+									<input
+										class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r dark:border-gray-800"
+										placeholder={$i18n.t('Subtitle (e.g. about the Roman Empire)')}
+										bind:value={prompt.title[1]}
+									/>
+								</div>
+
+								<input
+									class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r dark:border-gray-800"
+									placeholder={$i18n.t('Prompt (e.g. Tell me a fun fact about the Roman Empire)')}
+									bind:value={prompt.content}
+								/>
+							</div>
+
+							<button
+								class="px-3"
+								type="button"
+								on:click={() => {
+									promptSuggestions.splice(promptIdx, 1);
+									promptSuggestions = promptSuggestions;
+								}}
+							>
+								<svg
+									xmlns="http://www.w3.org/2000/svg"
+									viewBox="0 0 20 20"
+									fill="currentColor"
+									class="w-4 h-4"
+								>
+									<path
+										d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+									/>
+								</svg>
+							</button>
+						</div>
+					{/each}
+				</div>
+
+				{#if promptSuggestions.length > 0}
+					<div class="text-xs text-left w-full mt-2">
+						{$i18n.t('Adjusting these settings will apply changes universally to all users.')}
+					</div>
+				{/if}
+			</div>
+		{/if}
+	</div>
+
+	<div class="flex justify-end text-sm font-medium">
+		<button
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
+			type="submit"
+		>
+			{$i18n.t('Save')}
+		</button>
+	</div>
+</form>

src/lib/components/admin/Settings/Pipelines.svelte

@@ -14,7 +14,8 @@
 		getModels,
 		getPipelinesList,
 		downloadPipeline,
-		deletePipeline
+		deletePipeline,
+		uploadPipeline
 	} from '$lib/apis';
 
 	import Spinner from '$lib/components/common/Spinner.svelte';
@@ -24,6 +25,9 @@
 	export let saveHandler: Function;
 
 	let downloading = false;
+	let uploading = false;
+
+	let pipelineFiles;
 
 	let PIPELINES_LIST = null;
 	let selectedPipelinesUrlIdx = '';
@@ -126,6 +130,41 @@
 		downloading = false;
 	};
 
+	const uploadPipelineHandler = async () => {
+		uploading = true;
+
+		if (pipelineFiles && pipelineFiles.length !== 0) {
+			const file = pipelineFiles[0];
+
+			console.log(file);
+
+			const res = await uploadPipeline(localStorage.token, file, selectedPipelinesUrlIdx).catch(
+				(error) => {
+					console.log(error);
+					toast.error('Something went wrong :/');
+					return null;
+				}
+			);
+
+			if (res) {
+				toast.success('Pipeline downloaded successfully');
+				setPipelines();
+				models.set(await getModels(localStorage.token));
+			}
+		} else {
+			toast.error('No file selected');
+		}
+
+		pipelineFiles = null;
+		const pipelineUploadInputElement = document.getElementById('pipeline-upload-input');
+
+		if (pipelineUploadInputElement) {
+			pipelineUploadInputElement.value = null;
+		}
+
+		uploading = false;
+	};
+
 	const deletePipelineHandler = async () => {
 		const res = await deletePipeline(
 			localStorage.token,
@@ -161,7 +200,7 @@
 		updateHandler();
 	}}
 >
-	<div class="  pr-1.5 overflow-y-scroll max-h-80 h-full">
+	<div class="overflow-y-scroll scrollbar-hidden h-full">
 		{#if PIPELINES_LIST !== null}
 			<div class="flex w-full justify-between mb-2">
 				<div class=" self-center text-sm font-semibold">
@@ -196,6 +235,91 @@
 					</div>
 				</div>
 
+				<div class=" my-2">
+					<div class=" mb-2 text-sm font-medium">
+						{$i18n.t('Upload Pipeline')}
+					</div>
+					<div class="flex w-full">
+						<div class="flex-1 mr-2">
+							<input
+								id="pipelines-upload-input"
+								bind:files={pipelineFiles}
+								type="file"
+								accept=".py"
+								hidden
+							/>
+
+							<button
+								class="w-full text-sm font-medium py-2 bg-transparent hover:bg-gray-100 border border-dashed dark:border-gray-800 dark:hover:bg-gray-850 text-center rounded-xl"
+								type="button"
+								on:click={() => {
+									document.getElementById('pipelines-upload-input')?.click();
+								}}
+							>
+								{#if pipelineFiles}
+									{pipelineFiles.length > 0 ? `${pipelineFiles.length}` : ''} pipeline(s) selected.
+								{:else}
+									{$i18n.t('Click here to select a py file.')}
+								{/if}
+							</button>
+						</div>
+						<button
+							class="px-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-gray-100 rounded-lg transition"
+							on:click={() => {
+								uploadPipelineHandler();
+							}}
+							disabled={uploading}
+							type="button"
+						>
+							{#if uploading}
+								<div class="self-center">
+									<svg
+										class=" w-4 h-4"
+										viewBox="0 0 24 24"
+										fill="currentColor"
+										xmlns="http://www.w3.org/2000/svg"
+									>
+										<style>
+											.spinner_ajPY {
+												transform-origin: center;
+												animation: spinner_AtaB 0.75s infinite linear;
+											}
+
+											@keyframes spinner_AtaB {
+												100% {
+													transform: rotate(360deg);
+												}
+											}
+										</style>
+										<path
+											d="M12,1A11,11,0,1,0,23,12,11,11,0,0,0,12,1Zm0,19a8,8,0,1,1,8-8A8,8,0,0,1,12,20Z"
+											opacity=".25"
+										/>
+										<path
+											d="M10.14,1.16a11,11,0,0,0-9,8.92A1.59,1.59,0,0,0,2.46,12,1.52,1.52,0,0,0,4.11,10.7a8,8,0,0,1,6.66-6.61A1.42,1.42,0,0,0,12,2.69h0A1.57,1.57,0,0,0,10.14,1.16Z"
+											class="spinner_ajPY"
+										/>
+									</svg>
+								</div>
+							{:else}
+								<svg
+									xmlns="http://www.w3.org/2000/svg"
+									viewBox="0 0 16 16"
+									fill="currentColor"
+									class="size-4"
+								>
+									<path
+										d="M7.25 10.25a.75.75 0 0 0 1.5 0V4.56l2.22 2.22a.75.75 0 1 0 1.06-1.06l-3.5-3.5a.75.75 0 0 0-1.06 0l-3.5 3.5a.75.75 0 0 0 1.06 1.06l2.22-2.22v5.69Z"
+									/>
+									<path
+										d="M3.5 9.75a.75.75 0 0 0-1.5 0v1.5A2.75 2.75 0 0 0 4.75 14h6.5A2.75 2.75 0 0 0 14 11.25v-1.5a.75.75 0 0 0-1.5 0v1.5c0 .69-.56 1.25-1.25 1.25h-6.5c-.69 0-1.25-.56-1.25-1.25v-1.5Z"
+									/>
+								</svg>
+							{/if}
+						</button>
+					</div>
+				</div>
+
 				<div class=" my-2">
 					<div class=" mb-2 text-sm font-medium">
 						{$i18n.t('Install from Github URL')}
@@ -384,6 +508,8 @@
 						</div>
 					</div>
 				{/if}
+			{:else}
+				<div>Pipelines Not Detected</div>
 			{/if}
 		{:else}
 			<div class="flex justify-center h-full">

src/lib/components/admin/Settings/Users.svelte

@@ -48,7 +48,7 @@
 		await config.set(await getBackendConfig());
 	}}
 >
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-80">
+	<div class=" space-y-3 overflow-y-scroll max-h-full">
 		<div>
 			<div class=" mb-2 text-sm font-medium">{$i18n.t('User Permissions')}</div>
 
@@ -94,7 +94,7 @@
 			</div>
 		</div>
 
-		<hr class=" dark:border-gray-700 my-2" />
+		<hr class=" dark:border-gray-850 my-2" />
 
 		<div class="mt-2 space-y-3">
 			<div>

src/lib/components/admin/Settings/WebSearch.svelte

@@ -0,0 +1,303 @@
+<script lang="ts">
+	import { getRAGConfig, updateRAGConfig } from '$lib/apis/rag';
+	import Switch from '$lib/components/common/Switch.svelte';
+
+	import { documents, models } from '$lib/stores';
+	import { onMount, getContext } from 'svelte';
+	import { toast } from 'svelte-sonner';
+
+	const i18n = getContext('i18n');
+
+	export let saveHandler: Function;
+
+	let webConfig = null;
+	let webSearchEngines = ['searxng', 'google_pse', 'brave', 'serpstack', 'serper', 'serply'];
+
+	let youtubeLanguage = 'en';
+	let youtubeTranslation = null;
+
+	const submitHandler = async () => {
+		const res = await updateRAGConfig(localStorage.token, {
+			web: webConfig,
+			youtube: {
+				language: youtubeLanguage.split(',').map((lang) => lang.trim()),
+				translation: youtubeTranslation
+			}
+		});
+	};
+
+	onMount(async () => {
+		const res = await getRAGConfig(localStorage.token);
+
+		if (res) {
+			webConfig = res.web;
+
+			youtubeLanguage = res.youtube.language.join(',');
+			youtubeTranslation = res.youtube.translation;
+		}
+	});
+</script>
+
+<form
+	class="flex flex-col h-full justify-between space-y-3 text-sm"
+	on:submit|preventDefault={async () => {
+		await submitHandler();
+		saveHandler();
+	}}
+>
+	<div class=" space-y-3 overflow-y-scroll scrollbar-hidden h-full">
+		{#if webConfig}
+			<div>
+				<div class=" mb-1 text-sm font-medium">
+					{$i18n.t('Web Search')}
+				</div>
+
+				<div>
+					<div class=" py-0.5 flex w-full justify-between">
+						<div class=" self-center text-xs font-medium">
+							{$i18n.t('Enable Web Search')}
+						</div>
+
+						<Switch bind:state={webConfig.search.enabled} />
+					</div>
+				</div>
+
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs font-medium">{$i18n.t('Web Search Engine')}</div>
+					<div class="flex items-center relative">
+						<select
+							class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
+							bind:value={webConfig.search.engine}
+							placeholder={$i18n.t('Select a engine')}
+							required
+						>
+							<option disabled selected value="">{$i18n.t('Select a engine')}</option>
+							{#each webSearchEngines as engine}
+								<option value={engine}>{engine}</option>
+							{/each}
+						</select>
+					</div>
+				</div>
+
+				{#if webConfig.search.engine !== ''}
+					<div class="mt-1.5">
+						{#if webConfig.search.engine === 'searxng'}
+							<div>
+								<div class=" self-center text-xs font-medium mb-1">
+									{$i18n.t('Searxng Query URL')}
+								</div>
+
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+											type="text"
+											placeholder={$i18n.t('Enter Searxng Query URL')}
+											bind:value={webConfig.search.searxng_query_url}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+							</div>
+						{:else if webConfig.search.engine === 'google_pse'}
+							<div>
+								<div class=" self-center text-xs font-medium mb-1">
+									{$i18n.t('Google PSE API Key')}
+								</div>
+
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+											type="text"
+											placeholder={$i18n.t('Enter Google PSE API Key')}
+											bind:value={webConfig.search.google_pse_api_key}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+							</div>
+							<div class="mt-1.5">
+								<div class=" self-center text-xs font-medium mb-1">
+									{$i18n.t('Google PSE Engine Id')}
+								</div>
+
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+											type="text"
+											placeholder={$i18n.t('Enter Google PSE Engine Id')}
+											bind:value={webConfig.search.google_pse_engine_id}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+							</div>
+						{:else if webConfig.search.engine === 'brave'}
+							<div>
+								<div class=" self-center text-xs font-medium mb-1">
+									{$i18n.t('Brave Search API Key')}
+								</div>
+
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+											type="text"
+											placeholder={$i18n.t('Enter Brave Search API Key')}
+											bind:value={webConfig.search.brave_search_api_key}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+							</div>
+						{:else if webConfig.search.engine === 'serpstack'}
+							<div>
+								<div class=" self-center text-xs font-medium mb-1">
+									{$i18n.t('Serpstack API Key')}
+								</div>
+
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+											type="text"
+											placeholder={$i18n.t('Enter Serpstack API Key')}
+											bind:value={webConfig.search.serpstack_api_key}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+							</div>
+						{:else if webConfig.search.engine === 'serper'}
+							<div>
+								<div class=" self-center text-xs font-medium mb-1">
+									{$i18n.t('Serper API Key')}
+								</div>
+
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+											type="text"
+											placeholder={$i18n.t('Enter Serper API Key')}
+											bind:value={webConfig.search.serper_api_key}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+							</div>
+						{:else if webConfig.search.engine === 'serply'}
+							<div>
+								<div class=" self-center text-xs font-medium mb-1">
+									{$i18n.t('Serply API Key')}
+								</div>
+
+								<div class="flex w-full">
+									<div class="flex-1">
+										<input
+											class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+											type="text"
+											placeholder={$i18n.t('Enter Serply API Key')}
+											bind:value={webConfig.search.serply_api_key}
+											autocomplete="off"
+										/>
+									</div>
+								</div>
+							</div>
+						{/if}
+					</div>
+				{/if}
+
+				{#if webConfig.search.enabled}
+					<div class="mt-2 flex gap-2 mb-1">
+						<div class="w-full">
+							<div class=" self-center text-xs font-medium mb-1">
+								{$i18n.t('Search Result Count')}
+							</div>
+
+							<input
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								placeholder={$i18n.t('Search Result Count')}
+								bind:value={webConfig.search.result_count}
+								required
+							/>
+						</div>
+
+						<div class="w-full">
+							<div class=" self-center text-xs font-medium mb-1">
+								{$i18n.t('Concurrent Requests')}
+							</div>
+
+							<input
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								placeholder={$i18n.t('Concurrent Requests')}
+								bind:value={webConfig.search.concurrent_requests}
+								required
+							/>
+						</div>
+					</div>
+				{/if}
+			</div>
+
+			<hr class=" dark:border-gray-850 my-2" />
+
+			<div>
+				<div class=" mb-1 text-sm font-medium">
+					{$i18n.t('Web Loader Settings')}
+				</div>
+
+				<div>
+					<div class=" py-0.5 flex w-full justify-between">
+						<div class=" self-center text-xs font-medium">
+							{$i18n.t('Bypass SSL verification for Websites')}
+						</div>
+
+						<button
+							class="p-1 px-3 text-xs flex rounded transition"
+							on:click={() => {
+								webConfig.ssl_verification = !webConfig.ssl_verification;
+								submitHandler();
+							}}
+							type="button"
+						>
+							{#if webConfig.ssl_verification === true}
+								<span class="ml-2 self-center">{$i18n.t('On')}</span>
+							{:else}
+								<span class="ml-2 self-center">{$i18n.t('Off')}</span>
+							{/if}
+						</button>
+					</div>
+				</div>
+
+				<div class=" mt-2 mb-1 text-sm font-medium">
+					{$i18n.t('Youtube Loader Settings')}
+				</div>
+
+				<div>
+					<div class=" py-0.5 flex w-full justify-between">
+						<div class=" w-20 text-xs font-medium self-center">{$i18n.t('Language')}</div>
+						<div class=" flex-1 self-center">
+							<input
+								class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+								type="text"
+								placeholder={$i18n.t('Enter language codes')}
+								bind:value={youtubeLanguage}
+								autocomplete="off"
+							/>
+						</div>
+					</div>
+				</div>
+			</div>
+		{/if}
+	</div>
+	<div class="flex justify-end pt-3 text-sm font-medium">
+		<button
+			class=" px-4 py-2 bg-emerald-700 hover:bg-emerald-800 text-gray-100 transition rounded-lg"
+			type="submit"
+		>
+			{$i18n.t('Save')}
+		</button>
+	</div>
+</form>

src/lib/components/admin/SettingsModal.svelte

@@ -39,181 +39,5 @@
 				</svg>
 			</button>
 		</div>
-
-		<div class="flex flex-col md:flex-row w-full p-4 md:space-x-4">
-			<div
-				class="tabs flex flex-row overflow-x-auto space-x-1 md:space-x-0 md:space-y-1 md:flex-col flex-1 md:flex-none md:w-40 dark:text-gray-200 text-xs text-left mb-3 md:mb-0"
-			>
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'general'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'general';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 16 16"
-							fill="currentColor"
-							class="w-4 h-4"
-						>
-							<path
-								fill-rule="evenodd"
-								d="M6.955 1.45A.5.5 0 0 1 7.452 1h1.096a.5.5 0 0 1 .497.45l.17 1.699c.484.12.94.312 1.356.562l1.321-1.081a.5.5 0 0 1 .67.033l.774.775a.5.5 0 0 1 .034.67l-1.08 1.32c.25.417.44.873.561 1.357l1.699.17a.5.5 0 0 1 .45.497v1.096a.5.5 0 0 1-.45.497l-1.699.17c-.12.484-.312.94-.562 1.356l1.082 1.322a.5.5 0 0 1-.034.67l-.774.774a.5.5 0 0 1-.67.033l-1.322-1.08c-.416.25-.872.44-1.356.561l-.17 1.699a.5.5 0 0 1-.497.45H7.452a.5.5 0 0 1-.497-.45l-.17-1.699a4.973 4.973 0 0 1-1.356-.562L4.108 13.37a.5.5 0 0 1-.67-.033l-.774-.775a.5.5 0 0 1-.034-.67l1.08-1.32a4.971 4.971 0 0 1-.561-1.357l-1.699-.17A.5.5 0 0 1 1 8.548V7.452a.5.5 0 0 1 .45-.497l1.699-.17c.12-.484.312-.94.562-1.356L2.629 4.107a.5.5 0 0 1 .034-.67l.774-.774a.5.5 0 0 1 .67-.033L5.43 3.71a4.97 4.97 0 0 1 1.356-.561l.17-1.699ZM6 8c0 .538.212 1.026.558 1.385l.057.057a2 2 0 0 0 2.828-2.828l-.058-.056A2 2 0 0 0 6 8Z"
-								clip-rule="evenodd"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('General')}</div>
-				</button>
-
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'users'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'users';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 16 16"
-							fill="currentColor"
-							class="w-4 h-4"
-						>
-							<path
-								d="M8 8a2.5 2.5 0 1 0 0-5 2.5 2.5 0 0 0 0 5ZM3.156 11.763c.16-.629.44-1.21.813-1.72a2.5 2.5 0 0 0-2.725 1.377c-.136.287.102.58.418.58h1.449c.01-.077.025-.156.045-.237ZM12.847 11.763c.02.08.036.16.046.237h1.446c.316 0 .554-.293.417-.579a2.5 2.5 0 0 0-2.722-1.378c.374.51.653 1.09.813 1.72ZM14 7.5a1.5 1.5 0 1 1-3 0 1.5 1.5 0 0 1 3 0ZM3.5 9a1.5 1.5 0 1 0 0-3 1.5 1.5 0 0 0 0 3ZM5 13c-.552 0-1.013-.455-.876-.99a4.002 4.002 0 0 1 7.753 0c.136.535-.324.99-.877.99H5Z"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('Users')}</div>
-				</button>
-
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'db'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'db';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 16 16"
-							fill="currentColor"
-							class="w-4 h-4"
-						>
-							<path d="M8 7c3.314 0 6-1.343 6-3s-2.686-3-6-3-6 1.343-6 3 2.686 3 6 3Z" />
-							<path
-								d="M8 8.5c1.84 0 3.579-.37 4.914-1.037A6.33 6.33 0 0 0 14 6.78V8c0 1.657-2.686 3-6 3S2 9.657 2 8V6.78c.346.273.72.5 1.087.683C4.42 8.131 6.16 8.5 8 8.5Z"
-							/>
-							<path
-								d="M8 12.5c1.84 0 3.579-.37 4.914-1.037.366-.183.74-.41 1.086-.684V12c0 1.657-2.686 3-6 3s-6-1.343-6-3v-1.22c.346.273.72.5 1.087.683C4.42 12.131 6.16 12.5 8 12.5Z"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('Database')}</div>
-				</button>
-
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'banners'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'banners';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 24 24"
-							fill="currentColor"
-							class="size-4"
-						>
-							<path
-								d="M5.85 3.5a.75.75 0 0 0-1.117-1 9.719 9.719 0 0 0-2.348 4.876.75.75 0 0 0 1.479.248A8.219 8.219 0 0 1 5.85 3.5ZM19.267 2.5a.75.75 0 1 0-1.118 1 8.22 8.22 0 0 1 1.987 4.124.75.75 0 0 0 1.48-.248A9.72 9.72 0 0 0 19.266 2.5Z"
-							/>
-							<path
-								fill-rule="evenodd"
-								d="M12 2.25A6.75 6.75 0 0 0 5.25 9v.75a8.217 8.217 0 0 1-2.119 5.52.75.75 0 0 0 .298 1.206c1.544.57 3.16.99 4.831 1.243a3.75 3.75 0 1 0 7.48 0 24.583 24.583 0 0 0 4.83-1.244.75.75 0 0 0 .298-1.205 8.217 8.217 0 0 1-2.118-5.52V9A6.75 6.75 0 0 0 12 2.25ZM9.75 18c0-.034 0-.067.002-.1a25.05 25.05 0 0 0 4.496 0l.002.1a2.25 2.25 0 1 1-4.5 0Z"
-								clip-rule="evenodd"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('Banners')}</div>
-				</button>
-
-				<button
-					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-					'pipelines'
-						? 'bg-gray-200 dark:bg-gray-700'
-						: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-					on:click={() => {
-						selectedTab = 'pipelines';
-					}}
-				>
-					<div class=" self-center mr-2">
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 24 24"
-							fill="currentColor"
-							class="size-4"
-						>
-							<path
-								d="M11.644 1.59a.75.75 0 0 1 .712 0l9.75 5.25a.75.75 0 0 1 0 1.32l-9.75 5.25a.75.75 0 0 1-.712 0l-9.75-5.25a.75.75 0 0 1 0-1.32l9.75-5.25Z"
-							/>
-							<path
-								d="m3.265 10.602 7.668 4.129a2.25 2.25 0 0 0 2.134 0l7.668-4.13 1.37.739a.75.75 0 0 1 0 1.32l-9.75 5.25a.75.75 0 0 1-.71 0l-9.75-5.25a.75.75 0 0 1 0-1.32l1.37-.738Z"
-							/>
-							<path
-								d="m10.933 19.231-7.668-4.13-1.37.739a.75.75 0 0 0 0 1.32l9.75 5.25c.221.12.489.12.71 0l9.75-5.25a.75.75 0 0 0 0-1.32l-1.37-.738-7.668 4.13a2.25 2.25 0 0 1-2.134-.001Z"
-							/>
-						</svg>
-					</div>
-					<div class=" self-center">{$i18n.t('Pipelines')}</div>
-				</button>
-			</div>
-			<div class="flex-1 md:min-h-[380px]">
-				{#if selectedTab === 'general'}
-					<General
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{:else if selectedTab === 'users'}
-					<Users
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{:else if selectedTab === 'db'}
-					<Database
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{:else if selectedTab === 'banners'}
-					<Banners
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{:else if selectedTab === 'pipelines'}
-					<Pipelines
-						saveHandler={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
-				{/if}
-			</div>
-		</div>
 	</div>
 </Modal>

src/lib/components/chat/Chat.svelte

@@ -7,6 +7,10 @@
 	import { goto } from '$app/navigation';
 	import { page } from '$app/stores';
 
+	import type { Writable } from 'svelte/store';
+	import type { i18n as i18nType } from 'i18next';
+	import { OLLAMA_API_BASE_URL, OPENAI_API_BASE_URL, WEBUI_BASE_URL } from '$lib/constants';
+
 	import {
 		chatId,
 		chats,
@@ -18,7 +22,9 @@
 		tags as _tags,
 		WEBUI_NAME,
 		banners,
-		user
+		user,
+		socket,
+		showCallOverlay
 	} from '$lib/stores';
 	import {
 		convertMessagesToHistory,
@@ -38,24 +44,19 @@
 		getTagsById,
 		updateChatById
 	} from '$lib/apis/chats';
-	import {
-		generateOpenAIChatCompletion,
-		generateSearchQuery,
-		generateTitle
-	} from '$lib/apis/openai';
+	import { generateOpenAIChatCompletion } from '$lib/apis/openai';
+	import { runWebSearch } from '$lib/apis/rag';
+	import { createOpenAITextStream } from '$lib/apis/streaming';
+	import { queryMemory } from '$lib/apis/memories';
+	import { getUserSettings } from '$lib/apis/users';
+	import { chatCompleted, generateTitle, generateSearchQuery } from '$lib/apis';
 
+	import Banner from '../common/Banner.svelte';
 	import MessageInput from '$lib/components/chat/MessageInput.svelte';
 	import Messages from '$lib/components/chat/Messages.svelte';
 	import Navbar from '$lib/components/layout/Navbar.svelte';
-	import { OLLAMA_API_BASE_URL, OPENAI_API_BASE_URL, WEBUI_BASE_URL } from '$lib/constants';
-	import { createOpenAITextStream } from '$lib/apis/streaming';
-	import { queryMemory } from '$lib/apis/memories';
-	import type { Writable } from 'svelte/store';
-	import type { i18n as i18nType } from 'i18next';
-	import { runWebSearch } from '$lib/apis/rag';
-	import Banner from '../common/Banner.svelte';
-	import { getUserSettings } from '$lib/apis/users';
-	import { chatCompleted } from '$lib/apis';
+	import CallOverlay from './MessageInput/CallOverlay.svelte';
+	import { error } from '@sveltejs/kit';
 
 	const i18n: Writable<i18nType> = getContext('i18n');
 
@@ -280,11 +281,22 @@
 		}
 	};
 
+	const getChatEventEmitter = async (modelId: string, chatId: string = '') => {
+		return setInterval(() => {
+			$socket?.emit('usage', {
+				action: 'chat',
+				model: modelId,
+				chat_id: chatId
+			});
+		}, 1000);
+	};
+
 	//////////////////////////
-	// Ollama functions
+	// Chat functions
 	//////////////////////////
 
 	const submitPrompt = async (userPrompt, _user = null) => {
+		let _responses = [];
 		console.log('submitPrompt', $chatId);
 
 		selectedModels = selectedModels.map((modelId) =>
@@ -307,8 +319,18 @@
 				)
 			);
 		} else {
-			// Reset chat message textarea height
-			document.getElementById('chat-textarea').style.height = '';
+			// Reset chat input textarea
+			const chatTextAreaElement = document.getElementById('chat-textarea');
+
+			if (chatTextAreaElement) {
+				chatTextAreaElement.value = '';
+				chatTextAreaElement.style.height = '';
+			}
+
+			const _files = JSON.parse(JSON.stringify(files));
+			files = [];
+
+			prompt = '';
 
 			// Create user message
 			let userMessageId = uuidv4();
@@ -319,7 +341,7 @@
 				role: 'user',
 				user: _user ?? undefined,
 				content: userPrompt,
-				files: files.length > 0 ? files : undefined,
+				files: _files.length > 0 ? _files : undefined,
 				timestamp: Math.floor(Date.now() / 1000), // Unix epoch
 				models: selectedModels.filter((m, mIdx) => selectedModels.indexOf(m) === mIdx)
 			};
@@ -336,50 +358,87 @@
 			// Wait until history/message have been updated
 			await tick();
 
-			// Create new chat if only one message in messages
-			if (messages.length == 1) {
-				if ($settings.saveChatHistory ?? true) {
-					chat = await createNewChat(localStorage.token, {
-						id: $chatId,
-						title: $i18n.t('New Chat'),
-						models: selectedModels,
-						system: $settings.system ?? undefined,
-						options: {
-							...($settings.params ?? {})
-						},
-						messages: messages,
-						history: history,
-						tags: [],
-						timestamp: Date.now()
-					});
-					await chats.set(await getChatList(localStorage.token));
-					await chatId.set(chat.id);
-				} else {
-					await chatId.set('local');
-				}
-				await tick();
-			}
-
-			// Reset chat input textarea
-			prompt = '';
-			document.getElementById('chat-textarea').style.height = '';
-			files = [];
-
 			// Send prompt
-			await sendPrompt(userPrompt, userMessageId);
+			_responses = await sendPrompt(userPrompt, userMessageId);
 		}
+
+		return _responses;
 	};
 
 	const sendPrompt = async (prompt, parentId, modelId = null) => {
+		let _responses = [];
+
+		// If modelId is provided, use it, else use selected model
+		let selectedModelIds = modelId
+			? [modelId]
+			: atSelectedModel !== undefined
+			? [atSelectedModel.id]
+			: selectedModels;
+
+		// Create response messages for each selected model
+		const responseMessageIds = {};
+		for (const modelId of selectedModelIds) {
+			const model = $models.filter((m) => m.id === modelId).at(0);
+
+			if (model) {
+				let responseMessageId = uuidv4();
+				let responseMessage = {
+					parentId: parentId,
+					id: responseMessageId,
+					childrenIds: [],
+					role: 'assistant',
+					content: '',
+					model: model.id,
+					modelName: model.name ?? model.id,
+					userContext: null,
+					timestamp: Math.floor(Date.now() / 1000) // Unix epoch
+				};
+
+				// Add message to history and Set currentId to messageId
+				history.messages[responseMessageId] = responseMessage;
+				history.currentId = responseMessageId;
+
+				// Append messageId to childrenIds of parent message
+				if (parentId !== null) {
+					history.messages[parentId].childrenIds = [
+						...history.messages[parentId].childrenIds,
+						responseMessageId
+					];
+				}
+
+				responseMessageIds[modelId] = responseMessageId;
+			}
+		}
+		await tick();
+
+		// Create new chat if only one message in messages
+		if (messages.length == 2) {
+			if ($settings.saveChatHistory ?? true) {
+				chat = await createNewChat(localStorage.token, {
+					id: $chatId,
+					title: $i18n.t('New Chat'),
+					models: selectedModels,
+					system: $settings.system ?? undefined,
+					options: {
+						...($settings.params ?? {})
+					},
+					messages: messages,
+					history: history,
+					tags: [],
+					timestamp: Date.now()
+				});
+				await chats.set(await getChatList(localStorage.token));
+				await chatId.set(chat.id);
+			} else {
+				await chatId.set('local');
+			}
+			await tick();
+		}
+
 		const _chatId = JSON.parse(JSON.stringify($chatId));
 
 		await Promise.all(
-			(modelId
-				? [modelId]
-				: atSelectedModel !== undefined
-				? [atSelectedModel.id]
-				: selectedModels
-			).map(async (modelId) => {
+			selectedModelIds.map(async (modelId) => {
 				console.log('modelId', modelId);
 				const model = $models.filter((m) => m.id === modelId).at(0);
 
@@ -397,33 +456,8 @@
 						);
 					}
 
-					// Create response message
-					let responseMessageId = uuidv4();
-					let responseMessage = {
-						parentId: parentId,
-						id: responseMessageId,
-						childrenIds: [],
-						role: 'assistant',
-						content: '',
-						model: model.id,
-						modelName: model.name ?? model.id,
-						userContext: null,
-						timestamp: Math.floor(Date.now() / 1000) // Unix epoch
-					};
-
-					// Add message to history and Set currentId to messageId
-					history.messages[responseMessageId] = responseMessage;
-					history.currentId = responseMessageId;
-
-					// Append messageId to childrenIds of parent message
-					if (parentId !== null) {
-						history.messages[parentId].childrenIds = [
-							...history.messages[parentId].childrenIds,
-							responseMessageId
-						];
-					}
-
-					await tick();
+					let responseMessageId = responseMessageIds[modelId];
+					let responseMessage = history.messages[responseMessageId];
 
 					let userContext = null;
 					if ($settings?.memory ?? false) {
@@ -432,7 +466,6 @@
 								toast.error(error);
 								return null;
 							});
-
 							if (res) {
 								if (res.documents[0].length > 0) {
 									userContext = res.documents.reduce((acc, doc, index) => {
@@ -451,15 +484,23 @@
 					}
 					responseMessage.userContext = userContext;
 
+					const chatEventEmitter = await getChatEventEmitter(model.id, _chatId);
+
 					if (webSearchEnabled) {
 						await getWebSearchResults(model.id, parentId, responseMessageId);
 					}
 
+					let _response = null;
 					if (model?.owned_by === 'openai') {
-						await sendPromptOpenAI(model, prompt, responseMessageId, _chatId);
+						_response = await sendPromptOpenAI(model, prompt, responseMessageId, _chatId);
 					} else if (model) {
-						await sendPromptOllama(model, prompt, responseMessageId, _chatId);
+						_response = await sendPromptOllama(model, prompt, responseMessageId, _chatId);
 					}
+					_responses.push(_response);
+
+					console.log('chatEventEmitter', chatEventEmitter);
+
+					if (chatEventEmitter) clearInterval(chatEventEmitter);
 				} else {
 					toast.error($i18n.t(`Model {{modelId}} not found`, { modelId }));
 				}
@@ -467,39 +508,47 @@
 		);
 
 		await chats.set(await getChatList(localStorage.token));
+
+		return _responses;
 	};
 
 	const getWebSearchResults = async (model: string, parentId: string, responseId: string) => {
 		const responseMessage = history.messages[responseId];
 
-		responseMessage.status = {
-			done: false,
-			action: 'web_search',
-			description: $i18n.t('Generating search query')
-		};
+		responseMessage.statusHistory = [
+			{
+				done: false,
+				action: 'web_search',
+				description: $i18n.t('Generating search query')
+			}
+		];
 		messages = messages;
 
 		const prompt = history.messages[parentId].content;
-		let searchQuery = prompt;
-		if (prompt.length > 100) {
-			searchQuery = await generateChatSearchQuery(model, prompt);
-			if (!searchQuery) {
-				toast.warning($i18n.t('No search query generated'));
-				responseMessage.status = {
-					...responseMessage.status,
-					done: true,
-					error: true,
-					description: 'No search query generated'
-				};
-				messages = messages;
-				return;
+		let searchQuery = await generateSearchQuery(localStorage.token, model, messages, prompt).catch(
+			(error) => {
+				console.log(error);
+				return prompt;
 			}
+		);
+
+		if (!searchQuery) {
+			toast.warning($i18n.t('No search query generated'));
+			responseMessage.statusHistory.push({
+				done: true,
+				error: true,
+				action: 'web_search',
+				description: 'No search query generated'
+			});
+
+			messages = messages;
 		}
 
-		responseMessage.status = {
-			...responseMessage.status,
-			description: $i18n.t("Searching the web for '{{searchQuery}}'", { searchQuery })
-		};
+		responseMessage.statusHistory.push({
+			done: false,
+			action: 'web_search',
+			description: $i18n.t(`Searching "{{searchQuery}}"`, { searchQuery })
+		});
 		messages = messages;
 
 		const results = await runWebSearch(localStorage.token, searchQuery).catch((error) => {
@@ -510,12 +559,13 @@
 		});
 
 		if (results) {
-			responseMessage.status = {
-				...responseMessage.status,
+			responseMessage.statusHistory.push({
 				done: true,
+				action: 'web_search',
 				description: $i18n.t('Searched {{count}} sites', { count: results.filenames.length }),
+				query: searchQuery,
 				urls: results.filenames
-			};
+			});
 
 			if (responseMessage?.files ?? undefined === undefined) {
 				responseMessage.files = [];
@@ -530,18 +580,19 @@
 
 			messages = messages;
 		} else {
-			responseMessage.status = {
-				...responseMessage.status,
+			responseMessage.statusHistory.push({
 				done: true,
 				error: true,
+				action: 'web_search',
 				description: 'No search results found'
-			};
+			});
 			messages = messages;
 		}
 	};
 
 	const sendPromptOllama = async (model, userPrompt, responseMessageId, _chatId) => {
-		model = model.id;
+		let _response = null;
+
 		const responseMessage = history.messages[responseMessageId];
 
 		// Wait until history/message have been updated
@@ -599,17 +650,29 @@
 			}
 		});
 
-		const docs = messages
-			.filter((message) => message?.files ?? null)
-			.map((message) =>
-				message.files.filter((item) =>
-					['doc', 'collection', 'web_search_results'].includes(item.type)
+		let docs = [];
+
+		if (model?.info?.meta?.knowledge ?? false) {
+			docs = model.info.meta.knowledge;
+		}
+
+		docs = [
+			...docs,
+			...messages
+				.filter((message) => message?.files ?? null)
+				.map((message) =>
+					message.files.filter((item) =>
+						['doc', 'collection', 'web_search_results'].includes(item.type)
+					)
 				)
-			)
-			.flat(1);
+				.flat(1)
+		].filter(
+			(item, index, array) =>
+				array.findIndex((i) => JSON.stringify(i) === JSON.stringify(item)) === index
+		);
 
 		const [res, controller] = await generateChatCompletion(localStorage.token, {
-			model: model,
+			model: model.id,
 			messages: messagesBody,
 			options: {
 				...($settings.params ?? {}),
@@ -647,9 +710,10 @@
 						controller.abort('User: Stop Response');
 					} else {
 						const messages = createMessagesList(responseMessageId);
-						await chatCompletedHandler(model, messages);
+						await chatCompletedHandler(model.id, messages);
 					}
 
+					_response = responseMessage.content;
 					break;
 				}
 
@@ -707,7 +771,7 @@
 													selectedModelfile.title.charAt(0).toUpperCase() +
 													selectedModelfile.title.slice(1)
 											  }`
-											: `${model}`,
+											: `${model.id}`,
 										{
 											body: responseMessage.content,
 											icon: selectedModelfile?.imageUrl ?? `${WEBUI_BASE_URL}/static/favicon.png`
@@ -719,7 +783,7 @@
 									copyToClipboard(responseMessage.content);
 								}
 
-								if ($settings.responseAutoPlayback) {
+								if ($settings.responseAutoPlayback && !$showCallOverlay) {
 									await tick();
 									document.getElementById(`speak-button-${responseMessage.id}`)?.click();
 								}
@@ -786,21 +850,34 @@
 			const _title = await generateChatTitle(userPrompt);
 			await setChatTitle(_chatId, _title);
 		}
+
+		return _response;
 	};
 
 	const sendPromptOpenAI = async (model, userPrompt, responseMessageId, _chatId) => {
+		let _response = null;
 		const responseMessage = history.messages[responseMessageId];
 
-		const docs = messages
-			.filter((message) => message?.files ?? null)
-			.map((message) =>
-				message.files.filter((item) =>
-					['doc', 'collection', 'web_search_results'].includes(item.type)
-				)
-			)
-			.flat(1);
+		let docs = [];
 
-		console.log(docs);
+		if (model?.info?.meta?.knowledge ?? false) {
+			docs = model.info.meta.knowledge;
+		}
+
+		docs = [
+			...docs,
+			...messages
+				.filter((message) => message?.files ?? null)
+				.map((message) =>
+					message.files.filter((item) =>
+						['doc', 'collection', 'web_search_results'].includes(item.type)
+					)
+				)
+				.flat(1)
+		].filter(
+			(item, index, array) =>
+				array.findIndex((i) => JSON.stringify(i) === JSON.stringify(item)) === index
+		);
 
 		scrollToBottom();
 
@@ -905,6 +982,8 @@
 							await chatCompletedHandler(model.id, messages);
 						}
 
+						_response = responseMessage.content;
+
 						break;
 					}
 
@@ -930,7 +1009,7 @@
 				}
 
 				if ($settings.notificationEnabled && !document.hasFocus()) {
-					const notification = new Notification(`OpenAI ${model}`, {
+					const notification = new Notification(`${model.id}`, {
 						body: responseMessage.content,
 						icon: `${WEBUI_BASE_URL}/static/favicon.png`
 					});
@@ -940,8 +1019,9 @@
 					copyToClipboard(responseMessage.content);
 				}
 
-				if ($settings.responseAutoPlayback) {
+				if ($settings.responseAutoPlayback && !$showCallOverlay) {
 					await tick();
+
 					document.getElementById(`speak-button-${responseMessage.id}`)?.click();
 				}
 
@@ -980,6 +1060,8 @@
 			const _title = await generateChatTitle(userPrompt);
 			await setChatTitle(_chatId, _title);
 		}
+
+		return _response;
 	};
 
 	const handleOpenAIError = async (error, res: Response | null, model, responseMessage) => {
@@ -1075,28 +1157,15 @@
 
 	const generateChatTitle = async (userPrompt) => {
 		if ($settings?.title?.auto ?? true) {
-			const model = $models.find((model) => model.id === selectedModels[0]);
-
-			const titleModelId =
-				model?.owned_by === 'openai' ?? false
-					? $settings?.title?.modelExternal ?? selectedModels[0]
-					: $settings?.title?.model ?? selectedModels[0];
-			const titleModel = $models.find((model) => model.id === titleModelId);
-
-			console.log(titleModel);
 			const title = await generateTitle(
 				localStorage.token,
-				$settings?.title?.prompt ??
-					$i18n.t(
-						"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':"
-					) + ' {{prompt}}',
-				titleModelId,
+				selectedModels[0],
 				userPrompt,
-				$chatId,
-				titleModel?.owned_by === 'openai' ?? false
-					? `${OPENAI_API_BASE_URL}`
-					: `${OLLAMA_API_BASE_URL}/v1`
-			);
+				$chatId
+			).catch((error) => {
+				console.error(error);
+				return 'New Chat';
+			});
 
 			return title;
 		} else {
@@ -1104,29 +1173,6 @@
 		}
 	};
 
-	const generateChatSearchQuery = async (modelId: string, prompt: string) => {
-		const model = $models.find((model) => model.id === modelId);
-		const taskModelId =
-			model?.owned_by === 'openai' ?? false
-				? $settings?.title?.modelExternal ?? modelId
-				: $settings?.title?.model ?? modelId;
-		const taskModel = $models.find((model) => model.id === taskModelId);
-
-		const previousMessages = messages
-			.filter((message) => message.role === 'user')
-			.map((message) => message.content);
-
-		return await generateSearchQuery(
-			localStorage.token,
-			taskModelId,
-			previousMessages,
-			prompt,
-			taskModel?.owned_by === 'openai' ?? false
-				? `${OPENAI_API_BASE_URL}`
-				: `${OLLAMA_API_BASE_URL}/v1`
-		);
-	};
-
 	const setChatTitle = async (_chatId, _title) => {
 		if (_chatId === $chatId) {
 			title = _title;
@@ -1143,28 +1189,6 @@
 			return [];
 		});
 	};
-
-	const addTag = async (tagName) => {
-		const res = await addTagById(localStorage.token, $chatId, tagName);
-		tags = await getTags();
-
-		chat = await updateChatById(localStorage.token, $chatId, {
-			tags: tags
-		});
-
-		_tags.set(await getAllChatTags(localStorage.token));
-	};
-
-	const deleteTag = async (tagName) => {
-		const res = await deleteTagById(localStorage.token, $chatId, tagName);
-		tags = await getTags();
-
-		chat = await updateChatById(localStorage.token, $chatId, {
-			tags: tags
-		});
-
-		_tags.set(await getAllChatTags(localStorage.token));
-	};
 </script>
 
 <svelte:head>
@@ -1175,9 +1199,11 @@
 	</title>
 </svelte:head>
 
+<CallOverlay {submitPrompt} bind:files />
+
 {#if !chatIdProp || (loaded && chatIdProp)}
 	<div
-		class="min-h-screen max-h-screen {$showSidebar
+		class="h-screen max-h-[100dvh] {$showSidebar
 			? 'md:max-w-[calc(100%-260px)]'
 			: ''} w-full max-w-full flex flex-col"
 	>

src/lib/components/chat/MessageInput/CallOverlay.svelte

@@ -0,0 +1,693 @@
+<script lang="ts">
+	import { config, settings, showCallOverlay } from '$lib/stores';
+	import { onMount, tick, getContext } from 'svelte';
+
+	import { blobToFile, calculateSHA256, extractSentences, findWordIndices } from '$lib/utils';
+	import { synthesizeOpenAISpeech, transcribeAudio } from '$lib/apis/audio';
+	import { toast } from 'svelte-sonner';
+
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
+	import VideoInputMenu from './CallOverlay/VideoInputMenu.svelte';
+	import { get } from 'svelte/store';
+
+	const i18n = getContext('i18n');
+
+	export let submitPrompt: Function;
+	export let files;
+
+	let loading = false;
+	let confirmed = false;
+
+	let camera = false;
+	let cameraStream = null;
+
+	let assistantSpeaking = false;
+	let assistantAudio = {};
+	let assistantAudioIdx = null;
+
+	let rmsLevel = 0;
+	let hasStartedSpeaking = false;
+
+	let currentUtterance = null;
+
+	let mediaRecorder;
+	let audioChunks = [];
+
+	const MIN_DECIBELS = -45;
+	const VISUALIZER_BUFFER_LENGTH = 300;
+
+	// Function to calculate the RMS level from time domain data
+	const calculateRMS = (data: Uint8Array) => {
+		let sumSquares = 0;
+		for (let i = 0; i < data.length; i++) {
+			const normalizedValue = (data[i] - 128) / 128; // Normalize the data
+			sumSquares += normalizedValue * normalizedValue;
+		}
+		return Math.sqrt(sumSquares / data.length);
+	};
+
+	const normalizeRMS = (rms) => {
+		rms = rms * 10;
+		const exp = 1.5; // Adjust exponent value; values greater than 1 expand larger numbers more and compress smaller numbers more
+		const scaledRMS = Math.pow(rms, exp);
+
+		// Scale between 0.01 (1%) and 1.0 (100%)
+		return Math.min(1.0, Math.max(0.01, scaledRMS));
+	};
+
+	const analyseAudio = (stream) => {
+		const audioContext = new AudioContext();
+		const audioStreamSource = audioContext.createMediaStreamSource(stream);
+
+		const analyser = audioContext.createAnalyser();
+		analyser.minDecibels = MIN_DECIBELS;
+		audioStreamSource.connect(analyser);
+
+		const bufferLength = analyser.frequencyBinCount;
+
+		const domainData = new Uint8Array(bufferLength);
+		const timeDomainData = new Uint8Array(analyser.fftSize);
+
+		let lastSoundTime = Date.now();
+		hasStartedSpeaking = false;
+
+		const detectSound = () => {
+			const processFrame = () => {
+				if (!mediaRecorder || !$showCallOverlay) {
+					if (mediaRecorder) {
+						mediaRecorder.stop();
+					}
+
+					return;
+				}
+				analyser.getByteTimeDomainData(timeDomainData);
+				analyser.getByteFrequencyData(domainData);
+
+				// Calculate RMS level from time domain data
+				rmsLevel = calculateRMS(timeDomainData);
+
+				// Check if initial speech/noise has started
+				const hasSound = domainData.some((value) => value > 0);
+				if (hasSound) {
+					stopAllAudio();
+					hasStartedSpeaking = true;
+					lastSoundTime = Date.now();
+				}
+
+				// Start silence detection only after initial speech/noise has been detected
+				if (hasStartedSpeaking) {
+					if (Date.now() - lastSoundTime > 2000) {
+						confirmed = true;
+
+						if (mediaRecorder) {
+							mediaRecorder.stop();
+						}
+					}
+				}
+
+				window.requestAnimationFrame(processFrame);
+			};
+
+			window.requestAnimationFrame(processFrame);
+		};
+
+		detectSound();
+	};
+
+	const stopAllAudio = () => {
+		if (currentUtterance) {
+			speechSynthesis.cancel();
+			currentUtterance = null;
+		}
+		if (assistantAudio[assistantAudioIdx]) {
+			assistantAudio[assistantAudioIdx].pause();
+			assistantAudio[assistantAudioIdx].currentTime = 0;
+		}
+
+		const audioElement = document.getElementById('audioElement');
+		audioElement.pause();
+		audioElement.currentTime = 0;
+
+		assistantSpeaking = false;
+	};
+
+	const playAudio = (idx) => {
+		if ($showCallOverlay) {
+			return new Promise((res) => {
+				assistantAudioIdx = idx;
+				const audioElement = document.getElementById('audioElement');
+				const audio = assistantAudio[idx];
+
+				audioElement.src = audio.src; // Assume `assistantAudio` has objects with a `src` property
+
+				audioElement.muted = true;
+
+				audioElement
+					.play()
+					.then(() => {
+						audioElement.muted = false;
+					})
+					.catch((error) => {
+						toast.error(error);
+					});
+
+				audioElement.onended = async (e) => {
+					await new Promise((r) => setTimeout(r, 300));
+
+					if (Object.keys(assistantAudio).length - 1 === idx) {
+						assistantSpeaking = false;
+					}
+
+					res(e);
+				};
+			});
+		} else {
+			return Promise.resolve();
+		}
+	};
+
+	const getOpenAISpeech = async (text) => {
+		const res = await synthesizeOpenAISpeech(
+			localStorage.token,
+			$settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice,
+			text
+		).catch((error) => {
+			toast.error(error);
+			assistantSpeaking = false;
+			return null;
+		});
+
+		if (res) {
+			const blob = await res.blob();
+			const blobUrl = URL.createObjectURL(blob);
+			const audio = new Audio(blobUrl);
+			assistantAudio = audio;
+		}
+	};
+
+	const transcribeHandler = async (audioBlob) => {
+		// Create a blob from the audio chunks
+
+		await tick();
+		const file = blobToFile(audioBlob, 'recording.wav');
+
+		const res = await transcribeAudio(localStorage.token, file).catch((error) => {
+			toast.error(error);
+			return null;
+		});
+
+		if (res) {
+			console.log(res.text);
+
+			if (res.text !== '') {
+				const _responses = await submitPrompt(res.text);
+				console.log(_responses);
+
+				if (_responses.at(0)) {
+					const content = _responses[0];
+					if ((content ?? '').trim() !== '') {
+						assistantSpeakingHandler(content);
+					}
+				}
+			}
+		}
+	};
+
+	const assistantSpeakingHandler = async (content) => {
+		assistantSpeaking = true;
+
+		if (($config.audio.tts.engine ?? '') == '') {
+			let voices = [];
+			const getVoicesLoop = setInterval(async () => {
+				voices = await speechSynthesis.getVoices();
+				if (voices.length > 0) {
+					clearInterval(getVoicesLoop);
+
+					const voice =
+						voices
+							?.filter(
+								(v) => v.voiceURI === ($settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice)
+							)
+							?.at(0) ?? undefined;
+
+					currentUtterance = new SpeechSynthesisUtterance(content);
+
+					if (voice) {
+						currentUtterance.voice = voice;
+					}
+
+					speechSynthesis.speak(currentUtterance);
+				}
+			}, 100);
+		} else if ($config.audio.tts.engine === 'openai') {
+			console.log('openai');
+
+			const sentences = extractSentences(content).reduce((mergedTexts, currentText) => {
+				const lastIndex = mergedTexts.length - 1;
+				if (lastIndex >= 0) {
+					const previousText = mergedTexts[lastIndex];
+					const wordCount = previousText.split(/\s+/).length;
+					if (wordCount < 2) {
+						mergedTexts[lastIndex] = previousText + ' ' + currentText;
+					} else {
+						mergedTexts.push(currentText);
+					}
+				} else {
+					mergedTexts.push(currentText);
+				}
+				return mergedTexts;
+			}, []);
+
+			console.log(sentences);
+
+			let lastPlayedAudioPromise = Promise.resolve(); // Initialize a promise that resolves immediately
+
+			for (const [idx, sentence] of sentences.entries()) {
+				const res = await synthesizeOpenAISpeech(
+					localStorage.token,
+					$settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice,
+					sentence
+				).catch((error) => {
+					toast.error(error);
+
+					assistantSpeaking = false;
+					return null;
+				});
+
+				if (res) {
+					const blob = await res.blob();
+					const blobUrl = URL.createObjectURL(blob);
+					const audio = new Audio(blobUrl);
+					assistantAudio[idx] = audio;
+					lastPlayedAudioPromise = lastPlayedAudioPromise.then(() => playAudio(idx));
+				}
+			}
+		}
+	};
+
+	const stopRecordingCallback = async () => {
+		if ($showCallOverlay) {
+			if (confirmed) {
+				loading = true;
+
+				if (cameraStream) {
+					const imageUrl = takeScreenshot();
+
+					files = [
+						{
+							type: 'image',
+							url: imageUrl
+						}
+					];
+				}
+
+				const audioBlob = new Blob(audioChunks, { type: 'audio/wav' });
+				await transcribeHandler(audioBlob);
+
+				confirmed = false;
+				loading = false;
+			}
+			audioChunks = [];
+			mediaRecorder = false;
+
+			startRecording();
+		} else {
+			audioChunks = [];
+			mediaRecorder = false;
+		}
+	};
+
+	const startRecording = async () => {
+		const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+		mediaRecorder = new MediaRecorder(stream);
+		mediaRecorder.onstart = () => {
+			console.log('Recording started');
+			audioChunks = [];
+			analyseAudio(stream);
+		};
+		mediaRecorder.ondataavailable = (event) => {
+			if (hasStartedSpeaking) {
+				audioChunks.push(event.data);
+			}
+		};
+		mediaRecorder.onstop = async () => {
+			console.log('Recording stopped');
+
+			await stopRecordingCallback();
+		};
+		mediaRecorder.start();
+	};
+
+	let videoInputDevices = [];
+	let selectedVideoInputDeviceId = null;
+
+	const getVideoInputDevices = async () => {
+		const devices = await navigator.mediaDevices.enumerateDevices();
+		videoInputDevices = devices.filter((device) => device.kind === 'videoinput');
+
+		if (!!navigator.mediaDevices.getDisplayMedia) {
+			videoInputDevices = [
+				...videoInputDevices,
+				{
+					deviceId: 'screen',
+					label: 'Screen Share'
+				}
+			];
+		}
+
+		console.log(videoInputDevices);
+		if (selectedVideoInputDeviceId === null && videoInputDevices.length > 0) {
+			selectedVideoInputDeviceId = videoInputDevices[0].deviceId;
+		}
+	};
+
+	const startCamera = async () => {
+		await getVideoInputDevices();
+
+		if (cameraStream === null) {
+			camera = true;
+			await tick();
+			try {
+				await startVideoStream();
+			} catch (err) {
+				console.error('Error accessing webcam: ', err);
+			}
+		}
+	};
+
+	const startVideoStream = async () => {
+		const video = document.getElementById('camera-feed');
+		if (video) {
+			if (selectedVideoInputDeviceId === 'screen') {
+				cameraStream = await navigator.mediaDevices.getDisplayMedia({
+					video: {
+						cursor: 'always'
+					},
+					audio: false
+				});
+			} else {
+				cameraStream = await navigator.mediaDevices.getUserMedia({
+					video: {
+						deviceId: selectedVideoInputDeviceId ? { exact: selectedVideoInputDeviceId } : undefined
+					}
+				});
+			}
+
+			if (cameraStream) {
+				await getVideoInputDevices();
+				video.srcObject = cameraStream;
+				await video.play();
+			}
+		}
+	};
+
+	const stopVideoStream = async () => {
+		if (cameraStream) {
+			const tracks = cameraStream.getTracks();
+			tracks.forEach((track) => track.stop());
+		}
+
+		cameraStream = null;
+	};
+
+	const takeScreenshot = () => {
+		const video = document.getElementById('camera-feed');
+		const canvas = document.getElementById('camera-canvas');
+
+		if (!canvas) {
+			return;
+		}
+
+		const context = canvas.getContext('2d');
+
+		// Make the canvas match the video dimensions
+		canvas.width = video.videoWidth;
+		canvas.height = video.videoHeight;
+
+		// Draw the image from the video onto the canvas
+		context.drawImage(video, 0, 0, video.videoWidth, video.videoHeight);
+
+		// Convert the canvas to a data base64 URL and console log it
+		const dataURL = canvas.toDataURL('image/png');
+		console.log(dataURL);
+
+		return dataURL;
+	};
+
+	const stopCamera = async () => {
+		await stopVideoStream();
+		camera = false;
+	};
+
+	$: if ($showCallOverlay) {
+		startRecording();
+	} else {
+		stopCamera();
+	}
+</script>
+
+{#if $showCallOverlay}
+	<audio id="audioElement" src="" style="display: none;" />
+	<div class=" absolute w-full h-screen max-h-[100dvh] flex z-[999] overflow-hidden">
+		<div
+			class="absolute w-full h-screen max-h-[100dvh] bg-white text-gray-700 dark:bg-black dark:text-gray-300 flex justify-center"
+		>
+			<div class="max-w-lg w-full h-screen max-h-[100dvh] flex flex-col justify-between p-3 md:p-6">
+				{#if camera}
+					<div class="flex justify-center items-center w-full min-h-20">
+						{#if loading}
+							<svg
+								class="size-12 text-gray-900 dark:text-gray-400"
+								viewBox="0 0 24 24"
+								fill="currentColor"
+								xmlns="http://www.w3.org/2000/svg"
+								><style>
+									.spinner_qM83 {
+										animation: spinner_8HQG 1.05s infinite;
+									}
+									.spinner_oXPr {
+										animation-delay: 0.1s;
+									}
+									.spinner_ZTLf {
+										animation-delay: 0.2s;
+									}
+									@keyframes spinner_8HQG {
+										0%,
+										57.14% {
+											animation-timing-function: cubic-bezier(0.33, 0.66, 0.66, 1);
+											transform: translate(0);
+										}
+										28.57% {
+											animation-timing-function: cubic-bezier(0.33, 0, 0.66, 0.33);
+											transform: translateY(-6px);
+										}
+										100% {
+											transform: translate(0);
+										}
+									}
+								</style><circle class="spinner_qM83" cx="4" cy="12" r="3" /><circle
+									class="spinner_qM83 spinner_oXPr"
+									cx="12"
+									cy="12"
+									r="3"
+								/><circle class="spinner_qM83 spinner_ZTLf" cx="20" cy="12" r="3" /></svg
+							>
+						{:else}
+							<div
+								class=" {rmsLevel * 100 > 4
+									? ' size-[4.5rem]'
+									: rmsLevel * 100 > 2
+									? ' size-16'
+									: rmsLevel * 100 > 1
+									? 'size-14'
+									: 'size-12'}  transition-all bg-black dark:bg-white rounded-full"
+							/>
+						{/if}
+						<!-- navbar -->
+					</div>
+				{/if}
+
+				<div class="flex justify-center items-center flex-1 h-full w-full max-h-full">
+					{#if !camera}
+						{#if loading}
+							<svg
+								class="size-44 text-gray-900 dark:text-gray-400"
+								viewBox="0 0 24 24"
+								fill="currentColor"
+								xmlns="http://www.w3.org/2000/svg"
+								><style>
+									.spinner_qM83 {
+										animation: spinner_8HQG 1.05s infinite;
+									}
+									.spinner_oXPr {
+										animation-delay: 0.1s;
+									}
+									.spinner_ZTLf {
+										animation-delay: 0.2s;
+									}
+									@keyframes spinner_8HQG {
+										0%,
+										57.14% {
+											animation-timing-function: cubic-bezier(0.33, 0.66, 0.66, 1);
+											transform: translate(0);
+										}
+										28.57% {
+											animation-timing-function: cubic-bezier(0.33, 0, 0.66, 0.33);
+											transform: translateY(-6px);
+										}
+										100% {
+											transform: translate(0);
+										}
+									}
+								</style><circle class="spinner_qM83" cx="4" cy="12" r="3" /><circle
+									class="spinner_qM83 spinner_oXPr"
+									cx="12"
+									cy="12"
+									r="3"
+								/><circle class="spinner_qM83 spinner_ZTLf" cx="20" cy="12" r="3" /></svg
+							>
+						{:else}
+							<div
+								class=" {rmsLevel * 100 > 4
+									? ' size-52'
+									: rmsLevel * 100 > 2
+									? 'size-48'
+									: rmsLevel * 100 > 1
+									? 'size-[11.5rem]'
+									: 'size-44'}  transition-all bg-black dark:bg-white rounded-full"
+							/>
+						{/if}
+					{:else}
+						<div
+							class="relative flex video-container w-full max-h-full pt-2 pb-4 md:py-6 px-2 h-full"
+						>
+							<video
+								id="camera-feed"
+								autoplay
+								class="rounded-2xl h-full min-w-full object-cover object-center"
+								playsinline
+							/>
+
+							<canvas id="camera-canvas" style="display:none;" />
+
+							<div class=" absolute top-4 md:top-8 left-4">
+								<button
+									type="button"
+									class="p-1.5 text-white cursor-pointer backdrop-blur-xl bg-black/10 rounded-full"
+									on:click={() => {
+										stopCamera();
+									}}
+								>
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 16 16"
+										fill="currentColor"
+										class="size-6"
+									>
+										<path
+											d="M5.28 4.22a.75.75 0 0 0-1.06 1.06L6.94 8l-2.72 2.72a.75.75 0 1 0 1.06 1.06L8 9.06l2.72 2.72a.75.75 0 1 0 1.06-1.06L9.06 8l2.72-2.72a.75.75 0 0 0-1.06-1.06L8 6.94 5.28 4.22Z"
+										/>
+									</svg>
+								</button>
+							</div>
+						</div>
+					{/if}
+				</div>
+
+				<div class="flex justify-between items-center pb-2 w-full">
+					<div>
+						{#if camera}
+							<VideoInputMenu
+								devices={videoInputDevices}
+								on:change={async (e) => {
+									console.log(e.detail);
+									selectedVideoInputDeviceId = e.detail;
+									await stopVideoStream();
+									await startVideoStream();
+								}}
+							>
+								<button class=" p-3 rounded-full bg-gray-50 dark:bg-gray-900" type="button">
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 20 20"
+										fill="currentColor"
+										class="size-5"
+									>
+										<path
+											fill-rule="evenodd"
+											d="M15.312 11.424a5.5 5.5 0 0 1-9.201 2.466l-.312-.311h2.433a.75.75 0 0 0 0-1.5H3.989a.75.75 0 0 0-.75.75v4.242a.75.75 0 0 0 1.5 0v-2.43l.31.31a7 7 0 0 0 11.712-3.138.75.75 0 0 0-1.449-.39Zm1.23-3.723a.75.75 0 0 0 .219-.53V2.929a.75.75 0 0 0-1.5 0V5.36l-.31-.31A7 7 0 0 0 3.239 8.188a.75.75 0 1 0 1.448.389A5.5 5.5 0 0 1 13.89 6.11l.311.31h-2.432a.75.75 0 0 0 0 1.5h4.243a.75.75 0 0 0 .53-.219Z"
+											clip-rule="evenodd"
+										/>
+									</svg>
+								</button>
+							</VideoInputMenu>
+						{:else}
+							<Tooltip content={$i18n.t('Camera')}>
+								<button
+									class=" p-3 rounded-full bg-gray-50 dark:bg-gray-900"
+									type="button"
+									on:click={() => {
+										startCamera();
+									}}
+								>
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										fill="none"
+										viewBox="0 0 24 24"
+										stroke-width="1.5"
+										stroke="currentColor"
+										class="size-5"
+									>
+										<path
+											stroke-linecap="round"
+											stroke-linejoin="round"
+											d="M6.827 6.175A2.31 2.31 0 0 1 5.186 7.23c-.38.054-.757.112-1.134.175C2.999 7.58 2.25 8.507 2.25 9.574V18a2.25 2.25 0 0 0 2.25 2.25h15A2.25 2.25 0 0 0 21.75 18V9.574c0-1.067-.75-1.994-1.802-2.169a47.865 47.865 0 0 0-1.134-.175 2.31 2.31 0 0 1-1.64-1.055l-.822-1.316a2.192 2.192 0 0 0-1.736-1.039 48.774 48.774 0 0 0-5.232 0 2.192 2.192 0 0 0-1.736 1.039l-.821 1.316Z"
+										/>
+										<path
+											stroke-linecap="round"
+											stroke-linejoin="round"
+											d="M16.5 12.75a4.5 4.5 0 1 1-9 0 4.5 4.5 0 0 1 9 0ZM18.75 10.5h.008v.008h-.008V10.5Z"
+										/>
+									</svg>
+								</button>
+							</Tooltip>
+						{/if}
+					</div>
+
+					<div>
+						<button type="button">
+							<div class=" line-clamp-1 text-sm font-medium">
+								{#if loading}
+									{$i18n.t('Thinking...')}
+								{:else}
+									{$i18n.t('Listening...')}
+								{/if}
+							</div>
+						</button>
+					</div>
+
+					<div>
+						<button
+							class=" p-3 rounded-full bg-gray-50 dark:bg-gray-900"
+							on:click={async () => {
+								showCallOverlay.set(false);
+							}}
+							type="button"
+						>
+							<svg
+								xmlns="http://www.w3.org/2000/svg"
+								viewBox="0 0 20 20"
+								fill="currentColor"
+								class="size-5"
+							>
+								<path
+									d="M6.28 5.22a.75.75 0 0 0-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 1 0 1.06 1.06L10 11.06l3.72 3.72a.75.75 0 1 0 1.06-1.06L11.06 10l3.72-3.72a.75.75 0 0 0-1.06-1.06L10 8.94 6.28 5.22Z"
+								/>
+							</svg>
+						</button>
+					</div>
+				</div>
+			</div>
+		</div>
+	</div>
+{/if}

src/lib/components/chat/MessageInput/CallOverlay/VideoInputMenu.svelte

@@ -0,0 +1,51 @@
+<script lang="ts">
+	import { DropdownMenu } from 'bits-ui';
+	import { flyAndScale } from '$lib/utils/transitions';
+	import { getContext, createEventDispatcher } from 'svelte';
+
+	const i18n = getContext('i18n');
+	const dispatch = createEventDispatcher();
+
+	import Dropdown from '$lib/components/common/Dropdown.svelte';
+
+	export let onClose: Function = () => {};
+	export let devices: any;
+
+	let show = false;
+</script>
+
+<Dropdown
+	bind:show
+	on:change={(e) => {
+		if (e.detail === false) {
+			onClose();
+		}
+	}}
+>
+	<slot />
+
+	<div slot="content">
+		<DropdownMenu.Content
+			class="w-full max-w-[180px] rounded-lg px-1 py-1.5 border border-gray-300/30 dark:border-gray-700/50 z-[9999] bg-white dark:bg-gray-900 dark:text-white shadow-sm"
+			sideOffset={6}
+			side="top"
+			align="start"
+			transition={flyAndScale}
+		>
+			{#each devices as device}
+				<DropdownMenu.Item
+					class="flex gap-2 items-center px-3 py-2 text-sm  cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-md"
+					on:click={() => {
+						dispatch('change', device.deviceId);
+					}}
+				>
+					<div class="flex items-center">
+						<div class=" line-clamp-1">
+							{device?.label ?? 'Camera'}
+						</div>
+					</div>
+				</DropdownMenu.Item>
+			{/each}
+		</DropdownMenu.Content>
+	</div>
+</Dropdown>

src/lib/components/chat/MessageInput/Documents.svelte

@@ -101,7 +101,7 @@
 </script>
 
 {#if filteredItems.length > 0 || prompt.split(' ')?.at(0)?.substring(1).startsWith('http')}
-	<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
+	<div class="pl-1 pr-12 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
 		<div class="flex w-full px-2">
 			<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-xl text-center">
 				<div class=" text-lg font-semibold mt-2">#</div>

src/lib/components/chat/MessageInput/Models.svelte

@@ -133,7 +133,7 @@
 
 {#if prompt.charAt(0) === '@'}
 	{#if filteredModels.length > 0}
-		<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
+		<div class="pl-1 pr-12 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
 			<div class="flex w-full px-2">
 				<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-xl text-center">
 					<div class=" text-lg font-semibold mt-2">@</div>

src/lib/components/chat/MessageInput/PromptCommands.svelte

@@ -6,6 +6,7 @@
 
 	const i18n = getContext('i18n');
 
+	export let files;
 	export let prompt = '';
 	let selectedCommandIdx = 0;
 	let filteredPromptCommands = [];
@@ -35,6 +36,32 @@
 				return '{{CLIPBOARD}}';
 			});
 
+			console.log(clipboardText);
+
+			const clipboardItems = await navigator.clipboard.read();
+
+			let imageUrl = null;
+			for (const item of clipboardItems) {
+				// Check for known image types
+				for (const type of item.types) {
+					if (type.startsWith('image/')) {
+						const blob = await item.getType(type);
+						imageUrl = URL.createObjectURL(blob);
+						console.log(`Image URL (${type}): ${imageUrl}`);
+					}
+				}
+			}
+
+			if (imageUrl) {
+				files = [
+					...files,
+					{
+						type: 'image',
+						url: imageUrl
+					}
+				];
+			}
+
 			text = command.content.replaceAll('{{CLIPBOARD}}', clipboardText);
 		}
 
@@ -61,7 +88,7 @@
 </script>
 
 {#if filteredPromptCommands.length > 0}
-	<div class="md:px-2 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
+	<div class="pl-1 pr-12 mb-3 text-left w-full absolute bottom-0 left-0 right-0">
 		<div class="flex w-full px-2">
 			<div class=" bg-gray-100 dark:bg-gray-700 w-10 rounded-l-xl text-center">
 				<div class=" text-lg font-semibold mt-2">/</div>

src/lib/components/chat/MessageInput/VoiceRecording.svelte

@@ -0,0 +1,458 @@
+<script lang="ts">
+	import { toast } from 'svelte-sonner';
+	import { createEventDispatcher, tick, getContext } from 'svelte';
+	import { config, settings } from '$lib/stores';
+	import { blobToFile, calculateSHA256, findWordIndices } from '$lib/utils';
+
+	import { transcribeAudio } from '$lib/apis/audio';
+
+	const i18n = getContext('i18n');
+
+	const dispatch = createEventDispatcher();
+
+	export let recording = false;
+
+	let loading = false;
+	let confirmed = false;
+
+	let durationSeconds = 0;
+	let durationCounter = null;
+
+	let transcription = '';
+
+	const startDurationCounter = () => {
+		durationCounter = setInterval(() => {
+			durationSeconds++;
+		}, 1000);
+	};
+
+	const stopDurationCounter = () => {
+		clearInterval(durationCounter);
+		durationSeconds = 0;
+	};
+
+	$: if (recording) {
+		startRecording();
+	} else {
+		stopRecording();
+	}
+
+	const formatSeconds = (seconds) => {
+		const minutes = Math.floor(seconds / 60);
+		const remainingSeconds = seconds % 60;
+		const formattedSeconds = remainingSeconds < 10 ? `0${remainingSeconds}` : remainingSeconds;
+		return `${minutes}:${formattedSeconds}`;
+	};
+
+	let speechRecognition;
+
+	let mediaRecorder;
+	let audioChunks = [];
+
+	const MIN_DECIBELS = -45;
+	const VISUALIZER_BUFFER_LENGTH = 300;
+
+	let visualizerData = Array(VISUALIZER_BUFFER_LENGTH).fill(0);
+
+	// Function to calculate the RMS level from time domain data
+	const calculateRMS = (data: Uint8Array) => {
+		let sumSquares = 0;
+		for (let i = 0; i < data.length; i++) {
+			const normalizedValue = (data[i] - 128) / 128; // Normalize the data
+			sumSquares += normalizedValue * normalizedValue;
+		}
+		return Math.sqrt(sumSquares / data.length);
+	};
+
+	const normalizeRMS = (rms) => {
+		rms = rms * 10;
+		const exp = 1.5; // Adjust exponent value; values greater than 1 expand larger numbers more and compress smaller numbers more
+		const scaledRMS = Math.pow(rms, exp);
+
+		// Scale between 0.01 (1%) and 1.0 (100%)
+		return Math.min(1.0, Math.max(0.01, scaledRMS));
+	};
+
+	const analyseAudio = (stream) => {
+		const audioContext = new AudioContext();
+		const audioStreamSource = audioContext.createMediaStreamSource(stream);
+
+		const analyser = audioContext.createAnalyser();
+		analyser.minDecibels = MIN_DECIBELS;
+		audioStreamSource.connect(analyser);
+
+		const bufferLength = analyser.frequencyBinCount;
+
+		const domainData = new Uint8Array(bufferLength);
+		const timeDomainData = new Uint8Array(analyser.fftSize);
+
+		let lastSoundTime = Date.now();
+
+		const detectSound = () => {
+			const processFrame = () => {
+				if (!recording || loading) return;
+
+				if (recording && !loading) {
+					analyser.getByteTimeDomainData(timeDomainData);
+					analyser.getByteFrequencyData(domainData);
+
+					// Calculate RMS level from time domain data
+					const rmsLevel = calculateRMS(timeDomainData);
+					// Push the calculated decibel level to visualizerData
+					visualizerData.push(normalizeRMS(rmsLevel));
+
+					// Ensure visualizerData array stays within the buffer length
+					if (visualizerData.length >= VISUALIZER_BUFFER_LENGTH) {
+						visualizerData.shift();
+					}
+
+					visualizerData = visualizerData;
+
+					// if (domainData.some((value) => value > 0)) {
+					// 	lastSoundTime = Date.now();
+					// }
+
+					// if (recording && Date.now() - lastSoundTime > 3000) {
+					// 	if ($settings?.speechAutoSend ?? false) {
+					// 		confirmRecording();
+					// 	}
+					// }
+				}
+
+				window.requestAnimationFrame(processFrame);
+			};
+
+			window.requestAnimationFrame(processFrame);
+		};
+
+		detectSound();
+	};
+
+	const transcribeHandler = async (audioBlob) => {
+		// Create a blob from the audio chunks
+
+		await tick();
+		const file = blobToFile(audioBlob, 'recording.wav');
+
+		const res = await transcribeAudio(localStorage.token, file).catch((error) => {
+			toast.error(error);
+			return null;
+		});
+
+		if (res) {
+			console.log(res.text);
+			dispatch('confirm', res.text);
+		}
+	};
+
+	const saveRecording = (blob) => {
+		const url = URL.createObjectURL(blob);
+		const a = document.createElement('a');
+		document.body.appendChild(a);
+		a.style = 'display: none';
+		a.href = url;
+		a.download = 'recording.wav';
+		a.click();
+		window.URL.revokeObjectURL(url);
+	};
+
+	const startRecording = async () => {
+		startDurationCounter();
+
+		const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
+		mediaRecorder = new MediaRecorder(stream);
+		mediaRecorder.onstart = () => {
+			console.log('Recording started');
+			audioChunks = [];
+			analyseAudio(stream);
+		};
+		mediaRecorder.ondataavailable = (event) => audioChunks.push(event.data);
+		mediaRecorder.onstop = async () => {
+			console.log('Recording stopped');
+			if (($settings?.audio?.stt?.engine ?? '') === 'web') {
+				audioChunks = [];
+			} else {
+				if (confirmed) {
+					const audioBlob = new Blob(audioChunks, { type: 'audio/wav' });
+
+					await transcribeHandler(audioBlob);
+
+					confirmed = false;
+					loading = false;
+				}
+				audioChunks = [];
+				recording = false;
+			}
+		};
+		mediaRecorder.start();
+		if ($config.audio.stt.engine === 'web' || ($settings?.audio?.stt?.engine ?? '') === 'web') {
+			if ('SpeechRecognition' in window || 'webkitSpeechRecognition' in window) {
+				// Create a SpeechRecognition object
+				speechRecognition = new (window.SpeechRecognition || window.webkitSpeechRecognition)();
+
+				// Set continuous to true for continuous recognition
+				speechRecognition.continuous = true;
+
+				// Set the timeout for turning off the recognition after inactivity (in milliseconds)
+				const inactivityTimeout = 2000; // 3 seconds
+
+				let timeoutId;
+				// Start recognition
+				speechRecognition.start();
+
+				// Event triggered when speech is recognized
+				speechRecognition.onresult = async (event) => {
+					// Clear the inactivity timeout
+					clearTimeout(timeoutId);
+
+					// Handle recognized speech
+					console.log(event);
+					const transcript = event.results[Object.keys(event.results).length - 1][0].transcript;
+
+					transcription = `${transcription}${transcript}`;
+
+					await tick();
+					document.getElementById('chat-textarea')?.focus();
+
+					// Restart the inactivity timeout
+					timeoutId = setTimeout(() => {
+						console.log('Speech recognition turned off due to inactivity.');
+						speechRecognition.stop();
+					}, inactivityTimeout);
+				};
+
+				// Event triggered when recognition is ended
+				speechRecognition.onend = function () {
+					// Restart recognition after it ends
+					console.log('recognition ended');
+
+					confirmRecording();
+					dispatch('confirm', transcription);
+
+					confirmed = false;
+					loading = false;
+				};
+
+				// Event triggered when an error occurs
+				speechRecognition.onerror = function (event) {
+					console.log(event);
+					toast.error($i18n.t(`Speech recognition error: {{error}}`, { error: event.error }));
+					dispatch('cancel');
+
+					stopRecording();
+				};
+			}
+		}
+	};
+
+	const stopRecording = async () => {
+		if (recording && mediaRecorder) {
+			await mediaRecorder.stop();
+		}
+		stopDurationCounter();
+		audioChunks = [];
+	};
+
+	const confirmRecording = async () => {
+		loading = true;
+		confirmed = true;
+
+		if (recording && mediaRecorder) {
+			await mediaRecorder.stop();
+		}
+		clearInterval(durationCounter);
+	};
+</script>
+
+<div
+	class="{loading
+		? ' bg-gray-100/50 dark:bg-gray-850/50'
+		: 'bg-indigo-300/10 dark:bg-indigo-500/10 '} rounded-full flex p-2.5"
+>
+	<div class="flex items-center mr-1">
+		<button
+			type="button"
+			class="p-1.5
+
+            {loading
+				? ' bg-gray-200 dark:bg-gray-700/50'
+				: 'bg-indigo-400/20 text-indigo-600 dark:text-indigo-300 '} 
+
+
+             rounded-full"
+			on:click={async () => {
+				dispatch('cancel');
+				stopRecording();
+			}}
+		>
+			<svg
+				xmlns="http://www.w3.org/2000/svg"
+				fill="none"
+				viewBox="0 0 24 24"
+				stroke-width="3"
+				stroke="currentColor"
+				class="size-4"
+			>
+				<path stroke-linecap="round" stroke-linejoin="round" d="M6 18 18 6M6 6l12 12" />
+			</svg>
+		</button>
+	</div>
+
+	<div
+		class="flex flex-1 self-center items-center justify-between ml-2 mx-1 overflow-hidden h-6"
+		dir="rtl"
+	>
+		<div class="flex-1 flex items-center gap-0.5 h-6">
+			{#each visualizerData.slice().reverse() as rms}
+				<div
+					class="w-[2px]
+                    
+                    {loading
+						? ' bg-gray-500 dark:bg-gray-400   '
+						: 'bg-indigo-500 dark:bg-indigo-400  '} 
+                    
+                    inline-block h-full"
+					style="height: {Math.min(100, Math.max(14, rms * 100))}%;"
+				/>
+			{/each}
+		</div>
+	</div>
+
+	<div class="  mx-1.5 pr-1 flex justify-center items-center">
+		<div
+			class="text-sm
+        
+        
+        {loading ? ' text-gray-500  dark:text-gray-400  ' : ' text-indigo-400 '} 
+       font-medium flex-1 mx-auto text-center"
+		>
+			{formatSeconds(durationSeconds)}
+		</div>
+	</div>
+
+	<div class="flex items-center mr-1">
+		{#if loading}
+			<div class=" text-gray-500 rounded-full cursor-not-allowed">
+				<svg
+					width="24"
+					height="24"
+					viewBox="0 0 24 24"
+					xmlns="http://www.w3.org/2000/svg"
+					fill="currentColor"
+					><style>
+						.spinner_OSmW {
+							transform-origin: center;
+							animation: spinner_T6mA 0.75s step-end infinite;
+						}
+						@keyframes spinner_T6mA {
+							8.3% {
+								transform: rotate(30deg);
+							}
+							16.6% {
+								transform: rotate(60deg);
+							}
+							25% {
+								transform: rotate(90deg);
+							}
+							33.3% {
+								transform: rotate(120deg);
+							}
+							41.6% {
+								transform: rotate(150deg);
+							}
+							50% {
+								transform: rotate(180deg);
+							}
+							58.3% {
+								transform: rotate(210deg);
+							}
+							66.6% {
+								transform: rotate(240deg);
+							}
+							75% {
+								transform: rotate(270deg);
+							}
+							83.3% {
+								transform: rotate(300deg);
+							}
+							91.6% {
+								transform: rotate(330deg);
+							}
+							100% {
+								transform: rotate(360deg);
+							}
+						}
+					</style><g class="spinner_OSmW"
+						><rect x="11" y="1" width="2" height="5" opacity=".14" /><rect
+							x="11"
+							y="1"
+							width="2"
+							height="5"
+							transform="rotate(30 12 12)"
+							opacity=".29"
+						/><rect
+							x="11"
+							y="1"
+							width="2"
+							height="5"
+							transform="rotate(60 12 12)"
+							opacity=".43"
+						/><rect
+							x="11"
+							y="1"
+							width="2"
+							height="5"
+							transform="rotate(90 12 12)"
+							opacity=".57"
+						/><rect
+							x="11"
+							y="1"
+							width="2"
+							height="5"
+							transform="rotate(120 12 12)"
+							opacity=".71"
+						/><rect
+							x="11"
+							y="1"
+							width="2"
+							height="5"
+							transform="rotate(150 12 12)"
+							opacity=".86"
+						/><rect x="11" y="1" width="2" height="5" transform="rotate(180 12 12)" /></g
+					></svg
+				>
+			</div>
+		{:else}
+			<button
+				type="button"
+				class="p-1.5 bg-indigo-500 text-white dark:bg-indigo-500 dark:text-blue-950 rounded-full"
+				on:click={async () => {
+					await confirmRecording();
+				}}
+			>
+				<svg
+					xmlns="http://www.w3.org/2000/svg"
+					fill="none"
+					viewBox="0 0 24 24"
+					stroke-width="2.5"
+					stroke="currentColor"
+					class="size-4"
+				>
+					<path stroke-linecap="round" stroke-linejoin="round" d="m4.5 12.75 6 6 9-13.5" />
+				</svg>
+			</button>
+		{/if}
+	</div>
+</div>
+
+<style>
+	.visualizer {
+		display: flex;
+		height: 100%;
+	}
+
+	.visualizer-bar {
+		width: 2px;
+		background-color: #4a5aba; /* or whatever color you need */
+	}
+</style>

src/lib/components/chat/Messages.svelte

@@ -286,7 +286,7 @@
 				{#each messages as message, messageIdx}
 					<div class=" w-full {messageIdx === messages.length - 1 ? ' pb-12' : ''}">
 						<div
-							class="flex flex-col justify-between px-5 mb-3 {$settings?.fullScreenMode ?? null
+							class="flex flex-col justify-between px-5 mb-3 {$settings?.widescreenMode ?? null
 								? 'max-w-full'
 								: 'max-w-5xl'} mx-auto rounded-lg group"
 						>

src/lib/components/chat/Messages/CompareMessages.svelte

@@ -109,7 +109,7 @@
 					class=" snap-center min-w-80 w-full max-w-full m-1 border {history.messages[
 						currentMessageId
 					].model === model
-						? 'border-gray-100 dark:border-gray-700 border-[1.5px]'
+						? 'border-gray-100 dark:border-gray-850 border-[1.5px]'
 						: 'border-gray-50 dark:border-gray-850 '} transition p-5 rounded-3xl"
 					on:click={() => {
 						currentMessageId = groupedMessages[model].messages[groupedMessagesIdx[model]].id;

src/lib/components/chat/Messages/ResponseMessage.svelte

@@ -211,82 +211,98 @@
 			speaking = null;
 			speakingIdx = null;
 		} else {
-			speaking = true;
+			if ((message?.content ?? '').trim() !== '') {
+				speaking = true;
 
-			if ($settings?.audio?.TTSEngine === 'openai') {
-				loadingSpeech = true;
+				if ($config.audio.tts.engine === 'openai') {
+					loadingSpeech = true;
 
-				const sentences = extractSentences(message.content).reduce((mergedTexts, currentText) => {
-					const lastIndex = mergedTexts.length - 1;
-					if (lastIndex >= 0) {
-						const previousText = mergedTexts[lastIndex];
-						const wordCount = previousText.split(/\s+/).length;
-						if (wordCount < 2) {
-							mergedTexts[lastIndex] = previousText + ' ' + currentText;
+					const sentences = extractSentences(message.content).reduce((mergedTexts, currentText) => {
+						const lastIndex = mergedTexts.length - 1;
+						if (lastIndex >= 0) {
+							const previousText = mergedTexts[lastIndex];
+							const wordCount = previousText.split(/\s+/).length;
+							if (wordCount < 2) {
+								mergedTexts[lastIndex] = previousText + ' ' + currentText;
+							} else {
+								mergedTexts.push(currentText);
+							}
 						} else {
 							mergedTexts.push(currentText);
 						}
-					} else {
-						mergedTexts.push(currentText);
+						return mergedTexts;
+					}, []);
+
+					console.log(sentences);
+
+					sentencesAudio = sentences.reduce((a, e, i, arr) => {
+						a[i] = null;
+						return a;
+					}, {});
+
+					let lastPlayedAudioPromise = Promise.resolve(); // Initialize a promise that resolves immediately
+
+					for (const [idx, sentence] of sentences.entries()) {
+						const res = await synthesizeOpenAISpeech(
+							localStorage.token,
+							$settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice,
+							sentence
+						).catch((error) => {
+							toast.error(error);
+
+							speaking = null;
+							loadingSpeech = false;
+
+							return null;
+						});
+
+						if (res) {
+							const blob = await res.blob();
+							const blobUrl = URL.createObjectURL(blob);
+							const audio = new Audio(blobUrl);
+							sentencesAudio[idx] = audio;
+							loadingSpeech = false;
+							lastPlayedAudioPromise = lastPlayedAudioPromise.then(() => playAudio(idx));
+						}
 					}
-					return mergedTexts;
-				}, []);
+				} else {
+					let voices = [];
+					const getVoicesLoop = setInterval(async () => {
+						voices = await speechSynthesis.getVoices();
+						if (voices.length > 0) {
+							clearInterval(getVoicesLoop);
 
-				console.log(sentences);
+							const voice =
+								voices
+									?.filter(
+										(v) =>
+											v.voiceURI === ($settings?.audio?.tts?.voice ?? $config?.audio?.tts?.voice)
+									)
+									?.at(0) ?? undefined;
 
-				sentencesAudio = sentences.reduce((a, e, i, arr) => {
-					a[i] = null;
-					return a;
-				}, {});
+							console.log(voice);
 
-				let lastPlayedAudioPromise = Promise.resolve(); // Initialize a promise that resolves immediately
+							const speak = new SpeechSynthesisUtterance(message.content);
 
-				for (const [idx, sentence] of sentences.entries()) {
-					const res = await synthesizeOpenAISpeech(
-						localStorage.token,
-						$settings?.audio?.speaker,
-						sentence,
-						$settings?.audio?.model
-					).catch((error) => {
-						toast.error(error);
+							console.log(speak);
 
-						speaking = null;
-						loadingSpeech = false;
+							speak.onend = () => {
+								speaking = null;
+								if ($settings.conversationMode) {
+									document.getElementById('voice-input-button')?.click();
+								}
+							};
 
-						return null;
-					});
+							if (voice) {
+								speak.voice = voice;
+							}
 
-					if (res) {
-						const blob = await res.blob();
-						const blobUrl = URL.createObjectURL(blob);
-						const audio = new Audio(blobUrl);
-						sentencesAudio[idx] = audio;
-						loadingSpeech = false;
-						lastPlayedAudioPromise = lastPlayedAudioPromise.then(() => playAudio(idx));
-					}
+							speechSynthesis.speak(speak);
+						}
+					}, 100);
 				}
 			} else {
-				let voices = [];
-				const getVoicesLoop = setInterval(async () => {
-					voices = await speechSynthesis.getVoices();
-					if (voices.length > 0) {
-						clearInterval(getVoicesLoop);
-
-						const voice =
-							voices?.filter((v) => v.name === $settings?.audio?.speaker)?.at(0) ?? undefined;
-
-						const speak = new SpeechSynthesisUtterance(message.content);
-
-						speak.onend = () => {
-							speaking = null;
-							if ($settings.conversationMode) {
-								document.getElementById('voice-input-button')?.click();
-							}
-						};
-						speak.voice = voice;
-						speechSynthesis.speak(speak);
-					}
-				}, 100);
+				toast.error('No content to speak');
 			}
 		}
 	};
@@ -404,26 +420,29 @@
 				class="prose chat-{message.role} w-full max-w-full dark:prose-invert prose-headings:my-0 prose-headings:-mb-4 prose-p:m-0 prose-p:-mb-6 prose-pre:my-0 prose-table:my-0 prose-blockquote:my-0 prose-img:my-0 prose-ul:-my-4 prose-ol:-my-4 prose-li:-my-3 prose-ul:-mb-6 prose-ol:-mb-8 prose-ol:p-0 prose-li:-mb-4 whitespace-pre-line"
 			>
 				<div>
-					{#if message?.status}
+					{#if (message?.statusHistory ?? [...(message?.status ? [message?.status] : [])]).length > 0}
+						{@const status = (
+							message?.statusHistory ?? [...(message?.status ? [message?.status] : [])]
+						).at(-1)}
 						<div class="flex items-center gap-2 pt-1 pb-1">
-							{#if message?.status?.done === false}
+							{#if status.done === false}
 								<div class="">
 									<Spinner className="size-4" />
 								</div>
 							{/if}
 
-							{#if message?.status?.action === 'web_search' && message?.status?.urls}
-								<WebSearchResults urls={message?.status?.urls}>
+							{#if status?.action === 'web_search' && status?.urls}
+								<WebSearchResults {status}>
 									<div class="flex flex-col justify-center -space-y-0.5">
 										<div class="text-base line-clamp-1 text-wrap">
-											{message.status.description}
+											{status?.description}
 										</div>
 									</div>
 								</WebSearchResults>
 							{:else}
 								<div class="flex flex-col justify-center -space-y-0.5">
 									<div class=" text-gray-500 dark:text-gray-500 text-base line-clamp-1 text-wrap">
-										{message.status.description}
+										{status?.description}
 									</div>
 								</div>
 							{/if}
@@ -757,7 +776,7 @@
 										</Tooltip>
 
 										{#if $config?.features.enable_image_generation && !readOnly}
-											<Tooltip content="Generate Image" placement="bottom">
+											<Tooltip content={$i18n.t('Generate Image')} placement="bottom">
 												<button
 													class="{isLastMessage
 														? 'visible'

src/lib/components/chat/Messages/ResponseMessage/WebSearchResults.svelte

@@ -1,10 +1,11 @@
 <script lang="ts">
 	import ChevronDown from '$lib/components/icons/ChevronDown.svelte';
 	import ChevronUp from '$lib/components/icons/ChevronUp.svelte';
+	import MagnifyingGlass from '$lib/components/icons/MagnifyingGlass.svelte';
 	import { Collapsible } from 'bits-ui';
 	import { slide } from 'svelte/transition';
 
-	export let urls = [];
+	export let status = { urls: [], query: '' };
 	let state = false;
 </script>
 
@@ -27,11 +28,45 @@
 		class=" text-sm border border-gray-300/30 dark:border-gray-700/50 rounded-xl"
 		transition={slide}
 	>
-		{#each urls as url, urlIdx}
+		{#if status?.query}
+			<a
+				href="https://www.google.com/search?q={status.query}"
+				target="_blank"
+				class="flex w-full items-center p-3 px-4 border-b border-gray-300/30 dark:border-gray-700/50 group/item justify-between font-normal text-gray-800 dark:text-gray-300 no-underline"
+			>
+				<div class="flex gap-2 items-center">
+					<MagnifyingGlass />
+
+					<div class=" line-clamp-1">
+						{status.query}
+					</div>
+				</div>
+
+				<div
+					class=" ml-1 text-white dark:text-gray-900 group-hover/item:text-gray-600 dark:group-hover/item:text-white transition"
+				>
+					<!--  -->
+					<svg
+						xmlns="http://www.w3.org/2000/svg"
+						viewBox="0 0 16 16"
+						fill="currentColor"
+						class="size-4"
+					>
+						<path
+							fill-rule="evenodd"
+							d="M4.22 11.78a.75.75 0 0 1 0-1.06L9.44 5.5H5.75a.75.75 0 0 1 0-1.5h5.5a.75.75 0 0 1 .75.75v5.5a.75.75 0 0 1-1.5 0V6.56l-5.22 5.22a.75.75 0 0 1-1.06 0Z"
+							clip-rule="evenodd"
+						/>
+					</svg>
+				</div>
+			</a>
+		{/if}
+
+		{#each status.urls as url, urlIdx}
 			<a
 				href={url}
 				target="_blank"
-				class="flex w-full items-center p-3 px-4 {urlIdx === urls.length - 1
+				class="flex w-full items-center p-3 px-4 {urlIdx === status.urls.length - 1
 					? ''
 					: 'border-b border-gray-300/30 dark:border-gray-700/50'} group/item justify-between font-normal text-gray-800 dark:text-gray-300"
 			>

src/lib/components/chat/ModelSelector/Selector.svelte

@@ -219,7 +219,7 @@
 	<DropdownMenu.Content
 		class=" z-40 {$mobile
 			? `w-full`
-			: `${className}`} max-w-[calc(100vw-1rem)] justify-start rounded-xl  bg-white dark:bg-gray-850 dark:text-white shadow-lg border border-gray-300/30 dark:border-gray-700/50  outline-none "
+			: `${className}`} max-w-[calc(100vw-1rem)] justify-start rounded-xl  bg-white dark:bg-gray-850 dark:text-white shadow-lg border border-gray-300/30 dark:border-gray-850/50  outline-none "
 		transition={flyAndScale}
 		side={$mobile ? 'bottom' : 'bottom-start'}
 		sideOffset={4}
@@ -265,7 +265,7 @@
 								</div>
 							{/if}
 							<div class="flex items-center gap-2">
-								<div class="flex items-center">
+								<div class="flex items-center min-w-fit">
 									<div class="line-clamp-1">
 										{item.label}
 									</div>

src/lib/components/chat/Settings/About.svelte

@@ -92,7 +92,7 @@
 		</div>
 
 		{#if ollamaVersion}
-			<hr class=" dark:border-gray-700" />
+			<hr class=" dark:border-gray-850" />
 
 			<div>
 				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Ollama Version')}</div>
@@ -104,7 +104,7 @@
 			</div>
 		{/if}
 
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
 
 		<div class="flex space-x-1">
 			<a href="https://discord.gg/5rJgQTnV4s" target="_blank">

src/lib/components/chat/Settings/Account.svelte

@@ -234,7 +234,7 @@
 			<UpdatePassword />
 		</div>
 
-		<hr class=" dark:border-gray-700 my-4" />
+		<hr class=" dark:border-gray-850 my-4" />
 
 		<div class="flex justify-between items-center text-sm">
 			<div class="  font-medium">{$i18n.t('API keys')}</div>

src/lib/components/chat/Settings/Advanced/AdvancedParams.svelte

@@ -5,21 +5,23 @@
 
 	const i18n = getContext('i18n');
 
+	export let admin = false;
+
 	export let params = {
 		// Advanced
-		seed: 0,
+		seed: null,
 		stop: null,
-		temperature: '',
-		frequency_penalty: '',
-		repeat_last_n: '',
-		mirostat: '',
-		mirostat_eta: '',
-		mirostat_tau: '',
-		top_k: '',
-		top_p: '',
-		tfs_z: '',
-		num_ctx: '',
-		max_tokens: '',
+		temperature: null,
+		frequency_penalty: null,
+		repeat_last_n: null,
+		mirostat: null,
+		mirostat_eta: null,
+		mirostat_tau: null,
+		top_k: null,
+		top_p: null,
+		tfs_z: null,
+		num_ctx: null,
+		max_tokens: null,
 		use_mmap: null,
 		use_mlock: null,
 		num_thread: null,
@@ -112,10 +114,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.temperature = (params?.temperature ?? '') === '' ? 0.8 : '';
+					params.temperature = (params?.temperature ?? null) === null ? 0.8 : null;
 				}}
 			>
-				{#if (params?.temperature ?? '') === ''}
+				{#if (params?.temperature ?? null) === null}
 					<span class="ml-2 self-center"> {$i18n.t('Default')} </span>
 				{:else}
 					<span class="ml-2 self-center"> {$i18n.t('Custom')} </span>
@@ -123,7 +125,7 @@
 			</button>
 		</div>
 
-		{#if (params?.temperature ?? '') !== ''}
+		{#if (params?.temperature ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -143,7 +145,7 @@
 						class=" bg-transparent text-center w-14"
 						min="0"
 						max="1"
-						step="0.05"
+						step="any"
 					/>
 				</div>
 			</div>
@@ -158,10 +160,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.mirostat = (params?.mirostat ?? '') === '' ? 0 : '';
+					params.mirostat = (params?.mirostat ?? null) === null ? 0 : null;
 				}}
 			>
-				{#if (params?.mirostat ?? '') === ''}
+				{#if (params?.mirostat ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -169,7 +171,7 @@
 			</button>
 		</div>
 
-		{#if (params?.mirostat ?? '') !== ''}
+		{#if (params?.mirostat ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -204,10 +206,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.mirostat_eta = (params?.mirostat_eta ?? '') === '' ? 0.1 : '';
+					params.mirostat_eta = (params?.mirostat_eta ?? null) === null ? 0.1 : null;
 				}}
 			>
-				{#if (params?.mirostat_eta ?? '') === ''}
+				{#if (params?.mirostat_eta ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -215,7 +217,7 @@
 			</button>
 		</div>
 
-		{#if (params?.mirostat_eta ?? '') !== ''}
+		{#if (params?.mirostat_eta ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -235,7 +237,7 @@
 						class=" bg-transparent text-center w-14"
 						min="0"
 						max="1"
-						step="0.05"
+						step="any"
 					/>
 				</div>
 			</div>
@@ -250,10 +252,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.mirostat_tau = (params?.mirostat_tau ?? '') === '' ? 5.0 : '';
+					params.mirostat_tau = (params?.mirostat_tau ?? null) === null ? 5.0 : null;
 				}}
 			>
-				{#if (params?.mirostat_tau ?? '') === ''}
+				{#if (params?.mirostat_tau ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -261,7 +263,7 @@
 			</button>
 		</div>
 
-		{#if (params?.mirostat_tau ?? '') !== ''}
+		{#if (params?.mirostat_tau ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -281,7 +283,7 @@
 						class=" bg-transparent text-center w-14"
 						min="0"
 						max="10"
-						step="0.5"
+						step="any"
 					/>
 				</div>
 			</div>
@@ -296,10 +298,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.top_k = (params?.top_k ?? '') === '' ? 40 : '';
+					params.top_k = (params?.top_k ?? null) === null ? 40 : null;
 				}}
 			>
-				{#if (params?.top_k ?? '') === ''}
+				{#if (params?.top_k ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -307,7 +309,7 @@
 			</button>
 		</div>
 
-		{#if (params?.top_k ?? '') !== ''}
+		{#if (params?.top_k ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -327,7 +329,7 @@
 						class=" bg-transparent text-center w-14"
 						min="0"
 						max="100"
-						step="0.5"
+						step="any"
 					/>
 				</div>
 			</div>
@@ -342,10 +344,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.top_p = (params?.top_p ?? '') === '' ? 0.9 : '';
+					params.top_p = (params?.top_p ?? null) === null ? 0.9 : null;
 				}}
 			>
-				{#if (params?.top_p ?? '') === ''}
+				{#if (params?.top_p ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -353,7 +355,7 @@
 			</button>
 		</div>
 
-		{#if (params?.top_p ?? '') !== ''}
+		{#if (params?.top_p ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -373,7 +375,7 @@
 						class=" bg-transparent text-center w-14"
 						min="0"
 						max="1"
-						step="0.05"
+						step="any"
 					/>
 				</div>
 			</div>
@@ -388,10 +390,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.frequency_penalty = (params?.frequency_penalty ?? '') === '' ? 1.1 : '';
+					params.frequency_penalty = (params?.frequency_penalty ?? null) === null ? 1.1 : null;
 				}}
 			>
-				{#if (params?.frequency_penalty ?? '') === ''}
+				{#if (params?.frequency_penalty ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -399,7 +401,7 @@
 			</button>
 		</div>
 
-		{#if (params?.frequency_penalty ?? '') !== ''}
+		{#if (params?.frequency_penalty ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -419,7 +421,7 @@
 						class=" bg-transparent text-center w-14"
 						min="0"
 						max="2"
-						step="0.05"
+						step="any"
 					/>
 				</div>
 			</div>
@@ -434,10 +436,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.repeat_last_n = (params?.repeat_last_n ?? '') === '' ? 64 : '';
+					params.repeat_last_n = (params?.repeat_last_n ?? null) === null ? 64 : null;
 				}}
 			>
-				{#if (params?.repeat_last_n ?? '') === ''}
+				{#if (params?.repeat_last_n ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -445,7 +447,7 @@
 			</button>
 		</div>
 
-		{#if (params?.repeat_last_n ?? '') !== ''}
+		{#if (params?.repeat_last_n ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -480,10 +482,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.tfs_z = (params?.tfs_z ?? '') === '' ? 1 : '';
+					params.tfs_z = (params?.tfs_z ?? null) === null ? 1 : null;
 				}}
 			>
-				{#if (params?.tfs_z ?? '') === ''}
+				{#if (params?.tfs_z ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -491,7 +493,7 @@
 			</button>
 		</div>
 
-		{#if (params?.tfs_z ?? '') !== ''}
+		{#if (params?.tfs_z ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -511,7 +513,7 @@
 						class=" bg-transparent text-center w-14"
 						min="0"
 						max="2"
-						step="0.05"
+						step="any"
 					/>
 				</div>
 			</div>
@@ -526,10 +528,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.num_ctx = (params?.num_ctx ?? '') === '' ? 2048 : '';
+					params.num_ctx = (params?.num_ctx ?? null) === null ? 2048 : null;
 				}}
 			>
-				{#if (params?.num_ctx ?? '') === ''}
+				{#if (params?.num_ctx ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -537,7 +539,7 @@
 			</button>
 		</div>
 
-		{#if (params?.num_ctx ?? '') !== ''}
+		{#if (params?.num_ctx ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -556,7 +558,7 @@
 						type="number"
 						class=" bg-transparent text-center w-14"
 						min="-1"
-						step="10"
+						step="1"
 					/>
 				</div>
 			</div>
@@ -571,10 +573,10 @@
 				class="p-1 px-3 text-xs flex rounded transition"
 				type="button"
 				on:click={() => {
-					params.max_tokens = (params?.max_tokens ?? '') === '' ? 128 : '';
+					params.max_tokens = (params?.max_tokens ?? null) === null ? 128 : null;
 				}}
 			>
-				{#if (params?.max_tokens ?? '') === ''}
+				{#if (params?.max_tokens ?? null) === null}
 					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
 				{:else}
 					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
@@ -582,7 +584,7 @@
 			</button>
 		</div>
 
-		{#if (params?.max_tokens ?? '') !== ''}
+		{#if (params?.max_tokens ?? null) !== null}
 			<div class="flex mt-0.5 space-x-2">
 				<div class=" flex-1">
 					<input
@@ -609,122 +611,124 @@
 		{/if}
 	</div>
 
-	<div class=" py-0.5 w-full justify-between">
-		<div class="flex w-full justify-between">
-			<div class=" self-center text-xs font-medium">{$i18n.t('use_mmap (Ollama)')}</div>
+	{#if admin}
+		<div class=" py-0.5 w-full justify-between">
+			<div class="flex w-full justify-between">
+				<div class=" self-center text-xs font-medium">{$i18n.t('use_mmap (Ollama)')}</div>
 
-			<button
-				class="p-1 px-3 text-xs flex rounded transition"
-				type="button"
-				on:click={() => {
-					params.use_mmap = (params?.use_mmap ?? null) === null ? true : null;
-				}}
-			>
-				{#if (params?.use_mmap ?? null) === null}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
-				{:else}
-					<span class="ml-2 self-center">{$i18n.t('On')}</span>
-				{/if}
-			</button>
-		</div>
-	</div>
-
-	<div class=" py-0.5 w-full justify-between">
-		<div class="flex w-full justify-between">
-			<div class=" self-center text-xs font-medium">{$i18n.t('use_mlock (Ollama)')}</div>
-
-			<button
-				class="p-1 px-3 text-xs flex rounded transition"
-				type="button"
-				on:click={() => {
-					params.use_mlock = (params?.use_mlock ?? null) === null ? true : null;
-				}}
-			>
-				{#if (params?.use_mlock ?? null) === null}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
-				{:else}
-					<span class="ml-2 self-center">{$i18n.t('On')}</span>
-				{/if}
-			</button>
-		</div>
-	</div>
-
-	<div class=" py-0.5 w-full justify-between">
-		<div class="flex w-full justify-between">
-			<div class=" self-center text-xs font-medium">{$i18n.t('num_thread (Ollama)')}</div>
-
-			<button
-				class="p-1 px-3 text-xs flex rounded transition"
-				type="button"
-				on:click={() => {
-					params.num_thread = (params?.num_thread ?? null) === null ? 2 : null;
-				}}
-			>
-				{#if (params?.num_thread ?? null) === null}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
-				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
-				{/if}
-			</button>
-		</div>
-
-		{#if (params?.num_thread ?? null) !== null}
-			<div class="flex mt-0.5 space-x-2">
-				<div class=" flex-1">
-					<input
-						id="steps-range"
-						type="range"
-						min="1"
-						max="256"
-						step="1"
-						bind:value={params.num_thread}
-						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
-					/>
-				</div>
-				<div class="">
-					<input
-						bind:value={params.num_thread}
-						type="number"
-						class=" bg-transparent text-center w-14"
-						min="1"
-						max="256"
-						step="1"
-					/>
-				</div>
+				<button
+					class="p-1 px-3 text-xs flex rounded transition"
+					type="button"
+					on:click={() => {
+						params.use_mmap = (params?.use_mmap ?? null) === null ? true : null;
+					}}
+				>
+					{#if (params?.use_mmap ?? null) === null}
+						<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					{:else}
+						<span class="ml-2 self-center">{$i18n.t('On')}</span>
+					{/if}
+				</button>
 			</div>
-		{/if}
-	</div>
-
-	<div class=" py-0.5 w-full justify-between">
-		<div class="flex w-full justify-between">
-			<div class=" self-center text-xs font-medium">{$i18n.t('Template')}</div>
-
-			<button
-				class="p-1 px-3 text-xs flex rounded transition"
-				type="button"
-				on:click={() => {
-					params.template = (params?.template ?? null) === null ? '' : null;
-				}}
-			>
-				{#if (params?.template ?? null) === null}
-					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
-				{:else}
-					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
-				{/if}
-			</button>
 		</div>
 
-		{#if (params?.template ?? null) !== null}
-			<div class="flex mt-0.5 space-x-2">
-				<div class=" flex-1">
-					<textarea
-						class="px-3 py-1.5 text-sm w-full bg-transparent border dark:border-gray-600 outline-none rounded-lg -mb-1"
-						placeholder="Write your model template content here"
-						rows="4"
-						bind:value={params.template}
-					/>
-				</div>
+		<div class=" py-0.5 w-full justify-between">
+			<div class="flex w-full justify-between">
+				<div class=" self-center text-xs font-medium">{$i18n.t('use_mlock (Ollama)')}</div>
+
+				<button
+					class="p-1 px-3 text-xs flex rounded transition"
+					type="button"
+					on:click={() => {
+						params.use_mlock = (params?.use_mlock ?? null) === null ? true : null;
+					}}
+				>
+					{#if (params?.use_mlock ?? null) === null}
+						<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					{:else}
+						<span class="ml-2 self-center">{$i18n.t('On')}</span>
+					{/if}
+				</button>
 			</div>
-		{/if}
-	</div>
+		</div>
+
+		<div class=" py-0.5 w-full justify-between">
+			<div class="flex w-full justify-between">
+				<div class=" self-center text-xs font-medium">{$i18n.t('num_thread (Ollama)')}</div>
+
+				<button
+					class="p-1 px-3 text-xs flex rounded transition"
+					type="button"
+					on:click={() => {
+						params.num_thread = (params?.num_thread ?? null) === null ? 2 : null;
+					}}
+				>
+					{#if (params?.num_thread ?? null) === null}
+						<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					{:else}
+						<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
+					{/if}
+				</button>
+			</div>
+
+			{#if (params?.num_thread ?? null) !== null}
+				<div class="flex mt-0.5 space-x-2">
+					<div class=" flex-1">
+						<input
+							id="steps-range"
+							type="range"
+							min="1"
+							max="256"
+							step="1"
+							bind:value={params.num_thread}
+							class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
+						/>
+					</div>
+					<div class="">
+						<input
+							bind:value={params.num_thread}
+							type="number"
+							class=" bg-transparent text-center w-14"
+							min="1"
+							max="256"
+							step="1"
+						/>
+					</div>
+				</div>
+			{/if}
+		</div>
+
+		<!-- <div class=" py-0.5 w-full justify-between">
+			<div class="flex w-full justify-between">
+				<div class=" self-center text-xs font-medium">{$i18n.t('Template')}</div>
+
+				<button
+					class="p-1 px-3 text-xs flex rounded transition"
+					type="button"
+					on:click={() => {
+						params.template = (params?.template ?? null) === null ? '' : null;
+					}}
+				>
+					{#if (params?.template ?? null) === null}
+						<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					{:else}
+						<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
+					{/if}
+				</button>
+			</div>
+
+			{#if (params?.template ?? null) !== null}
+				<div class="flex mt-0.5 space-x-2">
+					<div class=" flex-1">
+						<textarea
+							class="px-3 py-1.5 text-sm w-full bg-transparent border dark:border-gray-600 outline-none rounded-lg -mb-1"
+							placeholder="Write your model template content here"
+							rows="4"
+							bind:value={params.template}
+						/>
+					</div>
+				</div>
+			{/if}
+		</div> -->
+	{/if}
 </div>

src/lib/components/chat/Settings/Audio.svelte

@@ -1,6 +1,5 @@
 <script lang="ts">
-	import { getAudioConfig, updateAudioConfig } from '$lib/apis/audio';
-	import { user, settings } from '$lib/stores';
+	import { user, settings, config } from '$lib/stores';
 	import { createEventDispatcher, onMount, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';
 	import Switch from '$lib/components/common/Switch.svelte';
@@ -11,26 +10,15 @@
 	export let saveSettings: Function;
 
 	// Audio
-
-	let OpenAIUrl = '';
-	let OpenAIKey = '';
-	let OpenAISpeaker = '';
-
-	let STTEngines = ['', 'openai'];
-	let STTEngine = '';
-
 	let conversationMode = false;
 	let speechAutoSend = false;
 	let responseAutoPlayback = false;
 	let nonLocalVoices = false;
 
-	let TTSEngines = ['', 'openai'];
-	let TTSEngine = '';
+	let STTEngine = '';
 
 	let voices = [];
-	let speaker = '';
-	let models = [];
-	let model = '';
+	let voice = '';
 
 	const getOpenAIVoices = () => {
 		voices = [
@@ -43,10 +31,6 @@
 		];
 	};
 
-	const getOpenAIVoicesModel = () => {
-		models = [{ name: 'tts-1' }, { name: 'tts-1-hd' }];
-	};
-
 	const getWebAPIVoices = () => {
 		const getVoicesLoop = setInterval(async () => {
 			voices = await speechSynthesis.getVoices();
@@ -58,21 +42,6 @@
 		}, 100);
 	};
 
-	const toggleConversationMode = async () => {
-		conversationMode = !conversationMode;
-
-		if (conversationMode) {
-			responseAutoPlayback = true;
-			speechAutoSend = true;
-		}
-
-		saveSettings({
-			conversationMode: conversationMode,
-			responseAutoPlayback: responseAutoPlayback,
-			speechAutoSend: speechAutoSend
-		});
-	};
-
 	const toggleResponseAutoPlayback = async () => {
 		responseAutoPlayback = !responseAutoPlayback;
 		saveSettings({ responseAutoPlayback: responseAutoPlayback });
@@ -83,76 +52,35 @@
 		saveSettings({ speechAutoSend: speechAutoSend });
 	};
 
-	const updateConfigHandler = async () => {
-		if (TTSEngine === 'openai') {
-			const res = await updateAudioConfig(localStorage.token, {
-				url: OpenAIUrl,
-				key: OpenAIKey,
-				model: model,
-				speaker: OpenAISpeaker
-			});
-
-			if (res) {
-				OpenAIUrl = res.OPENAI_API_BASE_URL;
-				OpenAIKey = res.OPENAI_API_KEY;
-				model = res.OPENAI_API_MODEL;
-				OpenAISpeaker = res.OPENAI_API_VOICE;
-			}
-		}
-	};
-
 	onMount(async () => {
 		conversationMode = $settings.conversationMode ?? false;
 		speechAutoSend = $settings.speechAutoSend ?? false;
 		responseAutoPlayback = $settings.responseAutoPlayback ?? false;
 
-		STTEngine = $settings?.audio?.STTEngine ?? '';
-		TTSEngine = $settings?.audio?.TTSEngine ?? '';
-		nonLocalVoices = $settings.audio?.nonLocalVoices ?? false;
-		speaker = $settings?.audio?.speaker ?? '';
-		model = $settings?.audio?.model ?? '';
+		STTEngine = $settings?.audio?.stt?.engine ?? '';
+		voice = $settings?.audio?.tts?.voice ?? $config.audio.tts.voice ?? '';
+		nonLocalVoices = $settings.audio?.tts?.nonLocalVoices ?? false;
 
-		if (TTSEngine === 'openai') {
+		if ($config.audio.tts.engine === 'openai') {
 			getOpenAIVoices();
-			getOpenAIVoicesModel();
 		} else {
 			getWebAPIVoices();
 		}
-
-		if ($user.role === 'admin') {
-			const res = await getAudioConfig(localStorage.token);
-
-			if (res) {
-				OpenAIUrl = res.OPENAI_API_BASE_URL;
-				OpenAIKey = res.OPENAI_API_KEY;
-				model = res.OPENAI_API_MODEL;
-				OpenAISpeaker = res.OPENAI_API_VOICE;
-				if (TTSEngine === 'openai') {
-					speaker = OpenAISpeaker;
-				}
-			}
-		}
 	});
 </script>
 
 <form
 	class="flex flex-col h-full justify-between space-y-3 text-sm"
 	on:submit|preventDefault={async () => {
-		if ($user.role === 'admin') {
-			await updateConfigHandler();
-		}
 		saveSettings({
 			audio: {
-				STTEngine: STTEngine !== '' ? STTEngine : undefined,
-				TTSEngine: TTSEngine !== '' ? TTSEngine : undefined,
-				speaker:
-					(TTSEngine === 'openai' ? OpenAISpeaker : speaker) !== ''
-						? TTSEngine === 'openai'
-							? OpenAISpeaker
-							: speaker
-						: undefined,
-				model: model !== '' ? model : undefined,
-				nonLocalVoices: nonLocalVoices
+				stt: {
+					engine: STTEngine !== '' ? STTEngine : undefined
+				},
+				tts: {
+					voice: voice !== '' ? voice : undefined,
+					nonLocalVoices: $config.audio.tts.engine === '' ? nonLocalVoices : undefined
+				}
 			}
 		});
 		dispatch('save');
@@ -162,53 +90,25 @@
 		<div>
 			<div class=" mb-1 text-sm font-medium">{$i18n.t('STT Settings')}</div>
 
-			<div class=" py-0.5 flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">{$i18n.t('Speech-to-Text Engine')}</div>
-				<div class="flex items-center relative">
-					<select
-						class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
-						bind:value={STTEngine}
-						placeholder="Select a mode"
-						on:change={(e) => {
-							if (e.target.value !== '') {
-								navigator.mediaDevices.getUserMedia({ audio: true }).catch(function (err) {
-									toast.error(
-										$i18n.t(`Permission denied when accessing microphone: {{error}}`, {
-											error: err
-										})
-									);
-									STTEngine = '';
-								});
-							}
-						}}
-					>
-						<option value="">{$i18n.t('Default (Web API)')}</option>
-						<option value="whisper-local">{$i18n.t('Whisper (Local)')}</option>
-					</select>
+			{#if $config.audio.stt.engine !== 'web'}
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs font-medium">{$i18n.t('Speech-to-Text Engine')}</div>
+					<div class="flex items-center relative">
+						<select
+							class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
+							bind:value={STTEngine}
+							placeholder="Select an engine"
+						>
+							<option value="">{$i18n.t('Default')}</option>
+							<option value="web">{$i18n.t('Web API')}</option>
+						</select>
+					</div>
 				</div>
-			</div>
-
-			<div class=" py-0.5 flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">{$i18n.t('Conversation Mode')}</div>
-
-				<button
-					class="p-1 px-3 text-xs flex rounded transition"
-					on:click={() => {
-						toggleConversationMode();
-					}}
-					type="button"
-				>
-					{#if conversationMode === true}
-						<span class="ml-2 self-center">{$i18n.t('On')}</span>
-					{:else}
-						<span class="ml-2 self-center">{$i18n.t('Off')}</span>
-					{/if}
-				</button>
-			</div>
+			{/if}
 
 			<div class=" py-0.5 flex w-full justify-between">
 				<div class=" self-center text-xs font-medium">
-					{$i18n.t('Auto-send input after 3 sec.')}
+					{$i18n.t('Instant Auto-Send After Voice Transcription')}
 				</div>
 
 				<button
@@ -230,50 +130,6 @@
 		<div>
 			<div class=" mb-1 text-sm font-medium">{$i18n.t('TTS Settings')}</div>
 
-			<div class=" py-0.5 flex w-full justify-between">
-				<div class=" self-center text-xs font-medium">{$i18n.t('Text-to-Speech Engine')}</div>
-				<div class="flex items-center relative">
-					<select
-						class=" dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
-						bind:value={TTSEngine}
-						placeholder="Select a mode"
-						on:change={(e) => {
-							if (e.target.value === 'openai') {
-								getOpenAIVoices();
-								OpenAISpeaker = 'alloy';
-								model = 'tts-1';
-							} else {
-								getWebAPIVoices();
-								speaker = '';
-							}
-						}}
-					>
-						<option value="">{$i18n.t('Default (Web API)')}</option>
-						<option value="openai">{$i18n.t('Open AI')}</option>
-					</select>
-				</div>
-			</div>
-
-			{#if $user.role === 'admin'}
-				{#if TTSEngine === 'openai'}
-					<div class="mt-1 flex gap-2 mb-1">
-						<input
-							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							placeholder={$i18n.t('API Base URL')}
-							bind:value={OpenAIUrl}
-							required
-						/>
-
-						<input
-							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							placeholder={$i18n.t('API Key')}
-							bind:value={OpenAIKey}
-							required
-						/>
-					</div>
-				{/if}
-			{/if}
-
 			<div class=" py-0.5 flex w-full justify-between">
 				<div class=" self-center text-xs font-medium">{$i18n.t('Auto-playback response')}</div>
 
@@ -293,30 +149,30 @@
 			</div>
 		</div>
 
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
 
-		{#if TTSEngine === ''}
+		{#if $config.audio.tts.engine === ''}
 			<div>
 				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Voice')}</div>
 				<div class="flex w-full">
 					<div class="flex-1">
 						<select
 							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							bind:value={speaker}
+							bind:value={voice}
 						>
-							<option value="" selected={speaker !== ''}>{$i18n.t('Default')}</option>
-							{#each voices.filter((v) => nonLocalVoices || v.localService === true) as voice}
+							<option value="" selected={voice !== ''}>{$i18n.t('Default')}</option>
+							{#each voices.filter((v) => nonLocalVoices || v.localService === true) as _voice}
 								<option
-									value={voice.name}
+									value={_voice.name}
 									class="bg-gray-100 dark:bg-gray-700"
-									selected={speaker === voice.name}>{voice.name}</option
+									selected={voice === _voice.name}>{_voice.name}</option
 								>
 							{/each}
 						</select>
 					</div>
 				</div>
-				<div class="flex items-center justify-between mb-1">
-					<div class="text-sm">
+				<div class="flex items-center justify-between my-1.5">
+					<div class="text-xs">
 						{$i18n.t('Allow non-local voices')}
 					</div>
 
@@ -325,7 +181,7 @@
 					</div>
 				</div>
 			</div>
-		{:else if TTSEngine === 'openai'}
+		{:else if $config.audio.tts.engine === 'openai'}
 			<div>
 				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Voice')}</div>
 				<div class="flex w-full">
@@ -333,7 +189,7 @@
 						<input
 							list="voice-list"
 							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							bind:value={OpenAISpeaker}
+							bind:value={voice}
 							placeholder="Select a voice"
 						/>
 
@@ -345,25 +201,6 @@
 					</div>
 				</div>
 			</div>
-			<div>
-				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Set Model')}</div>
-				<div class="flex w-full">
-					<div class="flex-1">
-						<input
-							list="model-list"
-							class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-							bind:value={model}
-							placeholder="Select a model"
-						/>
-
-						<datalist id="model-list">
-							{#each models as model}
-								<option value={model.name} />
-							{/each}
-						</datalist>
-					</div>
-				</div>
-			</div>
 		{/if}
 	</div>
 

src/lib/components/chat/Settings/Chats.svelte

@@ -161,7 +161,7 @@
 			</div>
 		</div>
 
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
 
 		<div class="flex flex-col">
 			<input
@@ -218,7 +218,7 @@
 			</button>
 		</div>
 
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
 
 		<div class="flex flex-col">
 			{#if showArchiveConfirm}

src/lib/components/chat/Settings/General.svelte

@@ -4,7 +4,7 @@
 	import { getLanguages } from '$lib/i18n';
 	const dispatch = createEventDispatcher();
 
-	import { models, settings, theme } from '$lib/stores';
+	import { models, settings, theme, user } from '$lib/stores';
 
 	const i18n = getContext('i18n');
 
@@ -43,19 +43,19 @@
 
 	let params = {
 		// Advanced
-		seed: 0,
-		temperature: '',
-		frequency_penalty: '',
-		repeat_last_n: '',
-		mirostat: '',
-		mirostat_eta: '',
-		mirostat_tau: '',
-		top_k: '',
-		top_p: '',
+		seed: null,
+		temperature: null,
+		frequency_penalty: null,
+		repeat_last_n: null,
+		mirostat: null,
+		mirostat_eta: null,
+		mirostat_tau: null,
+		top_k: null,
+		top_p: null,
 		stop: null,
-		tfs_z: '',
-		num_ctx: '',
-		max_tokens: ''
+		tfs_z: null,
+		num_ctx: null,
+		max_tokens: null
 	};
 
 	const toggleRequestFormat = async () => {
@@ -79,12 +79,6 @@
 		requestFormat = $settings.requestFormat ?? '';
 		keepAlive = $settings.keepAlive ?? null;
 
-		params.seed = $settings.seed ?? 0;
-		params.temperature = $settings.temperature ?? '';
-		params.frequency_penalty = $settings.frequency_penalty ?? '';
-		params.top_k = $settings.top_k ?? '';
-		params.top_p = $settings.top_p ?? '';
-		params.num_ctx = $settings.num_ctx ?? '';
 		params = { ...params, ...$settings.params };
 		params.stop = $settings?.params?.stop ? ($settings?.params?.stop ?? []).join(',') : null;
 	});
@@ -203,7 +197,7 @@
 			</div>
 		</div>
 
-		<hr class=" dark:border-gray-700 my-3" />
+		<hr class=" dark:border-gray-850 my-3" />
 
 		<div>
 			<div class=" my-2.5 text-sm font-medium">{$i18n.t('System Prompt')}</div>
@@ -227,8 +221,8 @@
 			</div>
 
 			{#if showAdvanced}
-				<AdvancedParams bind:params />
-				<hr class=" dark:border-gray-700" />
+				<AdvancedParams admin={$user?.role === 'admin'} bind:params />
+				<hr class=" dark:border-gray-850" />
 
 				<div class=" py-1 w-full justify-between">
 					<div class="flex w-full justify-between">
@@ -300,20 +294,23 @@
 				saveSettings({
 					system: system !== '' ? system : undefined,
 					params: {
-						seed: (params.seed !== 0 ? params.seed : undefined) ?? undefined,
+						seed: (params.seed !== null ? params.seed : undefined) ?? undefined,
 						stop: params.stop ? params.stop.split(',').filter((e) => e) : undefined,
-						temperature: params.temperature !== '' ? params.temperature : undefined,
+						temperature: params.temperature !== null ? params.temperature : undefined,
 						frequency_penalty:
-							params.frequency_penalty !== '' ? params.frequency_penalty : undefined,
-						repeat_last_n: params.repeat_last_n !== '' ? params.repeat_last_n : undefined,
-						mirostat: params.mirostat !== '' ? params.mirostat : undefined,
-						mirostat_eta: params.mirostat_eta !== '' ? params.mirostat_eta : undefined,
-						mirostat_tau: params.mirostat_tau !== '' ? params.mirostat_tau : undefined,
-						top_k: params.top_k !== '' ? params.top_k : undefined,
-						top_p: params.top_p !== '' ? params.top_p : undefined,
-						tfs_z: params.tfs_z !== '' ? params.tfs_z : undefined,
-						num_ctx: params.num_ctx !== '' ? params.num_ctx : undefined,
-						max_tokens: params.max_tokens !== '' ? params.max_tokens : undefined
+							params.frequency_penalty !== null ? params.frequency_penalty : undefined,
+						repeat_last_n: params.repeat_last_n !== null ? params.repeat_last_n : undefined,
+						mirostat: params.mirostat !== null ? params.mirostat : undefined,
+						mirostat_eta: params.mirostat_eta !== null ? params.mirostat_eta : undefined,
+						mirostat_tau: params.mirostat_tau !== null ? params.mirostat_tau : undefined,
+						top_k: params.top_k !== null ? params.top_k : undefined,
+						top_p: params.top_p !== null ? params.top_p : undefined,
+						tfs_z: params.tfs_z !== null ? params.tfs_z : undefined,
+						num_ctx: params.num_ctx !== null ? params.num_ctx : undefined,
+						max_tokens: params.max_tokens !== null ? params.max_tokens : undefined,
+						use_mmap: params.use_mmap !== null ? params.use_mmap : undefined,
+						use_mlock: params.use_mlock !== null ? params.use_mlock : undefined,
+						num_thread: params.num_thread !== null ? params.num_thread : undefined
 					},
 					keepAlive: keepAlive ? (isNaN(keepAlive) ? keepAlive : parseInt(keepAlive)) : undefined
 				});

src/lib/components/chat/Settings/Interface.svelte

@@ -14,14 +14,11 @@
 	// Addons
 	let titleAutoGenerate = true;
 	let responseAutoCopy = false;
-	let titleAutoGenerateModel = '';
-	let titleAutoGenerateModelExternal = '';
-	let fullScreenMode = false;
-	let titleGenerationPrompt = '';
+	let widescreenMode = false;
 	let splitLargeChunks = false;
 
 	// Interface
-	let promptSuggestions = [];
+	let defaultModelId = '';
 	let showUsername = false;
 	let chatBubble = true;
 	let chatDirection: 'LTR' | 'RTL' = 'LTR';
@@ -31,9 +28,9 @@
 		saveSettings({ splitLargeChunks: splitLargeChunks });
 	};
 
-	const toggleFullScreenMode = async () => {
-		fullScreenMode = !fullScreenMode;
-		saveSettings({ fullScreenMode: fullScreenMode });
+	const togglewidescreenMode = async () => {
+		widescreenMode = !widescreenMode;
+		saveSettings({ widescreenMode: widescreenMode });
 	};
 
 	const toggleChatBubble = async () => {
@@ -84,39 +81,21 @@
 	};
 
 	const updateInterfaceHandler = async () => {
-		if ($user.role === 'admin') {
-			promptSuggestions = await setDefaultPromptSuggestions(localStorage.token, promptSuggestions);
-			await config.set(await getBackendConfig());
-		}
-
 		saveSettings({
-			title: {
-				...$settings.title,
-				model: titleAutoGenerateModel !== '' ? titleAutoGenerateModel : undefined,
-				modelExternal:
-					titleAutoGenerateModelExternal !== '' ? titleAutoGenerateModelExternal : undefined,
-				prompt: titleGenerationPrompt ? titleGenerationPrompt : undefined
-			}
+			models: [defaultModelId]
 		});
 	};
 
 	onMount(async () => {
-		if ($user.role === 'admin') {
-			promptSuggestions = $config?.default_prompt_suggestions;
-		}
-
 		titleAutoGenerate = $settings?.title?.auto ?? true;
-		titleAutoGenerateModel = $settings?.title?.model ?? '';
-		titleAutoGenerateModelExternal = $settings?.title?.modelExternal ?? '';
-		titleGenerationPrompt =
-			$settings?.title?.prompt ??
-			`Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title': {{prompt}}`;
 		responseAutoCopy = $settings.responseAutoCopy ?? false;
 		showUsername = $settings.showUsername ?? false;
 		chatBubble = $settings.chatBubble ?? true;
-		fullScreenMode = $settings.fullScreenMode ?? false;
+		widescreenMode = $settings.widescreenMode ?? false;
 		splitLargeChunks = $settings.splitLargeChunks ?? false;
 		chatDirection = $settings.chatDirection ?? 'LTR';
+
+		defaultModelId = ($settings?.models ?? ['']).at(0);
 	});
 </script>
 
@@ -195,16 +174,16 @@
 
 			<div>
 				<div class=" py-0.5 flex w-full justify-between">
-					<div class=" self-center text-xs font-medium">{$i18n.t('Full Screen Mode')}</div>
+					<div class=" self-center text-xs font-medium">{$i18n.t('Widescreen Mode')}</div>
 
 					<button
 						class="p-1 px-3 text-xs flex rounded transition"
 						on:click={() => {
-							toggleFullScreenMode();
+							togglewidescreenMode();
 						}}
 						type="button"
 					>
-						{#if fullScreenMode === true}
+						{#if widescreenMode === true}
 							<span class="ml-2 self-center">{$i18n.t('On')}</span>
 						{:else}
 							<span class="ml-2 self-center">{$i18n.t('Off')}</span>
@@ -278,161 +257,28 @@
 			</div>
 		</div>
 
-		<hr class=" dark:border-gray-700" />
+		<hr class=" dark:border-gray-850" />
 
-		<div>
-			<div class=" mb-2.5 text-sm font-medium flex">
-				<div class=" mr-1">{$i18n.t('Set Task Model')}</div>
-				<Tooltip
-					content={$i18n.t(
-						'A task model is used when performing tasks such as generating titles for chats and web search queries'
-					)}
+		<div class=" space-y-1 mb-3">
+			<div class="mb-2">
+				<div class="flex justify-between items-center text-xs">
+					<div class=" text-xs font-medium">{$i18n.t('Default Model')}</div>
+				</div>
+			</div>
+
+			<div class="flex-1 mr-2">
+				<select
+					class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+					bind:value={defaultModelId}
+					placeholder="Select a model"
 				>
-					<svg
-						xmlns="http://www.w3.org/2000/svg"
-						fill="none"
-						viewBox="0 0 24 24"
-						stroke-width="1.5"
-						stroke="currentColor"
-						class="w-5 h-5"
-					>
-						<path
-							stroke-linecap="round"
-							stroke-linejoin="round"
-							d="m11.25 11.25.041-.02a.75.75 0 0 1 1.063.852l-.708 2.836a.75.75 0 0 0 1.063.853l.041-.021M21 12a9 9 0 1 1-18 0 9 9 0 0 1 18 0Zm-9-3.75h.008v.008H12V8.25Z"
-						/>
-					</svg>
-				</Tooltip>
-			</div>
-			<div class="flex w-full gap-2 pr-2">
-				<div class="flex-1">
-					<div class=" text-xs mb-1">Local Models</div>
-					<select
-						class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-						bind:value={titleAutoGenerateModel}
-						placeholder={$i18n.t('Select a model')}
-					>
-						<option value="" selected>{$i18n.t('Current Model')}</option>
-						{#each $models.filter((m) => m.owned_by === 'ollama') as model}
-							<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
-								{model.name}
-							</option>
-						{/each}
-					</select>
-				</div>
-
-				<div class="flex-1">
-					<div class=" text-xs mb-1">External Models</div>
-					<select
-						class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
-						bind:value={titleAutoGenerateModelExternal}
-						placeholder={$i18n.t('Select a model')}
-					>
-						<option value="" selected>{$i18n.t('Current Model')}</option>
-						{#each $models as model}
-							<option value={model.id} class="bg-gray-100 dark:bg-gray-700">
-								{model.name}
-							</option>
-						{/each}
-					</select>
-				</div>
-			</div>
-
-			<div class="mt-3 mr-2">
-				<div class=" mb-2.5 text-sm font-medium">{$i18n.t('Title Generation Prompt')}</div>
-				<textarea
-					bind:value={titleGenerationPrompt}
-					class="w-full rounded-lg p-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none resize-none"
-					rows="3"
-				/>
+					<option value="" disabled selected>{$i18n.t('Select a model')}</option>
+					{#each $models.filter((model) => model.id) as model}
+						<option value={model.id} class="bg-gray-100 dark:bg-gray-700">{model.name}</option>
+					{/each}
+				</select>
 			</div>
 		</div>
-
-		{#if $user.role === 'admin'}
-			<hr class=" dark:border-gray-700" />
-
-			<div class=" space-y-3 pr-1.5">
-				<div class="flex w-full justify-between mb-2">
-					<div class=" self-center text-sm font-semibold">
-						{$i18n.t('Default Prompt Suggestions')}
-					</div>
-
-					<button
-						class="p-1 px-3 text-xs flex rounded transition"
-						type="button"
-						on:click={() => {
-							if (promptSuggestions.length === 0 || promptSuggestions.at(-1).content !== '') {
-								promptSuggestions = [...promptSuggestions, { content: '', title: ['', ''] }];
-							}
-						}}
-					>
-						<svg
-							xmlns="http://www.w3.org/2000/svg"
-							viewBox="0 0 20 20"
-							fill="currentColor"
-							class="w-4 h-4"
-						>
-							<path
-								d="M10.75 4.75a.75.75 0 00-1.5 0v4.5h-4.5a.75.75 0 000 1.5h4.5v4.5a.75.75 0 001.5 0v-4.5h4.5a.75.75 0 000-1.5h-4.5v-4.5z"
-							/>
-						</svg>
-					</button>
-				</div>
-				<div class="flex flex-col space-y-1">
-					{#each promptSuggestions as prompt, promptIdx}
-						<div class=" flex border dark:border-gray-600 rounded-lg">
-							<div class="flex flex-col flex-1">
-								<div class="flex border-b dark:border-gray-600 w-full">
-									<input
-										class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r dark:border-gray-600"
-										placeholder={$i18n.t('Title (e.g. Tell me a fun fact)')}
-										bind:value={prompt.title[0]}
-									/>
-
-									<input
-										class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r dark:border-gray-600"
-										placeholder={$i18n.t('Subtitle (e.g. about the Roman Empire)')}
-										bind:value={prompt.title[1]}
-									/>
-								</div>
-
-								<input
-									class="px-3 py-1.5 text-xs w-full bg-transparent outline-none border-r dark:border-gray-600"
-									placeholder={$i18n.t('Prompt (e.g. Tell me a fun fact about the Roman Empire)')}
-									bind:value={prompt.content}
-								/>
-							</div>
-
-							<button
-								class="px-2"
-								type="button"
-								on:click={() => {
-									promptSuggestions.splice(promptIdx, 1);
-									promptSuggestions = promptSuggestions;
-								}}
-							>
-								<svg
-									xmlns="http://www.w3.org/2000/svg"
-									viewBox="0 0 20 20"
-									fill="currentColor"
-									class="w-4 h-4"
-								>
-									<path
-										d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
-									/>
-								</svg>
-							</button>
-						</div>
-					{/each}
-				</div>
-
-				{#if promptSuggestions.length > 0}
-					<div class="text-xs text-left w-full mt-2">
-						{$i18n.t('Adjusting these settings will apply changes universally to all users.')}
-					</div>
-				{/if}
-			</div>
-		{/if}
 	</div>
 
 	<div class="flex justify-end text-sm font-medium">

src/lib/components/chat/Settings/Models.svelte

@@ -43,6 +43,13 @@
 
 	let modelTransferring = false;
 	let modelTag = '';
+
+	let createModelLoading = false;
+	let createModelTag = '';
+	let createModelContent = '';
+	let createModelDigest = '';
+	let createModelPullProgress = null;
+
 	let digest = '';
 	let pullProgress = null;
 
@@ -434,6 +441,83 @@
 		}
 	};
 
+	const createModelHandler = async () => {
+		createModelLoading = true;
+		const res = await createModel(
+			localStorage.token,
+			createModelTag,
+			createModelContent,
+			selectedOllamaUrlIdx
+		).catch((error) => {
+			toast.error(error);
+			return null;
+		});
+
+		if (res && res.ok) {
+			const reader = res.body
+				.pipeThrough(new TextDecoderStream())
+				.pipeThrough(splitStream('\n'))
+				.getReader();
+
+			while (true) {
+				const { value, done } = await reader.read();
+				if (done) break;
+
+				try {
+					let lines = value.split('\n');
+
+					for (const line of lines) {
+						if (line !== '') {
+							console.log(line);
+							let data = JSON.parse(line);
+							console.log(data);
+
+							if (data.error) {
+								throw data.error;
+							}
+							if (data.detail) {
+								throw data.detail;
+							}
+
+							if (data.status) {
+								if (
+									!data.digest &&
+									!data.status.includes('writing') &&
+									!data.status.includes('sha256')
+								) {
+									toast.success(data.status);
+								} else {
+									if (data.digest) {
+										createModelDigest = data.digest;
+
+										if (data.completed) {
+											createModelPullProgress =
+												Math.round((data.completed / data.total) * 1000) / 10;
+										} else {
+											createModelPullProgress = 100;
+										}
+									}
+								}
+							}
+						}
+					}
+				} catch (error) {
+					console.log(error);
+					toast.error(error);
+				}
+			}
+		}
+
+		models.set(await getModels());
+
+		createModelLoading = false;
+
+		createModelTag = '';
+		createModelContent = '';
+		createModelDigest = '';
+		createModelPullProgress = null;
+	};
+
 	onMount(async () => {
 		const ollamaConfig = await getOllamaConfig(localStorage.token);
 
@@ -457,13 +541,13 @@
 			]);
 		} else {
 			ollamaEnabled = false;
-			toast.error('Ollama API is disabled');
+			toast.error($i18n.t('Ollama API is disabled'));
 		}
 	});
 </script>
 
 <div class="flex flex-col h-full justify-between text-sm">
-	<div class=" space-y-3 pr-1.5 overflow-y-scroll h-[24rem]">
+	<div class=" space-y-3 pr-1.5 overflow-y-scroll max-h-[27rem]">
 		{#if ollamaEnabled}
 			{#if ollamaVersion !== null}
 				<div class="space-y-2 pr-1.5">
@@ -695,6 +779,77 @@
 							</div>
 						</div>
 
+						<div>
+							<div class=" mb-2 text-sm font-medium">{$i18n.t('Create a model')}</div>
+							<div class="flex w-full">
+								<div class="flex-1 mr-2 flex flex-col gap-2">
+									<input
+										class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+										placeholder={$i18n.t('Enter model tag (e.g. {{modelTag}})', {
+											modelTag: 'my-modelfile'
+										})}
+										bind:value={createModelTag}
+										disabled={createModelLoading}
+									/>
+
+									<textarea
+										bind:value={createModelContent}
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-100 dark:text-gray-100 dark:bg-gray-850 outline-none resize-none scrollbar-hidden"
+										rows="6"
+										placeholder={`TEMPLATE """{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: """\nPARAMETER num_ctx 4096\nPARAMETER stop "</s>"\nPARAMETER stop "USER:"\nPARAMETER stop "ASSISTANT:"`}
+										disabled={createModelLoading}
+									/>
+								</div>
+
+								<div class="flex self-start">
+									<button
+										class="px-2.5 py-2.5 bg-gray-100 hover:bg-gray-200 text-gray-800 dark:bg-gray-850 dark:hover:bg-gray-800 dark:text-gray-100 rounded-lg transition disabled:cursor-not-allowed"
+										on:click={() => {
+											createModelHandler();
+										}}
+										disabled={createModelLoading}
+									>
+										<svg
+											xmlns="http://www.w3.org/2000/svg"
+											viewBox="0 0 16 16"
+											fill="currentColor"
+											class="size-4"
+										>
+											<path
+												d="M7.25 10.25a.75.75 0 0 0 1.5 0V4.56l2.22 2.22a.75.75 0 1 0 1.06-1.06l-3.5-3.5a.75.75 0 0 0-1.06 0l-3.5 3.5a.75.75 0 0 0 1.06 1.06l2.22-2.22v5.69Z"
+											/>
+											<path
+												d="M3.5 9.75a.75.75 0 0 0-1.5 0v1.5A2.75 2.75 0 0 0 4.75 14h6.5A2.75 2.75 0 0 0 14 11.25v-1.5a.75.75 0 0 0-1.5 0v1.5c0 .69-.56 1.25-1.25 1.25h-6.5c-.69 0-1.25-.56-1.25-1.25v-1.5Z"
+											/>
+										</svg>
+									</button>
+								</div>
+							</div>
+
+							{#if createModelDigest !== ''}
+								<div class="flex flex-col mt-1">
+									<div class="font-medium mb-1">{createModelTag}</div>
+									<div class="">
+										<div class="flex flex-row justify-between space-x-4 pr-2">
+											<div class=" flex-1">
+												<div
+													class="dark:bg-gray-600 bg-gray-500 text-xs font-medium text-gray-100 text-center p-0.5 leading-none rounded-full"
+													style="width: {Math.max(15, createModelPullProgress ?? 0)}%"
+												>
+													{createModelPullProgress ?? 0}%
+												</div>
+											</div>
+										</div>
+										{#if createModelDigest}
+											<div class="mt-1 text-xs dark:text-gray-500" style="font-size: 0.5rem;">
+												{createModelDigest}
+											</div>
+										{/if}
+									</div>
+								</div>
+							{/if}
+						</div>
+
 						<div class="pt-1">
 							<div class="flex justify-between items-center text-xs">
 								<div class=" text-sm font-medium">{$i18n.t('Experimental')}</div>
@@ -908,7 +1063,7 @@
 				</div>
 			{/if}
 		{:else if ollamaEnabled === false}
-			<div>Ollama API is disabled</div>
+			<div>{$i18n.t('Ollama API is disabled')}</div>
 		{:else}
 			<div class="flex h-full justify-center">
 				<div class="my-auto">

src/lib/components/chat/Settings/Personalization.svelte

@@ -35,7 +35,9 @@
 		<div>
 			<div class="flex items-center justify-between mb-1">
 				<Tooltip
-					content="This is an experimental feature, it may not function as expected and is subject to change at any time."
+					content={$i18n.t(
+						'This is an experimental feature, it may not function as expected and is subject to change at any time.'
+					)}
 				>
 					<div class="text-sm font-medium">
 						{$i18n.t('Memory')}
@@ -57,8 +59,9 @@
 
 		<div class="text-xs text-gray-600 dark:text-gray-400">
 			<div>
-				You can personalize your interactions with LLMs by adding memories through the 'Manage'
-				button below, making them more helpful and tailored to you.
+				{$i18n.t(
+					"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you."
+				)}
 			</div>
 
 			<!-- <div class="mt-3">
@@ -79,7 +82,7 @@
 					showManageModal = true;
 				}}
 			>
-				Manage
+				{$i18n.t('Manage')}
 			</button>
 		</div>
 	</div>

src/lib/components/chat/Settings/Personalization/AddMemoryModal.svelte

@@ -75,7 +75,7 @@
 						/>
 
 						<div class="text-xs text-gray-500">
-							ⓘ Refer to yourself as "User" (e.g., "User is learning Spanish")
+							ⓘ {$i18n.t('Refer to yourself as "User" (e.g., "User is learning Spanish")')}
 						</div>
 					</div>
 

src/lib/components/chat/Settings/Personalization/ManageModal.svelte

@@ -136,7 +136,7 @@
 					class=" px-3.5 py-1.5 font-medium hover:bg-black/5 dark:hover:bg-white/5 outline outline-1 outline-gray-300 dark:outline-gray-800 rounded-3xl"
 					on:click={() => {
 						showAddMemoryModal = true;
-					}}>Add memory</button
+					}}>{$i18n.t('Add Memory')}</button
 				>
 				<button
 					class=" px-3.5 py-1.5 font-medium text-red-500 hover:bg-black/5 dark:hover:bg-white/5 outline outline-1 outline-red-300 dark:outline-red-800 rounded-3xl"
@@ -150,7 +150,7 @@
 							toast.success('Memory cleared successfully');
 							memories = [];
 						}
-					}}>Clear memory</button
+					}}>{$i18n.t('Clear memory')}</button
 				>
 			</div>
 		</div>

src/lib/components/chat/SettingsModal.svelte

@@ -8,16 +8,14 @@
 	import Modal from '../common/Modal.svelte';
 	import Account from './Settings/Account.svelte';
 	import About from './Settings/About.svelte';
-	import Models from './Settings/Models.svelte';
 	import General from './Settings/General.svelte';
 	import Interface from './Settings/Interface.svelte';
 	import Audio from './Settings/Audio.svelte';
 	import Chats from './Settings/Chats.svelte';
-	import Connections from './Settings/Connections.svelte';
-	import Images from './Settings/Images.svelte';
 	import User from '../icons/User.svelte';
 	import Personalization from './Settings/Personalization.svelte';
 	import { updateUserSettings } from '$lib/apis/users';
+	import { goto } from '$app/navigation';
 
 	const i18n = getContext('i18n');
 
@@ -90,55 +88,32 @@
 					<div class=" self-center">{$i18n.t('General')}</div>
 				</button>
 
-				{#if $user?.role === 'admin'}
+				{#if $user.role === 'admin'}
 					<button
 						class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-						'connections'
+						'admin'
 							? 'bg-gray-200 dark:bg-gray-700'
 							: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-						on:click={() => {
-							selectedTab = 'connections';
+						on:click={async () => {
+							await goto('/admin/settings');
+							show = false;
 						}}
 					>
 						<div class=" self-center mr-2">
 							<svg
 								xmlns="http://www.w3.org/2000/svg"
-								viewBox="0 0 16 16"
+								viewBox="0 0 24 24"
 								fill="currentColor"
-								class="w-4 h-4"
-							>
-								<path
-									d="M1 9.5A3.5 3.5 0 0 0 4.5 13H12a3 3 0 0 0 .917-5.857 2.503 2.503 0 0 0-3.198-3.019 3.5 3.5 0 0 0-6.628 2.171A3.5 3.5 0 0 0 1 9.5Z"
-								/>
-							</svg>
-						</div>
-						<div class=" self-center">{$i18n.t('Connections')}</div>
-					</button>
-
-					<button
-						class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-						'models'
-							? 'bg-gray-200 dark:bg-gray-700'
-							: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-						on:click={() => {
-							selectedTab = 'models';
-						}}
-					>
-						<div class=" self-center mr-2">
-							<svg
-								xmlns="http://www.w3.org/2000/svg"
-								viewBox="0 0 20 20"
-								fill="currentColor"
-								class="w-4 h-4"
+								class="size-4"
 							>
 								<path
 									fill-rule="evenodd"
-									d="M10 1c3.866 0 7 1.79 7 4s-3.134 4-7 4-7-1.79-7-4 3.134-4 7-4zm5.694 8.13c.464-.264.91-.583 1.306-.952V10c0 2.21-3.134 4-7 4s-7-1.79-7-4V8.178c.396.37.842.688 1.306.953C5.838 10.006 7.854 10.5 10 10.5s4.162-.494 5.694-1.37zM3 13.179V15c0 2.21 3.134 4 7 4s7-1.79 7-4v-1.822c-.396.37-.842.688-1.306.953-1.532.875-3.548 1.369-5.694 1.369s-4.162-.494-5.694-1.37A7.009 7.009 0 013 13.179z"
+									d="M4.5 3.75a3 3 0 0 0-3 3v10.5a3 3 0 0 0 3 3h15a3 3 0 0 0 3-3V6.75a3 3 0 0 0-3-3h-15Zm4.125 3a2.25 2.25 0 1 0 0 4.5 2.25 2.25 0 0 0 0-4.5Zm-3.873 8.703a4.126 4.126 0 0 1 7.746 0 .75.75 0 0 1-.351.92 7.47 7.47 0 0 1-3.522.877 7.47 7.47 0 0 1-3.522-.877.75.75 0 0 1-.351-.92ZM15 8.25a.75.75 0 0 0 0 1.5h3.75a.75.75 0 0 0 0-1.5H15ZM14.25 12a.75.75 0 0 1 .75-.75h3.75a.75.75 0 0 1 0 1.5H15a.75.75 0 0 1-.75-.75Zm.75 2.25a.75.75 0 0 0 0 1.5h3.75a.75.75 0 0 0 0-1.5H15Z"
 									clip-rule="evenodd"
 								/>
 							</svg>
 						</div>
-						<div class=" self-center">{$i18n.t('Models')}</div>
+						<div class=" self-center">{$i18n.t('Admin Settings')}</div>
 					</button>
 				{/if}
 
@@ -210,34 +185,6 @@
 					<div class=" self-center">{$i18n.t('Audio')}</div>
 				</button>
 
-				{#if $user.role === 'admin'}
-					<button
-						class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
-						'images'
-							? 'bg-gray-200 dark:bg-gray-700'
-							: ' hover:bg-gray-300 dark:hover:bg-gray-800'}"
-						on:click={() => {
-							selectedTab = 'images';
-						}}
-					>
-						<div class=" self-center mr-2">
-							<svg
-								xmlns="http://www.w3.org/2000/svg"
-								viewBox="0 0 16 16"
-								fill="currentColor"
-								class="w-4 h-4"
-							>
-								<path
-									fill-rule="evenodd"
-									d="M2 4a2 2 0 0 1 2-2h8a2 2 0 0 1 2 2v8a2 2 0 0 1-2 2H4a2 2 0 0 1-2-2V4Zm10.5 5.707a.5.5 0 0 0-.146-.353l-1-1a.5.5 0 0 0-.708 0L9.354 9.646a.5.5 0 0 1-.708 0L6.354 7.354a.5.5 0 0 0-.708 0l-2 2a.5.5 0 0 0-.146.353V12a.5.5 0 0 0 .5.5h8a.5.5 0 0 0 .5-.5V9.707ZM12 5a1 1 0 1 1-2 0 1 1 0 0 1 2 0Z"
-									clip-rule="evenodd"
-								/>
-							</svg>
-						</div>
-						<div class=" self-center">{$i18n.t('Images')}</div>
-					</button>
-				{/if}
-
 				<button
 					class="px-2.5 py-2.5 min-w-fit rounded-lg flex-1 md:flex-none flex text-right transition {selectedTab ===
 					'chats'
@@ -325,15 +272,6 @@
 							toast.success($i18n.t('Settings saved successfully!'));
 						}}
 					/>
-				{:else if selectedTab === 'models'}
-					<Models {getModels} />
-				{:else if selectedTab === 'connections'}
-					<Connections
-						{getModels}
-						on:save={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
 				{:else if selectedTab === 'interface'}
 					<Interface
 						{saveSettings}
@@ -355,13 +293,6 @@
 							toast.success($i18n.t('Settings saved successfully!'));
 						}}
 					/>
-				{:else if selectedTab === 'images'}
-					<Images
-						{saveSettings}
-						on:save={() => {
-							toast.success($i18n.t('Settings saved successfully!'));
-						}}
-					/>
 				{:else if selectedTab === 'chats'}
 					<Chats {saveSettings} />
 				{:else if selectedTab === 'account'}

src/lib/components/common/Banner.svelte

@@ -39,7 +39,7 @@
 {#if !dismissed}
 	{#if mounted}
 		<div
-			class=" top-0 left-0 right-0 p-2 mx-4 px-3 flex justify-center items-center relative rounded-xl border border-gray-50 dark:border-gray-850 text-gray-800 dark:text-gary-100 bg-white dark:bg-gray-900 backdrop-blur-xl z-40"
+			class=" top-0 left-0 right-0 p-2 mx-4 px-3 flex justify-center items-center relative rounded-xl border border-gray-50 dark:border-gray-850 text-gray-800 dark:text-gary-100 bg-white dark:bg-gray-900 backdrop-blur-xl z-30"
 			transition:fade={{ delay: 100, duration: 300 }}
 		>
 			<div class=" flex flex-col md:flex-row md:items-center flex-1 text-sm w-fit gap-1.5">

src/lib/components/common/Selector.svelte

@@ -48,7 +48,7 @@
 		<ChevronDown className="absolute end-2 top-1/2 -translate-y-[45%] size-3.5" strokeWidth="2.5" />
 	</Select.Trigger>
 	<Select.Content
-		class="w-full rounded-lg  bg-white dark:bg-gray-900 dark:text-white shadow-lg border border-gray-300/30 dark:border-gray-700/50  outline-none"
+		class="w-full rounded-lg  bg-white dark:bg-gray-900 dark:text-white shadow-lg border border-gray-300/30 dark:border-gray-850/50  outline-none"
 		transition={flyAndScale}
 		sideOffset={4}
 	>

src/lib/components/common/Tooltip.svelte

@@ -21,6 +21,10 @@
 				touch: touch
 			});
 		}
+	} else if (tooltipInstance && content === '') {
+		if (tooltipInstance) {
+			tooltipInstance.destroy();
+		}
 	}
 
 	onDestroy(() => {

src/lib/components/documents/Settings/QueryParams.svelte

@@ -95,7 +95,7 @@
 					)}
 				</div>
 
-				<hr class=" dark:border-gray-700 my-3" />
+				<hr class=" dark:border-gray-850 my-3" />
 			{/if}
 
 			<div>

src/lib/components/documents/Settings/WebParams.svelte

@@ -11,7 +11,7 @@
 	export let saveHandler: Function;
 
 	let webConfig = null;
-	let webSearchEngines = ['searxng', 'google_pse', 'brave', 'serpstack', 'serper'];
+	let webSearchEngines = ['searxng', 'google_pse', 'brave', 'serpstack', 'serper', 'serply'];
 
 	let youtubeLanguage = 'en';
 	let youtubeTranslation = null;
@@ -68,10 +68,10 @@
 						<select
 							class="dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
 							bind:value={webConfig.search.engine}
-							placeholder="Select a engine"
+							placeholder={$i18n.t('Select a engine')}
 							required
 						>
-							<option disabled selected value="">Select a engine</option>
+							<option disabled selected value="">{$i18n.t('Select a engine')}</option>
 							{#each webSearchEngines as engine}
 								<option value={engine}>{engine}</option>
 							{/each}

src/lib/components/icons/Headphone.svelte

@@ -0,0 +1,20 @@
+<script lang="ts">
+	export let className = 'w-4 h-4';
+	export let strokeWidth = '0';
+</script>
+
+<svg
+	aria-hidden="true"
+	xmlns="http://www.w3.org/2000/svg"
+	fill="currentColor"
+	viewBox="0 0 24 24"
+	stroke-width={strokeWidth}
+	stroke="currentColor"
+	class={className}
+>
+	<path
+		fill-rule="evenodd"
+		d="M12 5a7 7 0 0 0-7 7v1.17c.313-.11.65-.17 1-.17h2a1 1 0 0 1 1 1v6a1 1 0 0 1-1 1H6a3 3 0 0 1-3-3v-6a9 9 0 0 1 18 0v6a3 3 0 0 1-3 3h-2a1 1 0 0 1-1-1v-6a1 1 0 0 1 1-1h2c.35 0 .687.06 1 .17V12a7 7 0 0 0-7-7Z"
+		clip-rule="evenodd"
+	/>
+</svg>

src/lib/components/icons/MagnifyingGlass.svelte

@@ -0,0 +1,19 @@
+<script lang="ts">
+	export let className = 'size-4';
+	export let strokeWidth = '2';
+</script>
+
+<svg
+	xmlns="http://www.w3.org/2000/svg"
+	fill="none"
+	viewBox="0 0 24 24"
+	stroke-width={strokeWidth}
+	stroke="currentColor"
+	class={className}
+>
+	<path
+		stroke-linecap="round"
+		stroke-linejoin="round"
+		d="m21 21-5.197-5.197m0 0A7.5 7.5 0 1 0 5.196 5.196a7.5 7.5 0 0 0 10.607 10.607Z"
+	/>
+</svg>

src/lib/components/layout/Navbar.svelte

@@ -67,7 +67,7 @@
 			<div class="self-start flex flex-none items-center text-gray-600 dark:text-gray-400">
 				<!-- <div class="md:hidden flex self-center w-[1px] h-5 mx-2 bg-gray-300 dark:bg-stone-700" /> -->
 
-				{#if shareEnabled}
+				{#if shareEnabled && chat && chat.id}
 					<Menu
 						{chat}
 						{shareEnabled}

src/lib/components/layout/Navbar/Menu.svelte

@@ -138,7 +138,6 @@
 				</svg>
 				<div class="flex items-center">{$i18n.t('Share')}</div>
 			</DropdownMenu.Item>
-
 			<!-- <DropdownMenu.Item
 					class="flex gap-2 items-center px-3 py-2 text-sm  font-medium cursor-pointer"
 					on:click={() => {

src/lib/components/layout/Overlay/AccountPending.svelte

@@ -21,17 +21,20 @@
 		<div class="m-auto pb-10 flex flex-col justify-center">
 			<div class="max-w-md">
 				<div class="text-center dark:text-white text-2xl font-medium z-50">
-					Account Activation Pending<br /> Contact Admin for WebUI Access
+					{$i18n.t('Account Activation Pending')}<br />
+					{$i18n.t('Contact Admin for WebUI Access')}
 				</div>
 
 				<div class=" mt-4 text-center text-sm dark:text-gray-200 w-full">
-					Your account status is currently pending activation.<br /> To access the WebUI, please reach
-					out to the administrator. Admins can manage user statuses from the Admin Panel.
+					{$i18n.t('Your account status is currently pending activation.')}<br />
+					{$i18n.t(
+						'To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.'
+					)}
 				</div>
 
 				{#if adminDetails}
 					<div class="mt-4 text-sm font-medium text-center">
-						<div>Admin: {adminDetails.name} ({adminDetails.email})</div>
+						<div>{$i18n.t('Admin')}: {adminDetails.name} ({adminDetails.email})</div>
 					</div>
 				{/if}
 

src/lib/components/layout/Sidebar.svelte

@@ -325,6 +325,10 @@
 					on:click={() => {
 						selectedChatId = null;
 						chatId.set('');
+
+						if ($mobile) {
+							showSidebar.set(false);
+						}
 					}}
 					draggable="false"
 				>

src/lib/components/layout/Sidebar/UserMenu.svelte

@@ -1,12 +1,13 @@
 <script lang="ts">
 	import { DropdownMenu } from 'bits-ui';
-	import { createEventDispatcher, getContext } from 'svelte';
+	import { createEventDispatcher, getContext, onMount } from 'svelte';
 
 	import { flyAndScale } from '$lib/utils/transitions';
 	import { goto } from '$app/navigation';
 	import ArchiveBox from '$lib/components/icons/ArchiveBox.svelte';
-	import { showSettings } from '$lib/stores';
+	import { showSettings, activeUserCount, USAGE_POOL } from '$lib/stores';
 	import { fade, slide } from 'svelte/transition';
+	import Tooltip from '$lib/components/common/Tooltip.svelte';
 
 	const i18n = getContext('i18n');
 
@@ -107,7 +108,7 @@
 				</button>
 			{/if}
 
-			<hr class=" dark:border-gray-800 my-2 p-0" />
+			<hr class=" dark:border-gray-800 my-1.5 p-0" />
 
 			<button
 				class="flex rounded-md py-2 px-3 w-full hover:bg-gray-50 dark:hover:bg-gray-800 transition"
@@ -139,6 +140,36 @@
 				<div class=" self-center font-medium">{$i18n.t('Sign Out')}</div>
 			</button>
 
+			{#if $activeUserCount}
+				<hr class=" dark:border-gray-800 my-1.5 p-0" />
+
+				<Tooltip
+					content={$USAGE_POOL && $USAGE_POOL.length > 0
+						? `${$i18n.t('Running')}: ${$USAGE_POOL.join(', ')} ✨`
+						: ''}
+				>
+					<div class="flex rounded-md py-1.5 px-3 text-xs gap-2.5 items-center">
+						<div class=" flex items-center">
+							<span class="relative flex size-2">
+								<span
+									class="animate-ping absolute inline-flex h-full w-full rounded-full bg-green-400 opacity-75"
+								/>
+								<span class="relative inline-flex rounded-full size-2 bg-green-500" />
+							</span>
+						</div>
+
+						<div class=" ">
+							<span class=" font-medium">
+								{$i18n.t('Active Users')}:
+							</span>
+							<span class=" font-semibold">
+								{$activeUserCount}
+							</span>
+						</div>
+					</div>
+				</Tooltip>
+			{/if}
+
 			<!-- <DropdownMenu.Item class="flex items-center px-3 py-2 text-sm  font-medium">
 				<div class="flex items-center">Profile</div>
 			</DropdownMenu.Item> -->

src/lib/components/workspace/Documents.svelte

@@ -4,7 +4,7 @@
 	const { saveAs } = fileSaver;
 
 	import { onMount, getContext } from 'svelte';
-	import { WEBUI_NAME, documents } from '$lib/stores';
+	import { WEBUI_NAME, documents, showSidebar } from '$lib/stores';
 	import { createNewDoc, deleteDocByName, getDocs } from '$lib/apis/documents';
 
 	import { SUPPORTED_FILE_TYPE, SUPPORTED_FILE_EXTENSIONS } from '$lib/constants';
@@ -15,7 +15,6 @@
 
 	import EditDocModal from '$lib/components/documents/EditDocModal.svelte';
 	import AddFilesPlaceholder from '$lib/components/AddFilesPlaceholder.svelte';
-	import SettingsModal from '$lib/components/documents/SettingsModal.svelte';
 	import AddDocModal from '$lib/components/documents/AddDocModal.svelte';
 
 	const i18n = getContext('i18n');
@@ -158,12 +157,14 @@
 
 {#if dragged}
 	<div
-		class="fixed w-full h-full flex z-50 touch-none pointer-events-none"
+		class="fixed {$showSidebar
+			? 'left-0 md:left-[260px] md:w-[calc(100%-260px)]'
+			: 'left-0'}  w-full h-full flex z-50 touch-none pointer-events-none"
 		id="dropzone"
 		role="region"
 		aria-label="Drag and Drop Container"
 	>
-		<div class="absolute rounded-xl w-full h-full backdrop-blur bg-gray-800/40 flex justify-center">
+		<div class="absolute w-full h-full backdrop-blur bg-gray-800/40 flex justify-center">
 			<div class="m-auto pt-64 flex flex-col justify-center">
 				<div class="max-w-md">
 					<AddFilesPlaceholder>
@@ -183,39 +184,9 @@
 
 <AddDocModal bind:show={showAddDocModal} />
 
-<SettingsModal bind:show={showSettingsModal} />
-
 <div class="mb-3">
 	<div class="flex justify-between items-center">
 		<div class=" text-lg font-semibold self-center">{$i18n.t('Documents')}</div>
-
-		<div>
-			<button
-				class="flex items-center space-x-1 px-3 py-1.5 rounded-xl bg-gray-50 hover:bg-gray-100 dark:bg-gray-800 dark:hover:bg-gray-700 transition"
-				type="button"
-				on:click={() => {
-					showSettingsModal = !showSettingsModal;
-				}}
-			>
-				<svg
-					xmlns="http://www.w3.org/2000/svg"
-					viewBox="0 0 16 16"
-					fill="currentColor"
-					class="w-4 h-4"
-				>
-					<path
-						fill-rule="evenodd"
-						d="M6.955 1.45A.5.5 0 0 1 7.452 1h1.096a.5.5 0 0 1 .497.45l.17 1.699c.484.12.94.312 1.356.562l1.321-1.081a.5.5 0 0 1 .67.033l.774.775a.5.5 0 0 1 .034.67l-1.08 1.32c.25.417.44.873.561 1.357l1.699.17a.5.5 0 0 1 .45.497v1.096a.5.5 0 0 1-.45.497l-1.699.17c-.12.484-.312.94-.562 1.356l1.082 1.322a.5.5 0 0 1-.034.67l-.774.774a.5.5 0 0 1-.67.033l-1.322-1.08c-.416.25-.872.44-1.356.561l-.17 1.699a.5.5 0 0 1-.497.45H7.452a.5.5 0 0 1-.497-.45l-.17-1.699a4.973 4.973 0 0 1-1.356-.562L4.108 13.37a.5.5 0 0 1-.67-.033l-.774-.775a.5.5 0 0 1-.034-.67l1.08-1.32a4.971 4.971 0 0 1-.561-1.357l-1.699-.17A.5.5 0 0 1 1 8.548V7.452a.5.5 0 0 1 .45-.497l1.699-.17c.12-.484.312-.94.562-1.356L2.629 4.107a.5.5 0 0 1 .034-.67l.774-.774a.5.5 0 0 1 .67-.033L5.43 3.71a4.97 4.97 0 0 1 1.356-.561l.17-1.699ZM6 8c0 .538.212 1.026.558 1.385l.057.057a2 2 0 0 0 2.828-2.828l-.058-.056A2 2 0 0 0 6 8Z"
-						clip-rule="evenodd"
-					/>
-				</svg>
-
-				<div class=" text-xs">{$i18n.t('Document Settings')}</div>
-			</button>
-		</div>
-	</div>
-	<div class=" text-gray-500 text-xs mt-1">
-		ⓘ {$i18n.t("Use '#' in the prompt input to load and select your documents.")}
 	</div>
 </div>
 
@@ -520,6 +491,10 @@
 	{/each}
 </div>
 
+<div class=" text-gray-500 text-xs mt-1">
+	ⓘ {$i18n.t("Use '#' in the prompt input to load and select your documents.")}
+</div>
+
 <div class=" flex justify-end w-full mb-2">
 	<div class="flex space-x-2">
 		<input

src/lib/components/workspace/Models.svelte

@@ -71,16 +71,19 @@
 		const url = 'https://openwebui.com';
 
 		const tab = await window.open(`${url}/models/create`, '_blank');
-		window.addEventListener(
-			'message',
-			(event) => {
-				if (event.origin !== url) return;
-				if (event.data === 'loaded') {
-					tab.postMessage(JSON.stringify(model), '*');
-				}
-			},
-			false
-		);
+
+		// Define the event handler function
+		const messageHandler = (event) => {
+			if (event.origin !== url) return;
+			if (event.data === 'loaded') {
+				tab.postMessage(JSON.stringify(model), '*');
+
+				// Remove the event listener after handling the message
+				window.removeEventListener('message', messageHandler);
+			}
+		};
+
+		window.addEventListener('message', messageHandler, false);
 	};
 
 	const hideModelHandler = async (model) => {

src/lib/components/workspace/Models/Knowledge.svelte

@@ -0,0 +1,106 @@
+<script lang="ts">
+	import { getContext } from 'svelte';
+	import Selector from './Knowledge/Selector.svelte';
+
+	export let knowledge = [];
+
+	const i18n = getContext('i18n');
+</script>
+
+<div>
+	<div class="flex w-full justify-between mb-1">
+		<div class=" self-center text-sm font-semibold">{$i18n.t('Knowledge')}</div>
+	</div>
+
+	<div class=" text-xs dark:text-gray-500">
+		{$i18n.t('To add documents here, upload them to the "Documents" workspace first.')}
+	</div>
+
+	<div class="flex flex-col">
+		{#if knowledge.length > 0}
+			<div class=" flex items-center gap-2 mt-2">
+				{#each knowledge as file, fileIdx}
+					<div class=" relative group">
+						<div
+							class="h-16 w-[15rem] flex items-center space-x-3 px-2.5 dark:bg-gray-600 rounded-xl border border-gray-200 dark:border-none"
+						>
+							<div class="p-2.5 bg-red-400 text-white rounded-lg">
+								{#if (file?.type ?? 'doc') === 'doc'}
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 24 24"
+										fill="currentColor"
+										class="size-6"
+									>
+										<path
+											fill-rule="evenodd"
+											d="M5.625 1.5c-1.036 0-1.875.84-1.875 1.875v17.25c0 1.035.84 1.875 1.875 1.875h12.75c1.035 0 1.875-.84 1.875-1.875V12.75A3.75 3.75 0 0 0 16.5 9h-1.875a1.875 1.875 0 0 1-1.875-1.875V5.25A3.75 3.75 0 0 0 9 1.5H5.625ZM7.5 15a.75.75 0 0 1 .75-.75h7.5a.75.75 0 0 1 0 1.5h-7.5A.75.75 0 0 1 7.5 15Zm.75 2.25a.75.75 0 0 0 0 1.5H12a.75.75 0 0 0 0-1.5H8.25Z"
+											clip-rule="evenodd"
+										/>
+										<path
+											d="M12.971 1.816A5.23 5.23 0 0 1 14.25 5.25v1.875c0 .207.168.375.375.375H16.5a5.23 5.23 0 0 1 3.434 1.279 9.768 9.768 0 0 0-6.963-6.963Z"
+										/>
+									</svg>
+								{:else if file.type === 'collection'}
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 24 24"
+										fill="currentColor"
+										class="size-6"
+									>
+										<path
+											d="M7.5 3.375c0-1.036.84-1.875 1.875-1.875h.375a3.75 3.75 0 0 1 3.75 3.75v1.875C13.5 8.161 14.34 9 15.375 9h1.875A3.75 3.75 0 0 1 21 12.75v3.375C21 17.16 20.16 18 19.125 18h-9.75A1.875 1.875 0 0 1 7.5 16.125V3.375Z"
+										/>
+										<path
+											d="M15 5.25a5.23 5.23 0 0 0-1.279-3.434 9.768 9.768 0 0 1 6.963 6.963A5.23 5.23 0 0 0 17.25 7.5h-1.875A.375.375 0 0 1 15 7.125V5.25ZM4.875 6H6v10.125A3.375 3.375 0 0 0 9.375 19.5H16.5v1.125c0 1.035-.84 1.875-1.875 1.875h-9.75A1.875 1.875 0 0 1 3 20.625V7.875C3 6.839 3.84 6 4.875 6Z"
+										/>
+									</svg>
+								{/if}
+							</div>
+
+							<div class="flex flex-col justify-center -space-y-0.5">
+								<div class=" dark:text-gray-100 text-sm font-medium line-clamp-1">
+									{file?.title ?? `#${file.name}`}
+								</div>
+
+								<div class=" text-gray-500 text-sm">{$i18n.t(file?.type ?? 'Document')}</div>
+							</div>
+						</div>
+
+						<div class=" absolute -top-1 -right-1">
+							<button
+								class=" bg-gray-400 text-white border border-white rounded-full group-hover:visible invisible transition"
+								type="button"
+								on:click={() => {
+									knowledge.splice(fileIdx, 1);
+									knowledge = knowledge;
+								}}
+							>
+								<svg
+									xmlns="http://www.w3.org/2000/svg"
+									viewBox="0 0 20 20"
+									fill="currentColor"
+									class="w-4 h-4"
+								>
+									<path
+										d="M6.28 5.22a.75.75 0 00-1.06 1.06L8.94 10l-3.72 3.72a.75.75 0 101.06 1.06L10 11.06l3.72 3.72a.75.75 0 101.06-1.06L11.06 10l3.72-3.72a.75.75 0 00-1.06-1.06L10 8.94 6.28 5.22z"
+									/>
+								</svg>
+							</button>
+						</div>
+					</div>
+				{/each}
+			</div>
+		{/if}
+
+		<div class="flex flex-wrap text-sm font-medium gap-1.5 mt-2">
+			<Selector bind:knowledge>
+				<button
+					class=" px-3.5 py-1.5 font-medium hover:bg-black/5 dark:hover:bg-white/5 outline outline-1 outline-gray-300 dark:outline-gray-800 rounded-3xl"
+					type="button">{$i18n.t('Select Documents')}</button
+				>
+			</Selector>
+		</div>
+		<!-- {knowledge} -->
+	</div>
+</div>

src/lib/components/workspace/Models/Knowledge/Selector.svelte

@@ -0,0 +1,138 @@
+<script lang="ts">
+	import { DropdownMenu } from 'bits-ui';
+
+	import { documents } from '$lib/stores';
+	import { flyAndScale } from '$lib/utils/transitions';
+
+	import Dropdown from '$lib/components/common/Dropdown.svelte';
+	import { onMount, getContext } from 'svelte';
+
+	const i18n = getContext('i18n');
+
+	export let onClose: Function = () => {};
+
+	export let knowledge = [];
+
+	let items = [];
+
+	onMount(() => {
+		let collections = [
+			...($documents.length > 0
+				? [
+						{
+							name: 'All Documents',
+							type: 'collection',
+							title: $i18n.t('All Documents'),
+							collection_names: $documents.map((doc) => doc.collection_name)
+						}
+				  ]
+				: []),
+			...$documents
+				.reduce((a, e, i, arr) => {
+					return [...new Set([...a, ...(e?.content?.tags ?? []).map((tag) => tag.name)])];
+				}, [])
+				.map((tag) => ({
+					name: tag,
+					type: 'collection',
+					collection_names: $documents
+						.filter((doc) => (doc?.content?.tags ?? []).map((tag) => tag.name).includes(tag))
+						.map((doc) => doc.collection_name)
+				}))
+		];
+
+		items = [...collections, ...$documents];
+	});
+</script>
+
+<Dropdown
+	on:change={(e) => {
+		if (e.detail === false) {
+			onClose();
+		}
+	}}
+>
+	<slot />
+
+	<div slot="content">
+		<DropdownMenu.Content
+			class="w-full max-w-[300px]  rounded-lg px-1 py-1.5 border border-gray-300/30 dark:border-gray-700/50 z-50 bg-white dark:bg-gray-850 dark:text-white shadow-lg"
+			sideOffset={8}
+			side="bottom"
+			align="start"
+			transition={flyAndScale}
+		>
+			<div class="max-h-[10rem] overflow-y-scroll">
+				{#if items.length === 0}
+					<div class="text-center text-sm text-gray-500 dark:text-gray-400">
+						{$i18n.t('No documents found')}
+					</div>
+				{:else}
+					{#each items as item}
+						<DropdownMenu.Item
+							class="flex gap-2.5 items-center px-3 py-2 text-sm  cursor-pointer hover:bg-gray-50 dark:hover:bg-gray-800 rounded-md"
+							on:click={() => {
+								if (!knowledge.find((k) => k.name === item.name)) {
+									knowledge = [
+										...knowledge,
+										{
+											...item,
+											type: item?.type ?? 'doc'
+										}
+									];
+								}
+							}}
+						>
+							<div class="flex self-start">
+								{#if (item?.type ?? 'doc') === 'doc'}
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 24 24"
+										fill="currentColor"
+										class="w-4"
+									>
+										<path
+											fill-rule="evenodd"
+											d="M5.625 1.5c-1.036 0-1.875.84-1.875 1.875v17.25c0 1.035.84 1.875 1.875 1.875h12.75c1.035 0 1.875-.84 1.875-1.875V12.75A3.75 3.75 0 0 0 16.5 9h-1.875a1.875 1.875 0 0 1-1.875-1.875V5.25A3.75 3.75 0 0 0 9 1.5H5.625ZM7.5 15a.75.75 0 0 1 .75-.75h7.5a.75.75 0 0 1 0 1.5h-7.5A.75.75 0 0 1 7.5 15Zm.75 2.25a.75.75 0 0 0 0 1.5H12a.75.75 0 0 0 0-1.5H8.25Z"
+											clip-rule="evenodd"
+										/>
+										<path
+											d="M12.971 1.816A5.23 5.23 0 0 1 14.25 5.25v1.875c0 .207.168.375.375.375H16.5a5.23 5.23 0 0 1 3.434 1.279 9.768 9.768 0 0 0-6.963-6.963Z"
+										/>
+									</svg>
+								{:else if item.type === 'collection'}
+									<svg
+										xmlns="http://www.w3.org/2000/svg"
+										viewBox="0 0 24 24"
+										fill="currentColor"
+										class="size-4"
+									>
+										<path
+											d="M7.5 3.375c0-1.036.84-1.875 1.875-1.875h.375a3.75 3.75 0 0 1 3.75 3.75v1.875C13.5 8.161 14.34 9 15.375 9h1.875A3.75 3.75 0 0 1 21 12.75v3.375C21 17.16 20.16 18 19.125 18h-9.75A1.875 1.875 0 0 1 7.5 16.125V3.375Z"
+										/>
+										<path
+											d="M15 5.25a5.23 5.23 0 0 0-1.279-3.434 9.768 9.768 0 0 1 6.963 6.963A5.23 5.23 0 0 0 17.25 7.5h-1.875A.375.375 0 0 1 15 7.125V5.25ZM4.875 6H6v10.125A3.375 3.375 0 0 0 9.375 19.5H16.5v1.125c0 1.035-.84 1.875-1.875 1.875h-9.75A1.875 1.875 0 0 1 3 20.625V7.875C3 6.839 3.84 6 4.875 6Z"
+										/>
+									</svg>
+								{/if}
+							</div>
+
+							<div class="flex items-center">
+								<div class="flex flex-col">
+									<div
+										class=" w-fit text-xs font-black px-1 rounded uppercase line-clamp-1 bg-gray-500/20 text-gray-700 dark:text-gray-200"
+									>
+										{item?.type ?? 'Document'}
+									</div>
+
+									<div class="line-clamp-1 font-medium pr-0.5">
+										{item.name}
+									</div>
+								</div>
+							</div>
+						</DropdownMenu.Item>
+					{/each}
+				{/if}
+			</div>
+		</DropdownMenu.Content>
+	</div>
+</Dropdown>

src/lib/components/workspace/Playground.svelte

@@ -80,8 +80,6 @@
 					if (stopResponseFlag) {
 						controller.abort('User: Stop Response');
 					}
-
-					currentRequestId = null;
 					break;
 				}
 
@@ -97,11 +95,7 @@
 								let data = JSON.parse(line.replace(/^data: /, ''));
 								console.log(data);
 
-								if ('request_id' in data) {
-									currentRequestId = data.request_id;
-								} else {
-									text += data.choices[0].delta.content ?? '';
-								}
+								text += data.choices[0].delta.content ?? '';
 							}
 						}
 					}
@@ -178,21 +172,17 @@
 								let data = JSON.parse(line.replace(/^data: /, ''));
 								console.log(data);
 
-								if ('request_id' in data) {
-									currentRequestId = data.request_id;
+								if (responseMessage.content == '' && data.choices[0].delta.content == '\n') {
+									continue;
 								} else {
-									if (responseMessage.content == '' && data.choices[0].delta.content == '\n') {
-										continue;
-									} else {
-										textareaElement.style.height = textareaElement.scrollHeight + 'px';
+									textareaElement.style.height = textareaElement.scrollHeight + 'px';
 
-										responseMessage.content += data.choices[0].delta.content ?? '';
-										messages = messages;
+									responseMessage.content += data.choices[0].delta.content ?? '';
+									messages = messages;
 
-										textareaElement.style.height = textareaElement.scrollHeight + 'px';
+									textareaElement.style.height = textareaElement.scrollHeight + 'px';
 
-										await tick();
-									}
+									await tick();
 								}
 							}
 						}

src/lib/constants.ts

@@ -2,8 +2,9 @@ import { browser, dev } from '$app/environment';
 // import { version } from '../../package.json';
 
 export const APP_NAME = 'Open WebUI';
-export const WEBUI_BASE_URL = browser ? (dev ? `http://${location.hostname}:8080` : ``) : ``;
 
+export const WEBUI_HOSTNAME = browser ? (dev ? `${location.hostname}:8080` : ``) : '';
+export const WEBUI_BASE_URL = browser ? (dev ? `http://${WEBUI_HOSTNAME}` : ``) : ``;
 export const WEBUI_API_BASE_URL = `${WEBUI_BASE_URL}/api/v1`;
 
 export const OLLAMA_API_BASE_URL = `${WEBUI_BASE_URL}/ollama`;
@@ -88,7 +89,8 @@ export const SUPPORTED_FILE_EXTENSIONS = [
 	'xls',
 	'xlsx',
 	'pptx',
-	'ppt'
+	'ppt',
+	'msg'
 ];
 
 // Source: https://kit.svelte.dev/docs/modules#$env-static-public

src/lib/i18n/locales/ar-BH/translation.json

@@ -12,7 +12,9 @@
 	"a user": "مستخدم",
 	"About": "عن",
 	"Account": "الحساب",
+	"Account Activation Pending": "",
 	"Accurate information": "معلومات دقيقة",
+	"Active Users": "",
 	"Add": "أضف",
 	"Add a model id": "إضافة معرف نموذج",
 	"Add a short description about what this model does": "أضف وصفا موجزا حول ما يفعله هذا النموذج",
@@ -28,6 +30,7 @@
 	"Add User": "اضافة مستخدم",
 	"Adjusting these settings will apply changes universally to all users.": "سيؤدي ضبط هذه الإعدادات إلى تطبيق التغييرات بشكل عام على كافة المستخدمين",
 	"admin": "المشرف",
+	"Admin": "",
 	"Admin Panel": "لوحة التحكم",
 	"Admin Settings": "اعدادات المشرف",
 	"Advanced Parameters": "التعليمات المتقدمة",
@@ -58,7 +61,6 @@
 	"Audio": "صوتي",
 	"August": "أغسطس",
 	"Auto-playback response": "استجابة التشغيل التلقائي",
-	"Auto-send input after 3 sec.": "إرسال تلقائي للإدخال بعد 3 ثواني.",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 الرابط الرئيسي",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 الرابط مطلوب",
 	"available!": "متاح",
@@ -70,6 +72,9 @@
 	"Being lazy": "كون كسول",
 	"Brave Search API Key": "مفتاح واجهة برمجة تطبيقات البحث الشجاع",
 	"Bypass SSL verification for Websites": "تجاوز التحقق من SSL للموقع",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "اللغاء",
 	"Capabilities": "قدرات",
 	"Change Password": "تغير الباسورد",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Chunk المتغيرات",
 	"Chunk Size": "Chunk حجم",
 	"Citation": "اقتباس",
+	"Clear memory": "",
 	"Click here for help.": "أضغط هنا للمساعدة",
 	"Click here to": "أضغط هنا الانتقال",
 	"Click here to select": "أضغط هنا للاختيار",
 	"Click here to select a csv file.": "أضغط هنا للاختيار ملف csv",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "انقر هنا لاختيار المستندات",
 	"click here.": "أضغط هنا",
 	"Click on the user role button to change a user's role.": "أضغط على أسم الصلاحيات لتغيرها للمستخدم",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "الطلبات المتزامنة",
 	"Confirm Password": "تأكيد كلمة المرور",
 	"Connections": "اتصالات",
+	"Contact Admin for WebUI Access": "",
 	"Content": "الاتصال",
 	"Context Length": "طول السياق",
 	"Continue Response": "متابعة الرد",
-	"Conversation Mode": "وضع المحادثة",
 	"Copied shared chat URL to clipboard!": "تم نسخ عنوان URL للدردشة المشتركة إلى الحافظة",
 	"Copy": "نسخ",
 	"Copy last code block": "انسخ كتلة التعليمات البرمجية الأخيرة",
 	"Copy last response": "انسخ الرد الأخير",
 	"Copy Link": "أنسخ الرابط",
 	"Copying to clipboard was successful!": "تم النسخ إلى الحافظة بنجاح",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "قم بإنشاء عبارة موجزة مكونة من 3-5 كلمات كرأس للاستعلام التالي، مع الالتزام الصارم بالحد الأقصى لعدد الكلمات الذي يتراوح بين 3-5 كلمات وتجنب استخدام الكلمة 'عنوان':",
 	"Create a model": "إنشاء نموذج",
 	"Create Account": "إنشاء حساب",
 	"Create new key": "عمل مفتاح جديد",
@@ -126,12 +132,12 @@
 	"Custom": "مخصص",
 	"Customize models for a specific purpose": "تخصيص النماذج لغرض معين",
 	"Dark": "مظلم",
+	"Dashboard": "",
 	"Database": "قاعدة البيانات",
 	"December": "ديسمبر",
 	"Default": "الإفتراضي",
 	"Default (Automatic1111)": "(Automatic1111) الإفتراضي",
 	"Default (SentenceTransformers)": "(SentenceTransformers) الإفتراضي",
-	"Default (Web API)": "(Web API) الإفتراضي",
 	"Default Model": "النموذج الافتراضي",
 	"Default model updated": "الإفتراضي تحديث الموديل",
 	"Default Prompt Suggestions": "الإفتراضي Prompt الاقتراحات",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "اكتشاف موجه",
 	"Discover, download, and explore custom prompts": "اكتشاف وتنزيل واستكشاف المطالبات المخصصة",
 	"Discover, download, and explore model presets": "اكتشاف وتنزيل واستكشاف الإعدادات المسبقة للنموذج",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "اعرض اسم المستخدم بدلاً منك في الدردشة",
 	"Document": "المستند",
 	"Document Settings": "أعدادات المستند",
@@ -194,6 +201,7 @@
 	"Enter Score": "أدخل النتيجة",
 	"Enter Searxng Query URL": "أدخل عنوان URL لاستعلام Searxng",
 	"Enter Serper API Key": "أدخل مفتاح واجهة برمجة تطبيقات Serper",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "أدخل مفتاح واجهة برمجة تطبيقات Serpstack",
 	"Enter stop sequence": "أدخل تسلسل التوقف",
 	"Enter Top K": "أدخل Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "تصدير وثائق الخرائط",
 	"Export Models": "نماذج التصدير",
 	"Export Prompts": "مطالبات التصدير",
+	"External Models": "",
 	"Failed to create API Key.": "فشل في إنشاء مفتاح API.",
 	"Failed to read clipboard contents": "فشل في قراءة محتويات الحافظة",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "اتبعت التعليمات على أكمل وجه",
 	"Format your variables using square brackets like this:": "قم بتنسيق المتغيرات الخاصة بك باستخدام الأقواس المربعة مثل هذا:",
 	"Frequency Penalty": "عقوبة التردد",
-	"Full Screen Mode": "وضع ملء الشاشة",
 	"General": "عام",
 	"General Settings": "الاعدادات العامة",
+	"Generate Image": "",
 	"Generating search query": "إنشاء استعلام بحث",
 	"Generation Info": "معلومات الجيل",
 	"Good Response": "استجابة جيدة",
@@ -252,6 +261,7 @@
 	"Info": "معلومات",
 	"Input commands": "إدخال الأوامر",
 	"Install from Github URL": "التثبيت من عنوان URL لجيثب",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "واجهه المستخدم",
 	"Invalid Tag": "تاق غير صالحة",
 	"January": "يناير",
@@ -264,14 +274,17 @@
 	"JWT Token": "JWT Token",
 	"Keep Alive": "Keep Alive",
 	"Keyboard shortcuts": "اختصارات لوحة المفاتيح",
+	"Knowledge": "",
 	"Language": "اللغة",
 	"Last Active": "آخر نشاط",
 	"Light": "فاتح",
-	"Listening...": "جاري الاستماع",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "يمكن أن تصدر بعض الأخطاء. لذلك يجب التحقق من المعلومات المهمة",
+	"Local Models": "",
 	"LTR": "من جهة اليسار إلى اليمين",
 	"Made by OpenWebUI Community": "OpenWebUI تم إنشاؤه بواسطة مجتمع ",
 	"Make sure to enclose them with": "تأكد من إرفاقها",
+	"Manage": "",
 	"Manage Models": "إدارة النماذج",
 	"Manage Ollama Models": "Ollama إدارة موديلات ",
 	"Manage Pipelines": "إدارة خطوط الأنابيب",
@@ -307,6 +320,7 @@
 	"Name your model": "قم بتسمية النموذج الخاص بك",
 	"New Chat": "دردشة جديدة",
 	"New Password": "كلمة المرور الجديدة",
+	"No documents found": "",
 	"No results found": "لا توجد نتايج",
 	"No search query generated": "لم يتم إنشاء استعلام بحث",
 	"No source available": "لا يوجد مصدر متاح",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "أولاما API",
 	"Ollama API disabled": "أولاما API معطلة",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Ollama الاصدار",
 	"On": "تشغيل",
 	"Only": "فقط",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "PDF ملف (.pdf)",
 	"PDF Extract Images (OCR)": "PDF أستخرج الصور (OCR)",
 	"pending": "قيد الانتظار",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "{{error}} تم رفض الإذن عند الوصول إلى الميكروفون ",
 	"Personalization": "التخصيص",
 	"Pipelines": "خطوط الانابيب",
@@ -367,6 +384,7 @@
 	"Read Aloud": "أقراء لي",
 	"Record voice": "سجل صوت",
 	"Redirecting you to OpenWebUI Community": "OpenWebUI إعادة توجيهك إلى مجتمع ",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "رفض عندما لا ينبغي أن يكون",
 	"Regenerate": "تجديد",
 	"Release Notes": "ملاحظات الإصدار",
@@ -378,12 +396,14 @@
 	"Reranking Model": "إعادة تقييم النموذج",
 	"Reranking model disabled": "تم تعطيل نموذج إعادة الترتيب",
 	"Reranking model set to \"{{reranking_model}}\"": "تم ضبط نموذج إعادة الترتيب على \"{{reranking_model}}\"",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "إعادة تعيين تخزين المتجهات",
 	"Response AutoCopy to Clipboard": "النسخ التلقائي للاستجابة إلى الحافظة",
 	"Role": "منصب",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Rosé Pine Dawn",
 	"RTL": "من اليمين إلى اليسار",
+	"Running": "",
 	"Save": "حفظ",
 	"Save & Create": "حفظ وإنشاء",
 	"Save & Update": "حفظ وتحديث",
@@ -397,6 +417,8 @@
 	"Search Documents": "البحث المستندات",
 	"Search Models": "نماذج البحث",
 	"Search Prompts": "أبحث حث",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "عدد نتائج البحث",
 	"Searched {{count}} sites_zero": "تم البحث في {{count}} sites_zero",
 	"Searched {{count}} sites_one": "تم البحث في {{count}} sites_one",
@@ -404,31 +426,34 @@
 	"Searched {{count}} sites_few": "تم البحث في {{count}} sites_few",
 	"Searched {{count}} sites_many": "تم البحث في {{count}} sites_many",
 	"Searched {{count}} sites_other": "تم البحث في {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "البحث في الويب عن \"{{searchQuery}}\"",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "عنوان URL لاستعلام Searxng",
 	"See readme.md for instructions": "readme.md للحصول على التعليمات",
 	"See what's new": "ما الجديد",
 	"Seed": "Seed",
 	"Select a base model": "حدد نموذجا أساسيا",
+	"Select a engine": "",
 	"Select a mode": "أختار موديل",
 	"Select a model": "أختار الموديل",
 	"Select a pipeline": "حدد مسارا",
 	"Select a pipeline url": "حدد عنوان URL لخط الأنابيب",
 	"Select an Ollama instance": "أختار سيرفر ",
+	"Select Documents": "",
 	"Select model": " أختار موديل",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "النموذج (النماذج) المحددة لا تدعم مدخلات الصور",
 	"Send": "تم",
 	"Send a Message": "يُرجى إدخال طلبك هنا",
 	"Send message": "يُرجى إدخال طلبك هنا.",
 	"September": "سبتمبر",
 	"Serper API Key": "مفتاح واجهة برمجة تطبيقات سيربر",
+	"Serply API Key": "",
 	"Serpstack API Key": "مفتاح واجهة برمجة تطبيقات Serpstack",
 	"Server connection verified": "تم التحقق من اتصال الخادم",
 	"Set as default": "الافتراضي",
 	"Set Default Model": "تفعيد الموديل الافتراضي",
 	"Set embedding model (e.g. {{model}})": "ضبط نموذج المتجهات (على سبيل المثال: {{model}})",
 	"Set Image Size": "حجم الصورة",
-	"Set Model": "ضبط النموذج",
 	"Set reranking model (e.g. {{model}})": "ضبط نموذج إعادة الترتيب (على سبيل المثال: {{model}})",
 	"Set Steps": "ضبط الخطوات",
 	"Set Task Model": "تعيين نموذج المهمة",
@@ -452,8 +477,8 @@
 	"Source": "المصدر",
 	"Speech recognition error: {{error}}": "{{error}} خطأ في التعرف على الكلام",
 	"Speech-to-Text Engine": "محرك تحويل الكلام إلى نص",
-	"SpeechRecognition API is not supported in this browser.": "API SpeechRecognition غير مدعومة في هذا المتصفح.",
 	"Stop Sequence": "وقف التسلسل",
+	"STT Model": "",
 	"STT Settings": "STT اعدادات",
 	"Submit": "إرسال",
 	"Subtitle (e.g. about the Roman Empire)": "(e.g. about the Roman Empire) الترجمة",
@@ -472,7 +497,9 @@
 	"Thanks for your feedback!": "شكرا لملاحظاتك!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "يجب أن تكون النتيجة قيمة تتراوح بين 0.0 (0%) و1.0 (100%).",
 	"Theme": "الثيم",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "وهذا يضمن حفظ محادثاتك القيمة بشكل آمن في قاعدة بياناتك الخلفية. شكرًا لك!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "لا تتم مزامنة هذا الإعداد عبر المتصفحات أو الأجهزة.",
 	"Thorough explanation": "شرح شامل",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "ملاحضة: قم بتحديث عدة فتحات متغيرة على التوالي عن طريق الضغط على مفتاح tab في مدخلات الدردشة بعد كل استبدال.",
@@ -484,6 +511,8 @@
 	"to": "الى",
 	"To access the available model names for downloading,": "للوصول إلى أسماء الموديلات المتاحة للتنزيل،",
 	"To access the GGUF models available for downloading,": "للوصول إلى الموديلات GGUF المتاحة للتنزيل،",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "الى كتابة المحادثه",
 	"Today": "اليوم",
 	"Toggle settings": "فتح وأغلاق الاعدادات",
@@ -491,7 +520,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "هل تواجه مشكلة في الوصول",
+	"TTS Model": "",
 	"TTS Settings": "TTS اعدادات",
+	"TTS Voice": "",
 	"Type": "نوع",
 	"Type Hugging Face Resolve (Download) URL": "اكتب عنوان URL لحل مشكلة الوجه (تنزيل).",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "{{provider}}خطاء أوه! حدثت مشكلة في الاتصال بـ ",
@@ -500,6 +531,7 @@
 	"Update password": "تحديث كلمة المرور",
 	"Upload a GGUF model": "GGUF رفع موديل نوع",
 	"Upload Files": "تحميل الملفات",
+	"Upload Pipeline": "",
 	"Upload Progress": "جاري التحميل",
 	"URL Mode": "رابط الموديل",
 	"Use '#' in the prompt input to load and select your documents.": "أستخدم '#' في المحادثة لربطهامن المستندات",
@@ -518,6 +550,7 @@
 	"Warning": "تحذير",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "تحذير: إذا قمت بتحديث أو تغيير نموذج التضمين الخاص بك، فستحتاج إلى إعادة استيراد كافة المستندات.",
 	"Web": "Web",
+	"Web API": "",
 	"Web Loader Settings": "Web تحميل اعدادات",
 	"Web Params": "Web تحميل اعدادات",
 	"Web Search": "بحث الويب",
@@ -528,17 +561,20 @@
 	"WebUI will make requests to": "سوف يقوم WebUI بتقديم طلبات ل",
 	"What’s New in": "ما هو الجديد",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "عند إيقاف تشغيل السجل، لن تظهر الدردشات الجديدة على هذا المتصفح في سجلك على أي من أجهزتك.",
-	"Whisper (Local)": "Whisper (Local)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "مساحة العمل",
 	"Write a prompt suggestion (e.g. Who are you?)": "اكتب اقتراحًا سريعًا (على سبيل المثال، من أنت؟)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "اكتب ملخصًا في 50 كلمة يلخص [الموضوع أو الكلمة الرئيسية]",
 	"Yesterday": "أمس",
 	"You": "انت",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "لا يمكنك استنساخ نموذج أساسي",
 	"You have no archived conversations.": "لا تملك محادثات محفوظه",
 	"You have shared this chat": "تم مشاركة هذه المحادثة",
 	"You're a helpful assistant.": "مساعدك المفيد هنا",
 	"You're now logged in.": "لقد قمت الآن بتسجيل الدخول.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "Youtube تحميل اعدادات"
 }

src/lib/i18n/locales/bg-BG/translation.json

@@ -12,7 +12,9 @@
 	"a user": "потребител",
 	"About": "Относно",
 	"Account": "Акаунт",
+	"Account Activation Pending": "",
 	"Accurate information": "Точни информация",
+	"Active Users": "",
 	"Add": "Добавяне",
 	"Add a model id": "Добавяне на ИД на модел",
 	"Add a short description about what this model does": "Добавете кратко описание за това какво прави този модел",
@@ -28,6 +30,7 @@
 	"Add User": "Добавяне на потребител",
 	"Adjusting these settings will apply changes universally to all users.": "При промяна на тези настройки промените се прилагат за всички потребители.",
 	"admin": "админ",
+	"Admin": "",
 	"Admin Panel": "Панел на Администратор",
 	"Admin Settings": "Настройки на Администратор",
 	"Advanced Parameters": "Разширени Параметри",
@@ -58,7 +61,6 @@
 	"Audio": "Аудио",
 	"August": "Август",
 	"Auto-playback response": "Аувтоматично възпроизвеждане на Отговора",
-	"Auto-send input after 3 sec.": "Аувтоматично изпращане на входа след 3 сек.",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 Базов URL",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 Базов URL е задължителен.",
 	"available!": "наличен!",
@@ -70,6 +72,9 @@
 	"Being lazy": "Да бъдеш мързелив",
 	"Brave Search API Key": "Смел ключ за API за търсене",
 	"Bypass SSL verification for Websites": "Изключване на SSL проверката за сайтове",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Отказ",
 	"Capabilities": "Възможности",
 	"Change Password": "Промяна на Парола",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Chunk Params",
 	"Chunk Size": "Chunk Size",
 	"Citation": "Цитат",
+	"Clear memory": "",
 	"Click here for help.": "Натиснете тук за помощ.",
 	"Click here to": "Натиснете тук за",
 	"Click here to select": "Натиснете тук, за да изберете",
 	"Click here to select a csv file.": "Натиснете тук, за да изберете csv файл.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Натиснете тук, за да изберете документи.",
 	"click here.": "натиснете тук.",
 	"Click on the user role button to change a user's role.": "Натиснете върху бутона за промяна на ролята на потребителя.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "Едновременни искания",
 	"Confirm Password": "Потвърди Парола",
 	"Connections": "Връзки",
+	"Contact Admin for WebUI Access": "",
 	"Content": "Съдържание",
 	"Context Length": "Дължина на Контекста",
 	"Continue Response": "Продължи отговора",
-	"Conversation Mode": "Режим на Чат",
 	"Copied shared chat URL to clipboard!": "Копирана е връзката за чат!",
 	"Copy": "Копирай",
 	"Copy last code block": "Копиране на последен код блок",
 	"Copy last response": "Копиране на последен отговор",
 	"Copy Link": "Копиране на връзка",
 	"Copying to clipboard was successful!": "Копирането в клипборда беше успешно!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Създайте кратка фраза от 3-5 думи като заглавие за следващото запитване, като стриктно спазвате ограничението от 3-5 думи и избягвате използването на думата 'заглавие':",
 	"Create a model": "Създаване на модел",
 	"Create Account": "Създаване на Акаунт",
 	"Create new key": "Създаване на нов ключ",
@@ -126,12 +132,12 @@
 	"Custom": "Персонализиран",
 	"Customize models for a specific purpose": "Персонализиране на модели за конкретна цел",
 	"Dark": "Тъмен",
+	"Dashboard": "",
 	"Database": "База данни",
 	"December": "Декември",
 	"Default": "По подразбиране",
 	"Default (Automatic1111)": "По подразбиране (Automatic1111)",
 	"Default (SentenceTransformers)": "По подразбиране (SentenceTransformers)",
-	"Default (Web API)": "По подразбиране (Web API)",
 	"Default Model": "Модел по подразбиране",
 	"Default model updated": "Моделът по подразбиране е обновен",
 	"Default Prompt Suggestions": "Промпт Предложения по подразбиране",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "Откриване на промпт",
 	"Discover, download, and explore custom prompts": "Откриване, сваляне и преглед на персонализирани промптове",
 	"Discover, download, and explore model presets": "Откриване, сваляне и преглед на пресетове на модели",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "Показване на потребителското име вместо Вие в чата",
 	"Document": "Документ",
 	"Document Settings": "Документ Настройки",
@@ -194,6 +201,7 @@
 	"Enter Score": "Въведете оценка",
 	"Enter Searxng Query URL": "Въведете URL адреса на заявката на Searxng",
 	"Enter Serper API Key": "Въведете Serper API ключ",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "Въведете Serpstack API ключ",
 	"Enter stop sequence": "Въведете стоп последователност",
 	"Enter Top K": "Въведете Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "Експортване на документен мапинг",
 	"Export Models": "Експортиране на модели",
 	"Export Prompts": "Експортване на промптове",
+	"External Models": "",
 	"Failed to create API Key.": "Неуспешно създаване на API ключ.",
 	"Failed to read clipboard contents": "Грешка при четене на съдържанието от клипборда",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "Следвайте инструкциите перфектно",
 	"Format your variables using square brackets like this:": "Форматирайте вашите променливи, като използвате квадратни скоби, както следва:",
 	"Frequency Penalty": "Наказание за честота",
-	"Full Screen Mode": "На Цял екран",
 	"General": "Основни",
 	"General Settings": "Основни Настройки",
+	"Generate Image": "",
 	"Generating search query": "Генериране на заявка за търсене",
 	"Generation Info": "Информация за Генерация",
 	"Good Response": "Добра отговор",
@@ -252,6 +261,7 @@
 	"Info": "Информация",
 	"Input commands": "Въведете команди",
 	"Install from Github URL": "Инсталиране от URL адреса на Github",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Интерфейс",
 	"Invalid Tag": "Невалиден тег",
 	"January": "Януари",
@@ -264,14 +274,17 @@
 	"JWT Token": "JWT Token",
 	"Keep Alive": "Keep Alive",
 	"Keyboard shortcuts": "Клавиши за бърз достъп",
+	"Knowledge": "",
 	"Language": "Език",
 	"Last Active": "Последни активни",
 	"Light": "Светъл",
-	"Listening...": "Слушам...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "LLMs могат да правят грешки. Проверете важните данни.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "Направено от OpenWebUI общността",
 	"Make sure to enclose them with": "Уверете се, че са заключени с",
+	"Manage": "",
 	"Manage Models": "Управление на Моделите",
 	"Manage Ollama Models": "Управление на Ollama Моделите",
 	"Manage Pipelines": "Управление на тръбопроводи",
@@ -307,6 +320,7 @@
 	"Name your model": "Дайте име на вашия модел",
 	"New Chat": "Нов чат",
 	"New Password": "Нова парола",
+	"No documents found": "",
 	"No results found": "Няма намерени резултати",
 	"No search query generated": "Не е генерирана заявка за търсене",
 	"No source available": "Няма наличен източник",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama API",
 	"Ollama API disabled": "Ollama API деактивиран",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Ollama Версия",
 	"On": "Вкл.",
 	"Only": "Само",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "PDF документ (.pdf)",
 	"PDF Extract Images (OCR)": "PDF Extract Images (OCR)",
 	"pending": "в очакване",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Permission denied when accessing microphone: {{error}}",
 	"Personalization": "Персонализация",
 	"Pipelines": "Тръбопроводи",
@@ -367,6 +384,7 @@
 	"Read Aloud": "Прочети на Голос",
 	"Record voice": "Записване на глас",
 	"Redirecting you to OpenWebUI Community": "Пренасочване към OpenWebUI общността",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "Отказано, когато не трябва да бъде",
 	"Regenerate": "Регенериране",
 	"Release Notes": "Бележки по изданието",
@@ -378,12 +396,14 @@
 	"Reranking Model": "Reranking Model",
 	"Reranking model disabled": "Reranking model disabled",
 	"Reranking model set to \"{{reranking_model}}\"": "Reranking model set to \"{{reranking_model}}\"",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "Ресет Vector Storage",
 	"Response AutoCopy to Clipboard": "Аувтоматично копиране на отговор в клипборда",
 	"Role": "Роля",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Rosé Pine Dawn",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "Запис",
 	"Save & Create": "Запис & Създаване",
 	"Save & Update": "Запис & Актуализиране",
@@ -397,34 +417,39 @@
 	"Search Documents": "Търси Документи",
 	"Search Models": "Търсене на модели",
 	"Search Prompts": "Търси Промптове",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "Брой резултати от търсенето",
 	"Searched {{count}} sites_one": "Търси се в {{count}} sites_one",
 	"Searched {{count}} sites_other": "Търси се в {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "Търсене в уеб за '{{searchQuery}}'",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "URL адрес на заявка на Searxng",
 	"See readme.md for instructions": "Виж readme.md за инструкции",
 	"See what's new": "Виж какво е новото",
 	"Seed": "Seed",
 	"Select a base model": "Изберете базов модел",
+	"Select a engine": "",
 	"Select a mode": "Изберете режим",
 	"Select a model": "Изберете модел",
 	"Select a pipeline": "Изберете тръбопровод",
 	"Select a pipeline url": "Избор на URL адрес на канал",
 	"Select an Ollama instance": "Изберете Ollama инстанция",
+	"Select Documents": "",
 	"Select model": "Изберете модел",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "Избраният(те) модел(и) не поддържа въвеждане на изображения",
 	"Send": "Изпрати",
 	"Send a Message": "Изпращане на Съобщение",
 	"Send message": "Изпращане на съобщение",
 	"September": "Септември",
 	"Serper API Key": "Serper API ключ",
+	"Serply API Key": "",
 	"Serpstack API Key": "Serpstack API ключ",
 	"Server connection verified": "Server connection verified",
 	"Set as default": "Задай по подразбиране",
 	"Set Default Model": "Задай Модел По Подразбиране",
 	"Set embedding model (e.g. {{model}})": "Задай embedding model (e.g. {{model}})",
 	"Set Image Size": "Задай Размер на Изображението",
-	"Set Model": "Задай Модел",
 	"Set reranking model (e.g. {{model}})": "Задай reranking model (e.g. {{model}})",
 	"Set Steps": "Задай Стъпки",
 	"Set Task Model": "Задаване на модел на задача",
@@ -448,8 +473,8 @@
 	"Source": "Източник",
 	"Speech recognition error: {{error}}": "Speech recognition error: {{error}}",
 	"Speech-to-Text Engine": "Speech-to-Text Engine",
-	"SpeechRecognition API is not supported in this browser.": "SpeechRecognition API is not supported in this browser.",
 	"Stop Sequence": "Stop Sequence",
+	"STT Model": "",
 	"STT Settings": "STT Настройки",
 	"Submit": "Изпращане",
 	"Subtitle (e.g. about the Roman Empire)": "Подтитул (напр. за Римска империя)",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "Благодарим ви за вашия отзив!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "The score should be a value between 0.0 (0%) and 1.0 (100%).",
 	"Theme": "Тема",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Това гарантира, че ценните ви разговори се запазват сигурно във вашата бекенд база данни. Благодарим ви!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "Тази настройка не се синхронизира между браузъри или устройства.",
 	"Thorough explanation": "Това е подробно описание.",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Съвет: Актуализирайте няколко слота за променливи последователно, като натискате клавиша Tab в чат входа след всяка подмяна.",
@@ -480,6 +507,8 @@
 	"to": "в",
 	"To access the available model names for downloading,": "За да получите достъп до наличните имена на модели за изтегляне,",
 	"To access the GGUF models available for downloading,": "За да получите достъп до GGUF моделите, налични за изтегляне,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "към чат входа.",
 	"Today": "днес",
 	"Toggle settings": "Toggle settings",
@@ -487,7 +516,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "Проблеми с достъпът до Ollama?",
+	"TTS Model": "",
 	"TTS Settings": "TTS Настройки",
+	"TTS Voice": "",
 	"Type": "Вид",
 	"Type Hugging Face Resolve (Download) URL": "Въведете Hugging Face Resolve (Download) URL",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "О, не! Възникна проблем при свързването с {{provider}}.",
@@ -496,6 +527,7 @@
 	"Update password": "Обновяване на парола",
 	"Upload a GGUF model": "Качване на GGUF модел",
 	"Upload Files": "Качване на файлове",
+	"Upload Pipeline": "",
 	"Upload Progress": "Прогрес на качването",
 	"URL Mode": "URL Mode",
 	"Use '#' in the prompt input to load and select your documents.": "Използвайте '#' във промпта за да заредите и изберете вашите документи.",
@@ -514,6 +546,7 @@
 	"Warning": "Предупреждение",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Предупреждение: Ако актуализирате или промените вашия модел за вграждане, трябва да повторите импортирането на всички документи.",
 	"Web": "Уеб",
+	"Web API": "",
 	"Web Loader Settings": "Настройки за зареждане на уеб",
 	"Web Params": "Параметри за уеб",
 	"Web Search": "Търсене в уеб",
@@ -524,17 +557,20 @@
 	"WebUI will make requests to": "WebUI ще направи заявки към",
 	"What’s New in": "Какво е новото в",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "Когато историята е изключена, нови чатове в този браузър ще не се показват в историята на никои от вашия профил.",
-	"Whisper (Local)": "Whisper (Локален)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "Работно пространство",
 	"Write a prompt suggestion (e.g. Who are you?)": "Напиши предложение за промпт (напр. Кой сте вие?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Напиши описание в 50 знака, което описва [тема или ключова дума].",
 	"Yesterday": "вчера",
 	"You": "вие",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "Не можете да клонирате базов модел",
 	"You have no archived conversations.": "Нямате архивирани разговори.",
 	"You have shared this chat": "Вие сте споделели този чат",
 	"You're a helpful assistant.": "Вие сте полезен асистент.",
 	"You're now logged in.": "Сега, вие влязохте в системата.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "Youtube Loader Settings"
 }

src/lib/i18n/locales/bn-BD/translation.json

@@ -12,7 +12,9 @@
 	"a user": "একজন ব্যাবহারকারী",
 	"About": "সম্পর্কে",
 	"Account": "একাউন্ট",
+	"Account Activation Pending": "",
 	"Accurate information": "সঠিক তথ্য",
+	"Active Users": "",
 	"Add": "যোগ করুন",
 	"Add a model id": "একটি মডেল ID যোগ করুন",
 	"Add a short description about what this model does": "এই মডেলটি কী করে সে সম্পর্কে একটি সংক্ষিপ্ত বিবরণ যুক্ত করুন",
@@ -28,6 +30,7 @@
 	"Add User": "ইউজার যোগ করুন",
 	"Adjusting these settings will apply changes universally to all users.": "এই সেটিংগুলো পরিবর্তন করলে তা সব ইউজারের উপরেই প্রয়োগ করা হবে",
 	"admin": "এডমিন",
+	"Admin": "",
 	"Admin Panel": "এডমিন প্যানেল",
 	"Admin Settings": "এডমিন সেটিংস",
 	"Advanced Parameters": "এডভান্সড প্যারামিটার্স",
@@ -58,7 +61,6 @@
 	"Audio": "অডিও",
 	"August": "আগস্ট",
 	"Auto-playback response": "রেসপন্স অটো-প্লেব্যাক",
-	"Auto-send input after 3 sec.": "৩ সেকেন্ড পর ইনপুট সংয়ক্রিয়ভাবে পাঠান",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 বেজ ইউআরএল",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 বেজ ইউআরএল আবশ্যক",
 	"available!": "উপলব্ধ!",
@@ -70,6 +72,9 @@
 	"Being lazy": "অলস হওয়া",
 	"Brave Search API Key": "সাহসী অনুসন্ধান API কী",
 	"Bypass SSL verification for Websites": "ওয়েবসাইটের জন্য SSL যাচাই বাতিল করুন",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "বাতিল",
 	"Capabilities": "সক্ষমতা",
 	"Change Password": "পাসওয়ার্ড পরিবর্তন করুন",
@@ -87,10 +92,12 @@
 	"Chunk Params": "চাঙ্ক প্যারামিটার্স",
 	"Chunk Size": "চাঙ্ক সাইজ",
 	"Citation": "উদ্ধৃতি",
+	"Clear memory": "",
 	"Click here for help.": "সাহায্যের জন্য এখানে ক্লিক করুন",
 	"Click here to": "এখানে ক্লিক করুন",
 	"Click here to select": "নির্বাচন করার জন্য এখানে ক্লিক করুন",
 	"Click here to select a csv file.": "একটি csv ফাইল নির্বাচন করার জন্য এখানে ক্লিক করুন",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "ডকুমেন্টগুলো নির্বাচন করার জন্য এখানে ক্লিক করুন",
 	"click here.": "এখানে ক্লিক করুন",
 	"Click on the user role button to change a user's role.": "ইউজারের পদবি পরিবর্তন করার জন্য ইউজারের পদবি বাটনে ক্লিক করুন",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "সমকালীন অনুরোধ",
 	"Confirm Password": "পাসওয়ার্ড নিশ্চিত করুন",
 	"Connections": "কানেকশনগুলো",
+	"Contact Admin for WebUI Access": "",
 	"Content": "বিষয়বস্তু",
 	"Context Length": "কনটেক্সটের দৈর্ঘ্য",
 	"Continue Response": "যাচাই করুন",
-	"Conversation Mode": "কথোপকথন মোড",
 	"Copied shared chat URL to clipboard!": "শেয়ারকৃত কথা-ব্যবহারের URL ক্লিপবোর্ডে কপি করা হয়েছে!",
 	"Copy": "অনুলিপি",
 	"Copy last code block": "সর্বশেষ কোড ব্লক কপি করুন",
 	"Copy last response": "সর্বশেষ রেসপন্স কপি করুন",
 	"Copy Link": "লিংক কপি করুন",
 	"Copying to clipboard was successful!": "ক্লিপবোর্ডে কপি করা সফল হয়েছে",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "'title' শব্দটি ব্যবহার না করে নিম্মোক্ত অনুসন্ধানের জন্য সংক্ষেপে সর্বোচ্চ ৩-৫ শব্দের একটি হেডার তৈরি করুন",
 	"Create a model": "একটি মডেল তৈরি করুন",
 	"Create Account": "একাউন্ট তৈরি করুন",
 	"Create new key": "একটি নতুন কী তৈরি করুন",
@@ -126,12 +132,12 @@
 	"Custom": "কাস্টম",
 	"Customize models for a specific purpose": "একটি নির্দিষ্ট উদ্দেশ্যে মডেল কাস্টমাইজ করুন",
 	"Dark": "ডার্ক",
+	"Dashboard": "",
 	"Database": "ডেটাবেজ",
 	"December": "ডেসেম্বর",
 	"Default": "ডিফল্ট",
 	"Default (Automatic1111)": "ডিফল্ট (Automatic1111)",
 	"Default (SentenceTransformers)": "ডিফল্ট (SentenceTransformers)",
-	"Default (Web API)": "ডিফল্ট (Web API)",
 	"Default Model": "ডিফল্ট মডেল",
 	"Default model updated": "ডিফল্ট মডেল আপডেট হয়েছে",
 	"Default Prompt Suggestions": "ডিফল্ট প্রম্পট সাজেশন",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "একটি প্রম্পট খুঁজে বের করুন",
 	"Discover, download, and explore custom prompts": "কাস্টম প্রম্পটগুলো আবিস্কার, ডাউনলোড এবং এক্সপ্লোর করুন",
 	"Discover, download, and explore model presets": "মডেল প্রিসেটগুলো আবিস্কার, ডাউনলোড এবং এক্সপ্লোর করুন",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "চ্যাটে 'আপনি'-র পরবর্তে ইউজারনেম দেখান",
 	"Document": "ডকুমেন্ট",
 	"Document Settings": "ডকুমেন্ট সেটিংসমূহ",
@@ -194,6 +201,7 @@
 	"Enter Score": "স্কোর দিন",
 	"Enter Searxng Query URL": "Searxng ক্যোয়ারী URL লিখুন",
 	"Enter Serper API Key": "Serper API কী লিখুন",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "Serpstack API কী লিখুন",
 	"Enter stop sequence": "স্টপ সিকোয়েন্স লিখুন",
 	"Enter Top K": "Top K লিখুন",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "ডকুমেন্টসমূহ ম্যাপিং এক্সপোর্ট করুন",
 	"Export Models": "রপ্তানি মডেল",
 	"Export Prompts": "প্রম্পটগুলো একপোর্ট করুন",
+	"External Models": "",
 	"Failed to create API Key.": "API Key তৈরি করা যায়নি।",
 	"Failed to read clipboard contents": "ক্লিপবোর্ডের বিষয়বস্তু পড়া সম্ভব হয়নি",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "নির্দেশাবলী নিখুঁতভাবে অনুসরণ করা হয়েছে",
 	"Format your variables using square brackets like this:": "আপনার ভেরিয়বলগুলো এভাবে স্কয়ার ব্রাকেটের মাধ্যমে সাজান",
 	"Frequency Penalty": "ফ্রিকোয়েন্সি পেনাল্টি",
-	"Full Screen Mode": "ফুলস্ক্রিন মোড",
 	"General": "সাধারণ",
 	"General Settings": "সাধারণ সেটিংসমূহ",
+	"Generate Image": "",
 	"Generating search query": "অনুসন্ধান ক্যোয়ারী তৈরি করা হচ্ছে",
 	"Generation Info": "জেনারেশন ইনফো",
 	"Good Response": "ভালো সাড়া",
@@ -252,6 +261,7 @@
 	"Info": "তথ্য",
 	"Input commands": "ইনপুট কমান্ডস",
 	"Install from Github URL": "Github URL থেকে ইনস্টল করুন",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "ইন্টারফেস",
 	"Invalid Tag": "অবৈধ ট্যাগ",
 	"January": "জানুয়ারী",
@@ -264,14 +274,17 @@
 	"JWT Token": "JWT টোকেন",
 	"Keep Alive": "সচল রাখুন",
 	"Keyboard shortcuts": "কিবোর্ড শর্টকাটসমূহ",
+	"Knowledge": "",
 	"Language": "ভাষা",
 	"Last Active": "সর্বশেষ সক্রিয়",
 	"Light": "লাইট",
-	"Listening...": "শুনছে...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "LLM ভুল করতে পারে। গুরুত্বপূর্ণ তথ্য যাচাই করে নিন।",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "OpenWebUI কমিউনিটিকর্তৃক নির্মিত",
 	"Make sure to enclose them with": "এটা দিয়ে বন্ধনী দিতে ভুলবেন না",
+	"Manage": "",
 	"Manage Models": "মডেলসমূহ ব্যবস্থাপনা করুন",
 	"Manage Ollama Models": "Ollama মডেলসূহ ব্যবস্থাপনা করুন",
 	"Manage Pipelines": "পাইপলাইন পরিচালনা করুন",
@@ -307,6 +320,7 @@
 	"Name your model": "আপনার মডেলের নাম দিন",
 	"New Chat": "নতুন চ্যাট",
 	"New Password": "নতুন পাসওয়ার্ড",
+	"No documents found": "",
 	"No results found": "কোন ফলাফল পাওয়া যায়নি",
 	"No search query generated": "কোনও অনুসন্ধান ক্যোয়ারী উত্পন্ন হয়নি",
 	"No source available": "কোন উৎস পাওয়া যায়নি",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama API",
 	"Ollama API disabled": "Ollama API নিষ্ক্রিয় করা হয়েছে",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Ollama ভার্সন",
 	"On": "চালু",
 	"Only": "শুধুমাত্র",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "PDF ডকুমেন্ট (.pdf)",
 	"PDF Extract Images (OCR)": "পিডিএফ এর ছবি থেকে লেখা বের করুন (OCR)",
 	"pending": "অপেক্ষমান",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "মাইক্রোফোন ব্যবহারের অনুমতি পাওয়া যায়নি: {{error}}",
 	"Personalization": "ডিজিটাল বাংলা",
 	"Pipelines": "পাইপলাইন",
@@ -367,6 +384,7 @@
 	"Read Aloud": "পড়াশোনা করুন",
 	"Record voice": "ভয়েস রেকর্ড করুন",
 	"Redirecting you to OpenWebUI Community": "আপনাকে OpenWebUI কমিউনিটিতে পাঠানো হচ্ছে",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "যদি উপযুক্ত নয়, তবে রেজিগেনেট করা হচ্ছে",
 	"Regenerate": "রেজিগেনেট করুন",
 	"Release Notes": "রিলিজ নোটসমূহ",
@@ -378,12 +396,14 @@
 	"Reranking Model": "রির্যাক্টিং মডেল",
 	"Reranking model disabled": "রির্যাক্টিং মডেল নিষ্ক্রিয় করা",
 	"Reranking model set to \"{{reranking_model}}\"": "রির ্যাঙ্কিং মডেল \"{{reranking_model}}\" -এ সেট করা আছে",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "ভেক্টর স্টোরেজ রিসেট করুন",
 	"Response AutoCopy to Clipboard": "রেসপন্সগুলো স্বয়ংক্রিভাবে ক্লিপবোর্ডে কপি হবে",
 	"Role": "পদবি",
 	"Rosé Pine": "রোজ পাইন",
 	"Rosé Pine Dawn": "ভোরের রোজ পাইন",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "সংরক্ষণ",
 	"Save & Create": "সংরক্ষণ এবং তৈরি করুন",
 	"Save & Update": "সংরক্ষণ এবং আপডেট করুন",
@@ -397,34 +417,39 @@
 	"Search Documents": "ডকুমেন্টসমূহ অনুসন্ধান করুন",
 	"Search Models": "অনুসন্ধান মডেল",
 	"Search Prompts": "প্রম্পটসমূহ অনুসন্ধান করুন",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "অনুসন্ধানের ফলাফল গণনা",
 	"Searched {{count}} sites_one": "{{কাউন্ট}} অনুসন্ধান করা হয়েছে sites_one",
 	"Searched {{count}} sites_other": "{{কাউন্ট}} অনুসন্ধান করা হয়েছে sites_other",
-	"Searching the web for '{{searchQuery}}'": "'{{searchQuery}}' এর জন্য ওয়েবে অনুসন্ধান করা হচ্ছে",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "Searxng ক্যোয়ারী URL",
 	"See readme.md for instructions": "নির্দেশিকার জন্য readme.md দেখুন",
 	"See what's new": "নতুন কী আছে দেখুন",
 	"Seed": "সীড",
 	"Select a base model": "একটি বেস মডেল নির্বাচন করুন",
+	"Select a engine": "",
 	"Select a mode": "একটি মডেল নির্বাচন করুন",
 	"Select a model": "একটি মডেল নির্বাচন করুন",
 	"Select a pipeline": "একটি পাইপলাইন নির্বাচন করুন",
 	"Select a pipeline url": "একটি পাইপলাইন URL নির্বাচন করুন",
 	"Select an Ollama instance": "একটি Ollama ইন্সট্যান্স নির্বাচন করুন",
+	"Select Documents": "",
 	"Select model": "মডেল নির্বাচন করুন",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "নির্বাচিত মডেল(গুলি) চিত্র ইনপুট সমর্থন করে না",
 	"Send": "পাঠান",
 	"Send a Message": "একটি মেসেজ পাঠান",
 	"Send message": "মেসেজ পাঠান",
 	"September": "সেপ্টেম্বর",
 	"Serper API Key": "Serper API Key",
+	"Serply API Key": "",
 	"Serpstack API Key": "Serpstack API Key",
 	"Server connection verified": "সার্ভার কানেকশন যাচাই করা হয়েছে",
 	"Set as default": "ডিফল্ট হিসেবে নির্ধারণ করুন",
 	"Set Default Model": "ডিফল্ট মডেল নির্ধারণ করুন",
 	"Set embedding model (e.g. {{model}})": "ইমেম্বিং মডেল নির্ধারণ করুন (উদাহরণ {{model}})",
 	"Set Image Size": "ছবির সাইজ নির্ধারণ করুন",
-	"Set Model": "মডেল নির্ধারণ করুন",
 	"Set reranking model (e.g. {{model}})": "রি-র্যাংকিং মডেল নির্ধারণ করুন (উদাহরণ {{model}})",
 	"Set Steps": "পরবর্তী ধাপসমূহ",
 	"Set Task Model": "টাস্ক মডেল সেট করুন",
@@ -448,8 +473,8 @@
 	"Source": "উৎস",
 	"Speech recognition error: {{error}}": "স্পিচ রিকগনিশনে সমস্যা: {{error}}",
 	"Speech-to-Text Engine": "স্পিচ-টু-টেক্সট ইঞ্জিন",
-	"SpeechRecognition API is not supported in this browser.": "এই ব্রাউজার স্পিচরিকগনিশন এপিআই সাপোর্ট করে না।",
 	"Stop Sequence": "সিকোয়েন্স থামান",
+	"STT Model": "",
 	"STT Settings": "STT সেটিংস",
 	"Submit": "সাবমিট",
 	"Subtitle (e.g. about the Roman Empire)": "সাবটাইটল (রোমান ইম্পার্টের সম্পর্কে)",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "আপনার মতামত ধন্যবাদ!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "স্কোর একটি 0.0 (0%) এবং 1.0 (100%) এর মধ্যে একটি মান হওয়া উচিত।",
 	"Theme": "থিম",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "এটা নিশ্চিত করে যে, আপনার গুরুত্বপূর্ণ আলোচনা নিরাপদে আপনার ব্যাকএন্ড ডেটাবেজে সংরক্ষিত আছে। ধন্যবাদ!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "এই সেটিং অন্যন্য ব্রাউজার বা ডিভাইসের সাথে সিঙ্ক্রোনাইজ নয় না।",
 	"Thorough explanation": "পুঙ্খানুপুঙ্খ ব্যাখ্যা",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "পরামর্শ: একাধিক ভেরিয়েবল স্লট একের পর এক রিপ্লেস করার জন্য চ্যাট ইনপুটে কিবোর্ডের Tab বাটন ব্যবহার করুন।",
@@ -480,6 +507,8 @@
 	"to": "প্রতি",
 	"To access the available model names for downloading,": "ডাউনলোডের জন্য এভেইলএবল মডেলের নামগুলো এক্সেস করতে,",
 	"To access the GGUF models available for downloading,": "ডাউলোডের জন্য এভেইলএবল GGUF মডেলগুলো এক্সেস করতে,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "চ্যাট ইনপুটে",
 	"Today": "আজ",
 	"Toggle settings": "সেটিংস টোগল",
@@ -487,7 +516,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "Ollama এক্সেস করতে সমস্যা হচ্ছে?",
+	"TTS Model": "",
 	"TTS Settings": "TTS সেটিংসমূহ",
+	"TTS Voice": "",
 	"Type": "টাইপ",
 	"Type Hugging Face Resolve (Download) URL": "Hugging Face থেকে ডাউনলোড করার ইউআরএল টাইপ করুন",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "ওহ-হো! {{provider}} এর সাথে কানেকশনে সমস্যা হয়েছে।",
@@ -496,6 +527,7 @@
 	"Update password": "পাসওয়ার্ড আপডেট করুন",
 	"Upload a GGUF model": "একটি GGUF মডেল আপলোড করুন",
 	"Upload Files": "ফাইল আপলোড করুন",
+	"Upload Pipeline": "",
 	"Upload Progress": "আপলোড হচ্ছে",
 	"URL Mode": "ইউআরএল মোড",
 	"Use '#' in the prompt input to load and select your documents.": "আপনার ডকুমেন্টসমূহ নির্বাচন করার জন্য আপনার প্রম্পট ইনপুটে '# ব্যবহার করুন।",
@@ -514,6 +546,7 @@
 	"Warning": "সতর্কীকরণ",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "সতর্কীকরণ: আপনি যদি আপনার এম্বেডিং মডেল আপডেট বা পরিবর্তন করেন, তাহলে আপনাকে সমস্ত নথি পুনরায় আমদানি করতে হবে।.",
 	"Web": "ওয়েব",
+	"Web API": "",
 	"Web Loader Settings": "ওয়েব লোডার সেটিংস",
 	"Web Params": "ওয়েব প্যারামিটারসমূহ",
 	"Web Search": "ওয়েব অনুসন্ধান",
@@ -524,17 +557,20 @@
 	"WebUI will make requests to": "WebUI যেখানে রিকোয়েস্ট পাঠাবে",
 	"What’s New in": "এতে নতুন কী",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "যদি হিস্টোরি বন্ধ থাকে তাহলে এই ব্রাউজারের নতুন চ্যাটগুলো আপনার কোন ডিভাইসের হিস্টোরিতেই দেখা যাবে না।",
-	"Whisper (Local)": "Whisper (লোকাল)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "ওয়ার্কস্পেস",
 	"Write a prompt suggestion (e.g. Who are you?)": "একটি প্রম্পট সাজেশন লিখুন (যেমন Who are you?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "৫০ শব্দের মধ্যে [topic or keyword] এর একটি সারসংক্ষেপ লিখুন।",
 	"Yesterday": "আগামী",
 	"You": "আপনি",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "আপনি একটি বেস মডেল ক্লোন করতে পারবেন না",
 	"You have no archived conversations.": "আপনার কোনও আর্কাইভ করা কথোপকথন নেই।",
 	"You have shared this chat": "আপনি এই চ্যাটটি শেয়ার করেছেন",
 	"You're a helpful assistant.": "আপনি একজন উপকারী এসিস্ট্যান্ট",
 	"You're now logged in.": "আপনি এখন লগইন করা অবস্থায় আছেন",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "YouTube",
 	"Youtube Loader Settings": "YouTube লোডার সেটিংস"
 }

src/lib/i18n/locales/ca-ES/translation.json

@@ -12,7 +12,9 @@
 	"a user": "un usuari",
 	"About": "Sobre",
 	"Account": "Compte",
+	"Account Activation Pending": "",
 	"Accurate information": "Informació precisa",
+	"Active Users": "",
 	"Add": "Afegir",
 	"Add a model id": "Afegir un identificador de model",
 	"Add a short description about what this model does": "Afegiu una breu descripció sobre què fa aquest model",
@@ -28,6 +30,7 @@
 	"Add User": "Afegir Usuari",
 	"Adjusting these settings will apply changes universally to all users.": "Ajustar aquests paràmetres aplicarà canvis de manera universal a tots els usuaris.",
 	"admin": "administrador",
+	"Admin": "",
 	"Admin Panel": "Panell d'Administració",
 	"Admin Settings": "Configuració d'Administració",
 	"Advanced Parameters": "Paràmetres Avançats",
@@ -58,7 +61,6 @@
 	"Audio": "Àudio",
 	"August": "Agost",
 	"Auto-playback response": "Resposta de reproducció automàtica",
-	"Auto-send input after 3 sec.": "Enviar entrada automàticament després de 3 segons",
 	"AUTOMATIC1111 Base URL": "URL Base AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "Es requereix l'URL Base AUTOMATIC1111.",
 	"available!": "disponible!",
@@ -70,6 +72,9 @@
 	"Being lazy": "Ser l'estupidez",
 	"Brave Search API Key": "Clau API Brave Search",
 	"Bypass SSL verification for Websites": "Desactivar la verificació SSL per a l'accés a l'Internet",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Cancel·la",
 	"Capabilities": "Capacitats",
 	"Change Password": "Canvia la Contrasenya",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Paràmetres de Blocs",
 	"Chunk Size": "Mida del Bloc",
 	"Citation": "Citació",
+	"Clear memory": "",
 	"Click here for help.": "Fes clic aquí per ajuda.",
 	"Click here to": "Fes clic aquí per",
 	"Click here to select": "Fes clic aquí per seleccionar",
 	"Click here to select a csv file.": "Fes clic aquí per seleccionar un fitxer csv.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Fes clic aquí per seleccionar documents.",
 	"click here.": "fes clic aquí.",
 	"Click on the user role button to change a user's role.": "Fes clic al botó de rol d'usuari per canviar el rol d'un usuari.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "Sol·licituds simultànies",
 	"Confirm Password": "Confirma la Contrasenya",
 	"Connections": "Connexions",
+	"Contact Admin for WebUI Access": "",
 	"Content": "Contingut",
 	"Context Length": "Longitud del Context",
 	"Continue Response": "Continua la Resposta",
-	"Conversation Mode": "Mode de Conversa",
 	"Copied shared chat URL to clipboard!": "S'ha copiat l'URL compartida al porta-retalls!",
 	"Copy": "Copiar",
 	"Copy last code block": "Copia l'últim bloc de codi",
 	"Copy last response": "Copia l'última resposta",
 	"Copy Link": "Copiar l'enllaç",
 	"Copying to clipboard was successful!": "La còpia al porta-retalls ha estat exitosa!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Crea una frase concisa de 3-5 paraules com a capçalera per a la següent consulta, seguint estrictament el límit de 3-5 paraules i evitant l'ús de la paraula 'títol':",
 	"Create a model": "Crear un model",
 	"Create Account": "Crea un Compte",
 	"Create new key": "Crea una nova clau",
@@ -126,12 +132,12 @@
 	"Custom": "Personalitzat",
 	"Customize models for a specific purpose": "Personalitzar models per a un propòsit específic",
 	"Dark": "Fosc",
+	"Dashboard": "",
 	"Database": "Base de Dades",
 	"December": "Desembre",
 	"Default": "Per defecte",
 	"Default (Automatic1111)": "Per defecte (Automatic1111)",
 	"Default (SentenceTransformers)": "Per defecte (SentenceTransformers)",
-	"Default (Web API)": "Per defecte (Web API)",
 	"Default Model": "Model per defecte",
 	"Default model updated": "Model per defecte actualitzat",
 	"Default Prompt Suggestions": "Suggeriments de Prompt Per Defecte",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "Descobreix un prompt",
 	"Discover, download, and explore custom prompts": "Descobreix, descarrega i explora prompts personalitzats",
 	"Discover, download, and explore model presets": "Descobreix, descarrega i explora presets de models",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "Mostra el nom d'usuari en lloc de 'Tu' al Xat",
 	"Document": "Document",
 	"Document Settings": "Configuració de Documents",
@@ -194,6 +201,7 @@
 	"Enter Score": "Introdueix el Puntuació",
 	"Enter Searxng Query URL": "Introduïu l'URL de consulta de Searxng",
 	"Enter Serper API Key": "Introduïu la clau de l'API Serper",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "Introduïu la clau de l'API Serpstack",
 	"Enter stop sequence": "Introdueix la seqüència de parada",
 	"Enter Top K": "Introdueix Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "Exporta el Mapatge de Documents",
 	"Export Models": "Models d'exportació",
 	"Export Prompts": "Exporta Prompts",
+	"External Models": "",
 	"Failed to create API Key.": "No s'ha pogut crear la clau d'API.",
 	"Failed to read clipboard contents": "No s'ha pogut llegir el contingut del porta-retalls",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "Siguiu les instruccions perfeicte",
 	"Format your variables using square brackets like this:": "Formata les teves variables utilitzant claudàtors així:",
 	"Frequency Penalty": "Pena de freqüència",
-	"Full Screen Mode": "Mode de Pantalla Completa",
 	"General": "General",
 	"General Settings": "Configuració General",
+	"Generate Image": "",
 	"Generating search query": "Generació de consultes de cerca",
 	"Generation Info": "Informació de Generació",
 	"Good Response": "Resposta bona",
@@ -252,6 +261,7 @@
 	"Info": "Informació",
 	"Input commands": "Entra ordres",
 	"Install from Github URL": "Instal·leu des de l'URL de Github",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Interfície",
 	"Invalid Tag": "Etiqueta Inválida",
 	"January": "Gener",
@@ -264,14 +274,17 @@
 	"JWT Token": "Token JWT",
 	"Keep Alive": "Mantén Actiu",
 	"Keyboard shortcuts": "Dreceres de Teclat",
+	"Knowledge": "",
 	"Language": "Idioma",
 	"Last Active": "Últim Actiu",
 	"Light": "Clar",
-	"Listening...": "Escoltant...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "Els LLMs poden cometre errors. Verifica la informació important.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "Creat per la Comunitat OpenWebUI",
 	"Make sure to enclose them with": "Assegura't d'envoltar-los amb",
+	"Manage": "",
 	"Manage Models": "Gestiona Models",
 	"Manage Ollama Models": "Gestiona Models Ollama",
 	"Manage Pipelines": "Gestionar canonades",
@@ -307,6 +320,7 @@
 	"Name your model": "Posa un nom al model",
 	"New Chat": "Xat Nou",
 	"New Password": "Nova Contrasenya",
+	"No documents found": "",
 	"No results found": "No s'han trobat resultats",
 	"No search query generated": "No es genera cap consulta de cerca",
 	"No source available": "Sense font disponible",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "API d'Ollama",
 	"Ollama API disabled": "L'API d'Ollama desactivada",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Versió d'Ollama",
 	"On": "Activat",
 	"Only": "Només",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "Document PDF (.pdf)",
 	"PDF Extract Images (OCR)": "Extreu Imatges de PDF (OCR)",
 	"pending": "pendent",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Permís denegat en accedir al micròfon: {{error}}",
 	"Personalization": "Personalització",
 	"Pipelines": "Canonades",
@@ -367,6 +384,7 @@
 	"Read Aloud": "Llegiu al voltant",
 	"Record voice": "Enregistra veu",
 	"Redirecting you to OpenWebUI Community": "Redirigint-te a la Comunitat OpenWebUI",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "Refusat quan no hauria d'haver-ho",
 	"Regenerate": "Regenerar",
 	"Release Notes": "Notes de la Versió",
@@ -378,12 +396,14 @@
 	"Reranking Model": "Model de Reranking desactivat",
 	"Reranking model disabled": "Model de Reranking desactivat",
 	"Reranking model set to \"{{reranking_model}}\"": "Model de Reranking establert a \"{{reranking_model}}\"",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "Reinicia l'Emmagatzematge de Vectors",
 	"Response AutoCopy to Clipboard": "Resposta AutoCopiar al Portapapers",
 	"Role": "Rol",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Albada Rosé Pine",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "Guarda",
 	"Save & Create": "Guarda i Crea",
 	"Save & Update": "Guarda i Actualitza",
@@ -397,35 +417,40 @@
 	"Search Documents": "Cerca Documents",
 	"Search Models": "Models de cerca",
 	"Search Prompts": "Cerca Prompts",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "Recompte de resultats de cerca",
 	"Searched {{count}} sites_one": "Cercat {{count}} sites_one",
 	"Searched {{count}} sites_many": "Cercat {{recompte}} sites_many",
 	"Searched {{count}} sites_other": "Cercat {{recompte}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "Cerca a la web de '{{searchQuery}}'",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "Searxng URL de consulta",
 	"See readme.md for instructions": "Consulta el readme.md per a instruccions",
 	"See what's new": "Veure novetats",
 	"Seed": "Llavor",
 	"Select a base model": "Seleccionar un model base",
+	"Select a engine": "",
 	"Select a mode": "Selecciona un mode",
 	"Select a model": "Selecciona un model",
 	"Select a pipeline": "Seleccioneu una canonada",
 	"Select a pipeline url": "Seleccionar un URL de canonada",
 	"Select an Ollama instance": "Selecciona una instància d'Ollama",
+	"Select Documents": "",
 	"Select model": "Selecciona un model",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "Els models seleccionats no admeten l'entrada d'imatges",
 	"Send": "Envia",
 	"Send a Message": "Envia un Missatge",
 	"Send message": "Envia missatge",
 	"September": "Setembre",
 	"Serper API Key": "Clau API Serper",
+	"Serply API Key": "",
 	"Serpstack API Key": "Serpstack API Key",
 	"Server connection verified": "Connexió al servidor verificada",
 	"Set as default": "Estableix com a predeterminat",
 	"Set Default Model": "Estableix Model Predeterminat",
 	"Set embedding model (e.g. {{model}})": "Estableix el model d'emboscada (p.ex. {{model}})",
 	"Set Image Size": "Estableix Mida de la Imatge",
-	"Set Model": "Estableix Model",
 	"Set reranking model (e.g. {{model}})": "Estableix el model de reranking (p.ex. {{model}})",
 	"Set Steps": "Estableix Passos",
 	"Set Task Model": "Defineix el model de tasca",
@@ -449,8 +474,8 @@
 	"Source": "Font",
 	"Speech recognition error: {{error}}": "Error de reconeixement de veu: {{error}}",
 	"Speech-to-Text Engine": "Motor de Veu a Text",
-	"SpeechRecognition API is not supported in this browser.": "L'API de Reconèixer Veu no és compatible amb aquest navegador.",
 	"Stop Sequence": "Atura Seqüència",
+	"STT Model": "",
 	"STT Settings": "Configuracions STT",
 	"Submit": "Envia",
 	"Subtitle (e.g. about the Roman Empire)": "Subtítol (per exemple, sobre l'Imperi Romà)",
@@ -469,7 +494,9 @@
 	"Thanks for your feedback!": "Gràcies pel teu comentari!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "El puntuatge ha de ser un valor entre 0.0 (0%) i 1.0 (100%).",
 	"Theme": "Tema",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Això assegura que les teves converses valuoses queden segurament guardades a la teva base de dades backend. Gràcies!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "Aquesta configuració no es sincronitza entre navegadors ni dispositius.",
 	"Thorough explanation": "Explacació exhaustiva",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Consell: Actualitza diversos espais de variables consecutivament prement la tecla de tabulació en l'entrada del xat després de cada reemplaçament.",
@@ -481,6 +508,8 @@
 	"to": "a",
 	"To access the available model names for downloading,": "Per accedir als noms dels models disponibles per descarregar,",
 	"To access the GGUF models available for downloading,": "Per accedir als models GGUF disponibles per descarregar,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "a l'entrada del xat.",
 	"Today": "Avui",
 	"Toggle settings": "Commuta configuracions",
@@ -488,7 +517,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "Problemes accedint a Ollama?",
+	"TTS Model": "",
 	"TTS Settings": "Configuracions TTS",
+	"TTS Voice": "",
 	"Type": "Tipus",
 	"Type Hugging Face Resolve (Download) URL": "Escriu URL de Resolució (Descàrrega) de Hugging Face",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Uf! Hi va haver un problema connectant-se a {{provider}}.",
@@ -497,6 +528,7 @@
 	"Update password": "Actualitza contrasenya",
 	"Upload a GGUF model": "Puja un model GGUF",
 	"Upload Files": "Pujar fitxers",
+	"Upload Pipeline": "",
 	"Upload Progress": "Progrés de Càrrega",
 	"URL Mode": "Mode URL",
 	"Use '#' in the prompt input to load and select your documents.": "Utilitza '#' a l'entrada del prompt per carregar i seleccionar els teus documents.",
@@ -515,6 +547,7 @@
 	"Warning": "Advertiment",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Avís: Si actualitzeu o canvieu el model d'incrustació, haureu de tornar a importar tots els documents.",
 	"Web": "Web",
+	"Web API": "",
 	"Web Loader Settings": "Configuració del carregador web",
 	"Web Params": "Paràmetres web",
 	"Web Search": "Cercador web",
@@ -525,17 +558,20 @@
 	"WebUI will make requests to": "WebUI farà peticions a",
 	"What’s New in": "Què hi ha de Nou en",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "Quan l'historial està desactivat, els nous xats en aquest navegador no apareixeran en el teu historial en cap dels teus dispositius.",
-	"Whisper (Local)": "Whisper (Local)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "Treball",
 	"Write a prompt suggestion (e.g. Who are you?)": "Escriu una suggerència de prompt (p. ex. Qui ets tu?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Escriu un resum en 50 paraules que resumeixi [tema o paraula clau].",
 	"Yesterday": "Ayer",
 	"You": "Tu",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "No es pot clonar un model base",
 	"You have no archived conversations.": "No tens converses arxivades.",
 	"You have shared this chat": "Has compartit aquest xat",
 	"You're a helpful assistant.": "Ets un assistent útil.",
 	"You're now logged in.": "Ara estàs connectat.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "Configuració del carregador de Youtube"
 }

src/lib/i18n/locales/ceb-PH/translation.json

@@ -12,7 +12,9 @@
 	"a user": "usa ka user",
 	"About": "Mahitungod sa",
 	"Account": "Account",
+	"Account Activation Pending": "",
 	"Accurate information": "",
+	"Active Users": "",
 	"Add": "",
 	"Add a model id": "",
 	"Add a short description about what this model does": "",
@@ -28,6 +30,7 @@
 	"Add User": "",
 	"Adjusting these settings will apply changes universally to all users.": "Ang pag-adjust niini nga mga setting magamit ang mga pagbag-o sa tanan nga tiggamit.",
 	"admin": "Administrator",
+	"Admin": "",
 	"Admin Panel": "Admin Panel",
 	"Admin Settings": "Mga setting sa administratibo",
 	"Advanced Parameters": "advanced settings",
@@ -58,7 +61,6 @@
 	"Audio": "Audio",
 	"August": "",
 	"Auto-playback response": "Autoplay nga tubag",
-	"Auto-send input after 3 sec.": "Awtomatikong ipadala ang entry pagkahuman sa 3 segundos.",
 	"AUTOMATIC1111 Base URL": "Base URL AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "Ang AUTOMATIC1111 base URL gikinahanglan.",
 	"available!": "magamit!",
@@ -70,6 +72,9 @@
 	"Being lazy": "",
 	"Brave Search API Key": "",
 	"Bypass SSL verification for Websites": "",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Pagkanselar",
 	"Capabilities": "",
 	"Change Password": "Usba ang password",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Mga Setting sa Block",
 	"Chunk Size": "Gidak-on sa block",
 	"Citation": "Mga kinutlo",
+	"Clear memory": "",
 	"Click here for help.": "I-klik dinhi alang sa tabang.",
 	"Click here to": "",
 	"Click here to select": "I-klik dinhi aron makapili",
 	"Click here to select a csv file.": "",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Pag-klik dinhi aron mapili ang mga dokumento.",
 	"click here.": "I-klik dinhi.",
 	"Click on the user role button to change a user's role.": "I-klik ang User Role button aron usbon ang role sa user.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "",
 	"Confirm Password": "Kumpirma ang password",
 	"Connections": "Mga koneksyon",
+	"Contact Admin for WebUI Access": "",
 	"Content": "Kontento",
 	"Context Length": "Ang gitas-on sa konteksto",
 	"Continue Response": "",
-	"Conversation Mode": "Talk mode",
 	"Copied shared chat URL to clipboard!": "",
 	"Copy": "",
 	"Copy last code block": "Kopyaha ang katapusang bloke sa code",
 	"Copy last response": "Kopyaha ang kataposang tubag",
 	"Copy Link": "",
 	"Copying to clipboard was successful!": "Ang pagkopya sa clipboard malampuson!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Paghimo og mugbo nga 3-5 ka pulong nga sentence isip usa ka ulohan alang sa mosunod nga pangutana, hugot nga pagsunod sa 3-5 ka pulong nga limitasyon ug paglikay sa paggamit sa pulong nga 'titulo':",
 	"Create a model": "",
 	"Create Account": "Paghimo og account",
 	"Create new key": "",
@@ -126,12 +132,12 @@
 	"Custom": "Custom",
 	"Customize models for a specific purpose": "",
 	"Dark": "Ngitngit",
+	"Dashboard": "",
 	"Database": "Database",
 	"December": "",
 	"Default": "Pinaagi sa default",
 	"Default (Automatic1111)": "Default (Awtomatiko1111)",
 	"Default (SentenceTransformers)": "",
-	"Default (Web API)": "Default (Web API)",
 	"Default Model": "",
 	"Default model updated": "Gi-update nga default template",
 	"Default Prompt Suggestions": "Default nga prompt nga mga sugyot",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "Pagkaplag usa ka prompt",
 	"Discover, download, and explore custom prompts": "Pagdiskubre, pag-download ug pagsuhid sa mga naandan nga pag-aghat",
 	"Discover, download, and explore model presets": "Pagdiskobre, pag-download, ug pagsuhid sa mga preset sa template",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "Ipakita ang username imbes nga 'Ikaw' sa Panaghisgutan",
 	"Document": "Dokumento",
 	"Document Settings": "Mga Setting sa Dokumento",
@@ -194,6 +201,7 @@
 	"Enter Score": "",
 	"Enter Searxng Query URL": "",
 	"Enter Serper API Key": "",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "",
 	"Enter stop sequence": "Pagsulod sa katapusan nga han-ay",
 	"Enter Top K": "Pagsulod sa Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "I-export ang pagmapa sa dokumento",
 	"Export Models": "",
 	"Export Prompts": "Export prompts",
+	"External Models": "",
 	"Failed to create API Key.": "",
 	"Failed to read clipboard contents": "Napakyas sa pagbasa sa sulod sa clipboard",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "",
 	"Format your variables using square brackets like this:": "I-format ang imong mga variable gamit ang square brackets sama niini:",
 	"Frequency Penalty": "",
-	"Full Screen Mode": "Full screen mode",
 	"General": "Heneral",
 	"General Settings": "kinatibuk-ang mga setting",
+	"Generate Image": "",
 	"Generating search query": "",
 	"Generation Info": "",
 	"Good Response": "",
@@ -252,6 +261,7 @@
 	"Info": "",
 	"Input commands": "Pagsulod sa input commands",
 	"Install from Github URL": "",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Interface",
 	"Invalid Tag": "",
 	"January": "",
@@ -264,14 +274,17 @@
 	"JWT Token": "JWT token",
 	"Keep Alive": "Padayon nga aktibo",
 	"Keyboard shortcuts": "Mga shortcut sa keyboard",
+	"Knowledge": "",
 	"Language": "Pinulongan",
 	"Last Active": "",
 	"Light": "Kahayag",
-	"Listening...": "Paminaw...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "Ang mga LLM mahimong masayop. ",
+	"Local Models": "",
 	"LTR": "",
 	"Made by OpenWebUI Community": "Gihimo sa komunidad sa OpenWebUI",
 	"Make sure to enclose them with": "Siguruha nga palibutan sila",
+	"Manage": "",
 	"Manage Models": "Pagdumala sa mga templates",
 	"Manage Ollama Models": "Pagdumala sa mga modelo sa Ollama",
 	"Manage Pipelines": "",
@@ -307,6 +320,7 @@
 	"Name your model": "",
 	"New Chat": "Bag-ong diskusyon",
 	"New Password": "Bag-ong Password",
+	"No documents found": "",
 	"No results found": "",
 	"No search query generated": "",
 	"No source available": "Walay tinubdan nga anaa",
@@ -323,6 +337,7 @@
 	"Ollama": "",
 	"Ollama API": "",
 	"Ollama API disabled": "",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Ollama nga bersyon",
 	"On": "Gipaandar",
 	"Only": "Lamang",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "",
 	"PDF Extract Images (OCR)": "PDF Image Extraction (OCR)",
 	"pending": "gipugngan",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Gidili ang pagtugot sa dihang nag-access sa mikropono: {{error}}",
 	"Personalization": "",
 	"Pipelines": "",
@@ -367,6 +384,7 @@
 	"Read Aloud": "",
 	"Record voice": "Irekord ang tingog",
 	"Redirecting you to OpenWebUI Community": "Gi-redirect ka sa komunidad sa OpenWebUI",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "",
 	"Regenerate": "",
 	"Release Notes": "Release Notes",
@@ -378,12 +396,14 @@
 	"Reranking Model": "",
 	"Reranking model disabled": "",
 	"Reranking model set to \"{{reranking_model}}\"": "",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "I-reset ang pagtipig sa vector",
 	"Response AutoCopy to Clipboard": "Awtomatikong kopya sa tubag sa clipboard",
 	"Role": "Papel",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Aube Pine Rosé",
 	"RTL": "",
+	"Running": "",
 	"Save": "Tipigi",
 	"Save & Create": "I-save ug Paghimo",
 	"Save & Update": "I-save ug I-update",
@@ -397,34 +417,39 @@
 	"Search Documents": "Pangitaa ang mga dokumento",
 	"Search Models": "",
 	"Search Prompts": "Pangitaa ang mga prompt",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "",
 	"Searched {{count}} sites_one": "",
 	"Searched {{count}} sites_other": "",
-	"Searching the web for '{{searchQuery}}'": "",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "",
 	"See readme.md for instructions": "Tan-awa ang readme.md alang sa mga panudlo",
 	"See what's new": "Tan-awa unsay bag-o",
 	"Seed": "Binhi",
 	"Select a base model": "",
+	"Select a engine": "",
 	"Select a mode": "Pagpili og mode",
 	"Select a model": "Pagpili og modelo",
 	"Select a pipeline": "",
 	"Select a pipeline url": "",
 	"Select an Ollama instance": "Pagpili usa ka pananglitan sa Ollama",
+	"Select Documents": "",
 	"Select model": "Pagpili og modelo",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "",
 	"Send": "",
 	"Send a Message": "Magpadala ug mensahe",
 	"Send message": "Magpadala ug mensahe",
 	"September": "",
 	"Serper API Key": "",
+	"Serply API Key": "",
 	"Serpstack API Key": "",
 	"Server connection verified": "Gipamatud-an nga koneksyon sa server",
 	"Set as default": "Define pinaagi sa default",
 	"Set Default Model": "Ibutang ang default template",
 	"Set embedding model (e.g. {{model}})": "",
 	"Set Image Size": "Ibutang ang gidak-on sa hulagway",
-	"Set Model": "I-configure ang template",
 	"Set reranking model (e.g. {{model}})": "",
 	"Set Steps": "Ipasabot ang mga lakang",
 	"Set Task Model": "",
@@ -448,8 +473,8 @@
 	"Source": "Tinubdan",
 	"Speech recognition error: {{error}}": "Sayop sa pag-ila sa tingog: {{error}}",
 	"Speech-to-Text Engine": "Engine sa pag-ila sa tingog",
-	"SpeechRecognition API is not supported in this browser.": "Ang SpeechRecognition API wala gisuportahan niini nga browser.",
 	"Stop Sequence": "Pagkasunod-sunod sa pagsira",
+	"STT Model": "",
 	"STT Settings": "Mga setting sa STT",
 	"Submit": "Isumite",
 	"Subtitle (e.g. about the Roman Empire)": "",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "",
 	"Theme": "Tema",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Kini nagsiguro nga ang imong bililhon nga mga panag-istoryahanay luwas nga natipig sa imong backend database. ",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "Kini nga setting wala mag-sync tali sa mga browser o device.",
 	"Thorough explanation": "",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Sugyot: Pag-update sa daghang variable nga lokasyon nga sunud-sunod pinaagi sa pagpindot sa tab key sa chat entry pagkahuman sa matag puli.",
@@ -480,6 +507,8 @@
 	"to": "adunay",
 	"To access the available model names for downloading,": "Aron ma-access ang mga ngalan sa modelo nga ma-download,",
 	"To access the GGUF models available for downloading,": "Aron ma-access ang mga modelo sa GGUF nga magamit alang sa pag-download,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "sa entrada sa iring.",
 	"Today": "",
 	"Toggle settings": "I-toggle ang mga setting",
@@ -487,7 +516,9 @@
 	"Top K": "Top K",
 	"Top P": "Ibabaw nga P",
 	"Trouble accessing Ollama?": "Adunay mga problema sa pag-access sa Ollama?",
+	"TTS Model": "",
 	"TTS Settings": "Mga Setting sa TTS",
+	"TTS Voice": "",
 	"Type": "",
 	"Type Hugging Face Resolve (Download) URL": "Pagsulod sa resolusyon (pag-download) URL Hugging Face",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Uh-oh!  {{provider}}.",
@@ -496,6 +527,7 @@
 	"Update password": "I-update ang password",
 	"Upload a GGUF model": "Pag-upload ug modelo sa GGUF",
 	"Upload Files": "",
+	"Upload Pipeline": "",
 	"Upload Progress": "Pag-uswag sa Pag-upload",
 	"URL Mode": "URL mode",
 	"Use '#' in the prompt input to load and select your documents.": "Gamita ang '#' sa dali nga pagsulod aron makarga ug mapili ang imong mga dokumento.",
@@ -514,6 +546,7 @@
 	"Warning": "",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "",
 	"Web": "Web",
+	"Web API": "",
 	"Web Loader Settings": "",
 	"Web Params": "",
 	"Web Search": "",
@@ -524,17 +557,20 @@
 	"WebUI will make requests to": "Ang WebUI maghimo mga hangyo sa",
 	"What’s New in": "Unsay bag-o sa",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "Kung ang kasaysayan gipalong, ang mga bag-ong chat sa kini nga browser dili makita sa imong kasaysayan sa bisan unsang mga aparato.",
-	"Whisper (Local)": "Whisper (Lokal)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "",
 	"Write a prompt suggestion (e.g. Who are you?)": "Pagsulat og gisugyot nga prompt (eg. Kinsa ka?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Pagsulat og 50 ka pulong nga summary nga nagsumaryo [topic o keyword].",
 	"Yesterday": "",
 	"You": "",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "",
 	"You have no archived conversations.": "",
 	"You have shared this chat": "",
 	"You're a helpful assistant.": "Usa ka ka mapuslanon nga katabang",
 	"You're now logged in.": "Konektado ka na karon.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "",
 	"Youtube Loader Settings": ""
 }

src/lib/i18n/locales/de-DE/translation.json

@@ -12,7 +12,9 @@
 	"a user": "ein Benutzer",
 	"About": "Über",
 	"Account": "Account",
+	"Account Activation Pending": "",
 	"Accurate information": "Genaue Information",
+	"Active Users": "Aktive Benutzer",
 	"Add": "Hinzufügen",
 	"Add a model id": "Hinzufügen einer Modell-ID",
 	"Add a short description about what this model does": "Fügen Sie eine kurze Beschreibung hinzu, was dieses Modell tut",
@@ -28,6 +30,7 @@
 	"Add User": "User hinzufügen",
 	"Adjusting these settings will apply changes universally to all users.": "Das Anpassen dieser Einstellungen wirkt sich universell auf alle Benutzer aus.",
 	"admin": "Administrator",
+	"Admin": "",
 	"Admin Panel": "Admin Panel",
 	"Admin Settings": "Admin Einstellungen",
 	"Advanced Parameters": "Erweiterte Parameter",
@@ -37,7 +40,7 @@
 	"All Users": "Alle Benutzer",
 	"Allow": "Erlauben",
 	"Allow Chat Deletion": "Chat Löschung erlauben",
-	"Allow non-local voices": "",
+	"Allow non-local voices": "Nicht-lokale Stimmen erlauben",
 	"alphanumeric characters and hyphens": "alphanumerische Zeichen und Bindestriche",
 	"Already have an account?": "Hast du vielleicht schon ein Account?",
 	"an assistant": "ein Assistent",
@@ -58,7 +61,6 @@
 	"Audio": "Audio",
 	"August": "August",
 	"Auto-playback response": "Automatische Wiedergabe der Antwort",
-	"Auto-send input after 3 sec.": "Automatisches Senden der Eingabe nach 3 Sek",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 Basis URL",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 Basis URL wird benötigt",
 	"available!": "verfügbar!",
@@ -70,6 +72,9 @@
 	"Being lazy": "Faul sein",
 	"Brave Search API Key": "API-Schlüssel für die Brave-Suche",
 	"Bypass SSL verification for Websites": "Bypass SSL-Verifizierung für Websites",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Abbrechen",
 	"Capabilities": "Fähigkeiten",
 	"Change Password": "Passwort ändern",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Chunk Parameter",
 	"Chunk Size": "Chunk Size",
 	"Citation": "Zitate",
+	"Clear memory": "Memory löschen",
 	"Click here for help.": "Klicke hier für Hilfe.",
 	"Click here to": "Klicke hier, um",
 	"Click here to select": "Klicke hier um auszuwählen",
 	"Click here to select a csv file.": "Klicke hier um eine CSV-Datei auszuwählen.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Klicke hier um Dokumente auszuwählen",
 	"click here.": "hier klicken.",
 	"Click on the user role button to change a user's role.": "Klicke auf die Benutzerrollenschaltfläche, um die Rolle eines Benutzers zu ändern.",
@@ -104,18 +111,17 @@
 	"Concurrent Requests": "Gleichzeitige Anforderungen",
 	"Confirm Password": "Passwort bestätigen",
 	"Connections": "Verbindungen",
-	"Content": "Inhalt",
+	"Contact Admin for WebUI Access": "",
+	"Content": "Info",
 	"Context Length": "Context Length",
 	"Continue Response": "Antwort fortsetzen",
-	"Conversation Mode": "Konversationsmodus",
 	"Copied shared chat URL to clipboard!": "Geteilte Chat-URL in die Zwischenablage kopiert!",
 	"Copy": "Kopieren",
 	"Copy last code block": "Letzten Codeblock kopieren",
 	"Copy last response": "Letzte Antwort kopieren",
 	"Copy Link": "Link kopieren",
 	"Copying to clipboard was successful!": "Das Kopieren in die Zwischenablage war erfolgreich!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Erstelle einen prägnanten Satz mit 3-5 Wörtern als Überschrift für die folgende Abfrage. Halte dich dabei strikt an die 3-5-Wort-Grenze und vermeide die Verwendung des Wortes Titel:",
-	"Create a model": "Erstellen eines Modells",
+	"Create a model": "Ein Modell erstellen",
 	"Create Account": "Konto erstellen",
 	"Create new key": "Neuen Schlüssel erstellen",
 	"Create new secret key": "Neuen API Schlüssel erstellen",
@@ -126,12 +132,12 @@
 	"Custom": "Benutzerdefiniert",
 	"Customize models for a specific purpose": "Modelle für einen bestimmten Zweck anpassen",
 	"Dark": "Dunkel",
+	"Dashboard": "",
 	"Database": "Datenbank",
 	"December": "Dezember",
 	"Default": "Standard",
 	"Default (Automatic1111)": "Standard (Automatic1111)",
 	"Default (SentenceTransformers)": "Standard (SentenceTransformers)",
-	"Default (Web API)": "Standard (Web-API)",
 	"Default Model": "Standardmodell",
 	"Default model updated": "Standardmodell aktualisiert",
 	"Default Prompt Suggestions": "Standard-Prompt-Vorschläge",
@@ -152,10 +158,11 @@
 	"Discover a prompt": "Einen Prompt entdecken",
 	"Discover, download, and explore custom prompts": "Benutzerdefinierte Prompts entdecken, herunterladen und erkunden",
 	"Discover, download, and explore model presets": "Modellvorgaben entdecken, herunterladen und erkunden",
+	"Dismissible": "ausblendbar",
 	"Display the username instead of You in the Chat": "Den Benutzernamen anstelle von 'du' im Chat anzeigen",
 	"Document": "Dokument",
 	"Document Settings": "Dokumenteinstellungen",
-	"Documentation": "",
+	"Documentation": "Dokumentation",
 	"Documents": "Dokumente",
 	"does not make any external connections, and your data stays securely on your locally hosted server.": "stellt keine externen Verbindungen her, und Deine Daten bleiben sicher auf Deinen lokal gehosteten Server.",
 	"Don't Allow": "Nicht erlauben",
@@ -170,7 +177,7 @@
 	"Edit Doc": "Dokument bearbeiten",
 	"Edit User": "Benutzer bearbeiten",
 	"Email": "E-Mail",
-	"Embedding Batch Size": "",
+	"Embedding Batch Size": "Embedding Batch Größe",
 	"Embedding Model": "Embedding-Modell",
 	"Embedding Model Engine": "Embedding-Modell-Engine",
 	"Embedding model set to \"{{embedding_model}}\"": "Embedding-Modell auf \"{{embedding_model}}\" gesetzt",
@@ -194,40 +201,42 @@
 	"Enter Score": "Score eingeben",
 	"Enter Searxng Query URL": "Geben Sie die Searxng-Abfrage-URL ein",
 	"Enter Serper API Key": "Serper-API-Schlüssel eingeben",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "Geben Sie den Serpstack-API-Schlüssel ein",
 	"Enter stop sequence": "Stop-Sequenz eingeben",
 	"Enter Top K": "Gib Top K ein",
 	"Enter URL (e.g. http://127.0.0.1:7860/)": "Gib die URL ein (z.B. http://127.0.0.1:7860/)",
 	"Enter URL (e.g. http://localhost:11434)": "Gib die URL ein (z.B. http://localhost:11434)",
-	"Enter Your Email": "Gib deine E-Mail-Adresse ein",
-	"Enter Your Full Name": "Gib deinen vollständigen Namen ein",
-	"Enter Your Password": "Gib dein Passwort ein",
+	"Enter Your Email": "E-Mail-Adresse",
+	"Enter Your Full Name": "Name",
+	"Enter Your Password": "Passwort",
 	"Enter Your Role": "Gebe deine Rolle ein",
 	"Error": "Fehler",
 	"Experimental": "Experimentell",
 	"Export": "Exportieren",
 	"Export All Chats (All Users)": "Alle Chats exportieren (alle Benutzer)",
-	"Export chat (.json)": "",
+	"Export chat (.json)": "Chat exportieren (.json)",
 	"Export Chats": "Chats exportieren",
 	"Export Documents Mapping": "Dokumentenmapping exportieren",
 	"Export Models": "Modelle exportieren",
 	"Export Prompts": "Prompts exportieren",
+	"External Models": "",
 	"Failed to create API Key.": "API Key erstellen fehlgeschlagen",
 	"Failed to read clipboard contents": "Fehler beim Lesen des Zwischenablageninhalts",
-	"Failed to update settings": "",
+	"Failed to update settings": "Fehler beim Aktualisieren der Einstellungen",
 	"February": "Februar",
 	"Feel free to add specific details": "Ergänze Details.",
 	"File Mode": "File Modus",
 	"File not found.": "Datei nicht gefunden.",
 	"Fingerprint spoofing detected: Unable to use initials as avatar. Defaulting to default profile image.": "Fingerprint spoofing erkannt: Initialen können nicht als Avatar verwendet werden. Es wird auf das Standardprofilbild zurückgegriffen.",
-	"Fluidly stream large external response chunks": "Streamen Sie große externe Antwortblöcke flüssig",
+	"Fluidly stream large external response chunks": "Große externe Antwortblöcke flüssig streamen",
 	"Focus chat input": "Chat-Eingabe fokussieren",
 	"Followed instructions perfectly": "Anweisungen perfekt befolgt",
 	"Format your variables using square brackets like this:": "Formatiere deine Variablen mit eckigen Klammern wie folgt:",
 	"Frequency Penalty": "Frequenz-Strafe",
-	"Full Screen Mode": "Vollbildmodus",
 	"General": "Allgemein",
 	"General Settings": "Allgemeine Einstellungen",
+	"Generate Image": "",
 	"Generating search query": "Suchanfrage generieren",
 	"Generation Info": "Generierungsinformationen",
 	"Good Response": "Gute Antwort",
@@ -252,6 +261,7 @@
 	"Info": "Info",
 	"Input commands": "Eingabebefehle",
 	"Install from Github URL": "Installieren Sie von der Github-URL",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Benutzeroberfläche",
 	"Invalid Tag": "Ungültiger Tag",
 	"January": "Januar",
@@ -264,14 +274,17 @@
 	"JWT Token": "JWT-Token",
 	"Keep Alive": "Keep Alive",
 	"Keyboard shortcuts": "Tastenkürzel",
+	"Knowledge": "",
 	"Language": "Sprache",
 	"Last Active": "Zuletzt aktiv",
 	"Light": "Hell",
-	"Listening...": "Hören...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "LLMs können Fehler machen. Überprüfe wichtige Informationen.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "Von der OpenWebUI-Community",
 	"Make sure to enclose them with": "Formatiere deine Variablen mit:",
+	"Manage": "Verwalten",
 	"Manage Models": "Modelle verwalten",
 	"Manage Ollama Models": "Ollama-Modelle verwalten",
 	"Manage Pipelines": "Verwalten von Pipelines",
@@ -307,6 +320,7 @@
 	"Name your model": "Benennen Sie Ihr Modell",
 	"New Chat": "Neuer Chat",
 	"New Password": "Neues Passwort",
+	"No documents found": "",
 	"No results found": "Keine Ergebnisse gefunden",
 	"No search query generated": "Keine Suchanfrage generiert",
 	"No source available": "Keine Quelle verfügbar.",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama-API",
 	"Ollama API disabled": "Ollama-API deaktiviert",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Ollama-Version",
 	"On": "Ein",
 	"Only": "Nur",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "PDF-Dokument (.pdf)",
 	"PDF Extract Images (OCR)": "Text von Bildern aus PDFs extrahieren (OCR)",
 	"pending": "ausstehend",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Zugriff auf das Mikrofon verweigert: {{error}}",
 	"Personalization": "Personalisierung",
 	"Pipelines": "Pipelines",
@@ -362,11 +379,12 @@
 	"Prompts": "Prompts",
 	"Pull \"{{searchValue}}\" from Ollama.com": "\"{{searchValue}}\" von Ollama.com herunterladen",
 	"Pull a model from Ollama.com": "Ein Modell von Ollama.com abrufen",
-	"Query Params": "Query Parameter",
-	"RAG Template": "RAG-Vorlage",
+	"Query Params": "Abfrage Parameter",
+	"RAG Template": "RAG-Template",
 	"Read Aloud": "Vorlesen",
 	"Record voice": "Stimme aufnehmen",
 	"Redirecting you to OpenWebUI Community": "Du wirst zur OpenWebUI-Community weitergeleitet",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "Abgelehnt, obwohl es nicht hätte sein sollen.",
 	"Regenerate": "Neu generieren",
 	"Release Notes": "Versionshinweise",
@@ -378,12 +396,14 @@
 	"Reranking Model": "Reranking Modell",
 	"Reranking model disabled": "Rranking Modell deaktiviert",
 	"Reranking model set to \"{{reranking_model}}\"": "Reranking Modell auf \"{{reranking_model}}\" gesetzt",
+	"Reset Upload Directory": "Uploadverzeichnis löschen",
 	"Reset Vector Storage": "Vektorspeicher zurücksetzen",
 	"Response AutoCopy to Clipboard": "Antwort automatisch in die Zwischenablage kopieren",
 	"Role": "Rolle",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Rosé Pine Dawn",
 	"RTL": "RTL",
+	"Running": "Läuft",
 	"Save": "Speichern",
 	"Save & Create": "Speichern und erstellen",
 	"Save & Update": "Speichern und aktualisieren",
@@ -397,47 +417,52 @@
 	"Search Documents": "Dokumente suchen",
 	"Search Models": "Modelle suchen",
 	"Search Prompts": "Prompts suchen",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "Anzahl der Suchergebnisse",
 	"Searched {{count}} sites_one": "Gesucht {{count}} sites_one",
 	"Searched {{count}} sites_other": "Gesucht {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "Suche im Web nach '{{searchQuery}}'",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "Searxng-Abfrage-URL",
 	"See readme.md for instructions": "Anleitung in readme.md anzeigen",
 	"See what's new": "Was gibt's Neues",
 	"Seed": "Seed",
 	"Select a base model": "Wählen Sie ein Basismodell",
+	"Select a engine": "Wähle eine Engine",
 	"Select a mode": "Einen Modus auswählen",
 	"Select a model": "Ein Modell auswählen",
 	"Select a pipeline": "Wählen Sie eine Pipeline aus",
 	"Select a pipeline url": "Auswählen einer Pipeline-URL",
 	"Select an Ollama instance": "Eine Ollama Instanz auswählen",
+	"Select Documents": "",
 	"Select model": "Modell auswählen",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "Ausgewählte Modelle unterstützen keine Bildeingaben",
 	"Send": "Senden",
 	"Send a Message": "Eine Nachricht senden",
 	"Send message": "Nachricht senden",
 	"September": "September",
 	"Serper API Key": "Serper-API-Schlüssel",
+	"Serply API Key": "",
 	"Serpstack API Key": "Serpstack-API-Schlüssel",
 	"Server connection verified": "Serververbindung überprüft",
 	"Set as default": "Als Standard festlegen",
 	"Set Default Model": "Standardmodell festlegen",
 	"Set embedding model (e.g. {{model}})": "Eingabemodell festlegen (z.B. {{model}})",
 	"Set Image Size": "Bildgröße festlegen",
-	"Set Model": "Modell festlegen",
 	"Set reranking model (e.g. {{model}})": "Rerankingmodell festlegen (z.B. {{model}})",
 	"Set Steps": "Schritte festlegen",
 	"Set Task Model": "Aufgabenmodell festlegen",
 	"Set Voice": "Stimme festlegen",
 	"Settings": "Einstellungen",
 	"Settings saved successfully!": "Einstellungen erfolgreich gespeichert!",
-	"Settings updated successfully": "",
+	"Settings updated successfully": "Settings updated successfully",
 	"Share": "Teilen",
 	"Share Chat": "Chat teilen",
 	"Share to OpenWebUI Community": "Mit OpenWebUI Community teilen",
 	"short-summary": "kurze-zusammenfassung",
 	"Show": "Anzeigen",
-	"Show Admin Details in Account Pending Overlay": "",
+	"Show Admin Details in Account Pending Overlay": "Admin-Details im Account-Pending-Overlay anzeigen",
 	"Show shortcuts": "Verknüpfungen anzeigen",
 	"Showcased creativity": "Kreativität zur Schau gestellt",
 	"sidebar": "Seitenleiste",
@@ -448,8 +473,8 @@
 	"Source": "Quellen",
 	"Speech recognition error: {{error}}": "Spracherkennungsfehler: {{error}}",
 	"Speech-to-Text Engine": "Sprache-zu-Text-Engine",
-	"SpeechRecognition API is not supported in this browser.": "Die Spracherkennungs-API wird in diesem Browser nicht unterstützt.",
 	"Stop Sequence": "Stop Sequence",
+	"STT Model": "",
 	"STT Settings": "STT-Einstellungen",
 	"Submit": "Senden",
 	"Subtitle (e.g. about the Roman Empire)": "Untertitel (z.B. über das Römische Reich)",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "Danke für dein Feedback",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "Der Score sollte ein Wert zwischen 0,0 (0 %) und 1,0 (100 %) sein.",
 	"Theme": "Design",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Dadurch werden deine wertvollen Unterhaltungen sicher in der Backend-Datenbank gespeichert. Vielen Dank!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "Diese Einstellung wird nicht zwischen Browsern oder Geräten synchronisiert.",
 	"Thorough explanation": "Genaue Erklärung",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Tipp: Aktualisiere mehrere Variablen nacheinander, indem du nach jeder Aktualisierung die Tabulatortaste im Chat-Eingabefeld drückst.",
@@ -480,6 +507,8 @@
 	"to": "für",
 	"To access the available model names for downloading,": "Um auf die verfügbaren Modellnamen zum Herunterladen zuzugreifen,",
 	"To access the GGUF models available for downloading,": "Um auf die verfügbaren GGUF Modelle zum Herunterladen zuzugreifen",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "to chat input.",
 	"Today": "Heute",
 	"Toggle settings": "Einstellungen umschalten",
@@ -487,7 +516,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "Probleme beim Zugriff auf Ollama?",
+	"TTS Model": "",
 	"TTS Settings": "TTS-Einstellungen",
+	"TTS Voice": "",
 	"Type": "Art",
 	"Type Hugging Face Resolve (Download) URL": "Gib die Hugging Face Resolve (Download) URL ein",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Ups! Es gab ein Problem bei der Verbindung mit {{provider}}.",
@@ -496,6 +527,7 @@
 	"Update password": "Passwort aktualisieren",
 	"Upload a GGUF model": "GGUF Model hochladen",
 	"Upload Files": "Dateien hochladen",
+	"Upload Pipeline": "",
 	"Upload Progress": "Upload Progress",
 	"URL Mode": "URL Modus",
 	"Use '#' in the prompt input to load and select your documents.": "Verwende '#' in der Prompt-Eingabe, um deine Dokumente zu laden und auszuwählen.",
@@ -514,6 +546,7 @@
 	"Warning": "Warnung",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Warnung: Wenn du dein Einbettungsmodell aktualisierst oder änderst, musst du alle Dokumente erneut importieren.",
 	"Web": "Web",
+	"Web API": "",
 	"Web Loader Settings": "Web Loader Einstellungen",
 	"Web Params": "Web Parameter",
 	"Web Search": "Websuche",
@@ -524,17 +557,20 @@
 	"WebUI will make requests to": "Wenn aktiviert sendet WebUI externe Anfragen an",
 	"What’s New in": "Was gibt's Neues in",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "Wenn die Historie ausgeschaltet ist, werden neue Chats nicht in deiner Historie auf deine Geräte angezeigt.",
-	"Whisper (Local)": "Whisper (Lokal)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "Widescreen Modus",
 	"Workspace": "Arbeitsbereich",
 	"Write a prompt suggestion (e.g. Who are you?)": "Gebe einen Prompt-Vorschlag ein (z.B. Wer bist du?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Schreibe eine kurze Zusammenfassung in 50 Wörtern, die [Thema oder Schlüsselwort] zusammenfasst.",
 	"Yesterday": "Gestern",
 	"You": "Du",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "Du kannst deine Interaktionen mit LLMs personalisieren, indem du Erinnerungen durch den 'Verwalten'-Button unten hinzufügst, um sie hilfreicher und auf dich zugeschnitten zu machen.",
 	"You cannot clone a base model": "Sie können ein Basismodell nicht klonen",
 	"You have no archived conversations.": "Du hast keine archivierten Unterhaltungen.",
 	"You have shared this chat": "Du hast diesen Chat",
 	"You're a helpful assistant.": "Du bist ein hilfreicher Assistent.",
 	"You're now logged in.": "Du bist nun eingeloggt.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "YouTube",
 	"Youtube Loader Settings": "YouTube-Ladeeinstellungen"
 }

src/lib/i18n/locales/dg-DG/translation.json

@@ -12,7 +12,9 @@
 	"a user": "such user",
 	"About": "Much About",
 	"Account": "Account",
+	"Account Activation Pending": "",
 	"Accurate information": "",
+	"Active Users": "",
 	"Add": "",
 	"Add a model id": "",
 	"Add a short description about what this model does": "",
@@ -28,6 +30,7 @@
 	"Add User": "",
 	"Adjusting these settings will apply changes universally to all users.": "Adjusting these settings will apply changes to all users. Such universal, very wow.",
 	"admin": "admin",
+	"Admin": "",
 	"Admin Panel": "Admin Panel",
 	"Admin Settings": "Admin Settings",
 	"Advanced Parameters": "Advanced Parameters",
@@ -58,7 +61,6 @@
 	"Audio": "Audio",
 	"August": "",
 	"Auto-playback response": "Auto-playback response",
-	"Auto-send input after 3 sec.": "Auto-send after 3 sec.",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 Base URL",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 Base URL is required.",
 	"available!": "available! So excite!",
@@ -70,6 +72,9 @@
 	"Being lazy": "",
 	"Brave Search API Key": "",
 	"Bypass SSL verification for Websites": "",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Cancel",
 	"Capabilities": "",
 	"Change Password": "Change Password",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Chunk Params",
 	"Chunk Size": "Chunk Size",
 	"Citation": "",
+	"Clear memory": "",
 	"Click here for help.": "Click for help. Much assist.",
 	"Click here to": "",
 	"Click here to select": "Click to select",
 	"Click here to select a csv file.": "",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Click to select documents",
 	"click here.": "click here. Such click.",
 	"Click on the user role button to change a user's role.": "Click user role button to change role.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "",
 	"Confirm Password": "Confirm Password",
 	"Connections": "Connections",
+	"Contact Admin for WebUI Access": "",
 	"Content": "Content",
 	"Context Length": "Context Length",
 	"Continue Response": "",
-	"Conversation Mode": "Conversation Mode",
 	"Copied shared chat URL to clipboard!": "",
 	"Copy": "",
 	"Copy last code block": "Copy last code block",
 	"Copy last response": "Copy last response",
 	"Copy Link": "",
 	"Copying to clipboard was successful!": "Copying to clipboard was success! Very success!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Create short phrase, 3-5 word, as header for query, much strict, avoid 'title':",
 	"Create a model": "",
 	"Create Account": "Create Account",
 	"Create new key": "",
@@ -126,12 +132,12 @@
 	"Custom": "Custom",
 	"Customize models for a specific purpose": "",
 	"Dark": "Dark",
+	"Dashboard": "",
 	"Database": "Database",
 	"December": "",
 	"Default": "Default",
 	"Default (Automatic1111)": "Default (Automatic1111)",
 	"Default (SentenceTransformers)": "",
-	"Default (Web API)": "Default (Web API)",
 	"Default Model": "",
 	"Default model updated": "Default model much updated",
 	"Default Prompt Suggestions": "Default Prompt Suggestions",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "Discover a prompt",
 	"Discover, download, and explore custom prompts": "Discover, download, and explore custom prompts",
 	"Discover, download, and explore model presets": "Discover, download, and explore model presets",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "Display username instead of You in Chat",
 	"Document": "Document",
 	"Document Settings": "Document Settings",
@@ -194,6 +201,7 @@
 	"Enter Score": "",
 	"Enter Searxng Query URL": "",
 	"Enter Serper API Key": "",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "",
 	"Enter stop sequence": "Enter stop bark",
 	"Enter Top K": "Enter Top Wow",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "Export Mappings of Dogos",
 	"Export Models": "",
 	"Export Prompts": "Export Promptos",
+	"External Models": "",
 	"Failed to create API Key.": "",
 	"Failed to read clipboard contents": "Failed to read clipboard borks",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "",
 	"Format your variables using square brackets like this:": "Format variables using square brackets like wow:",
 	"Frequency Penalty": "",
-	"Full Screen Mode": "Much Full Bark Mode",
 	"General": "Woweral",
 	"General Settings": "General Doge Settings",
+	"Generate Image": "",
 	"Generating search query": "",
 	"Generation Info": "",
 	"Good Response": "",
@@ -252,6 +261,7 @@
 	"Info": "",
 	"Input commands": "Input commands",
 	"Install from Github URL": "",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Interface",
 	"Invalid Tag": "",
 	"January": "",
@@ -264,14 +274,17 @@
 	"JWT Token": "JWT Borken",
 	"Keep Alive": "Keep Wow",
 	"Keyboard shortcuts": "Keyboard Barkcuts",
+	"Knowledge": "",
 	"Language": "Doge Speak",
 	"Last Active": "",
 	"Light": "Light",
-	"Listening...": "Listening...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "LLMs can make borks. Verify important info.",
+	"Local Models": "",
 	"LTR": "",
 	"Made by OpenWebUI Community": "Made by OpenWebUI Community",
 	"Make sure to enclose them with": "Make sure to enclose them with",
+	"Manage": "",
 	"Manage Models": "Manage Wowdels",
 	"Manage Ollama Models": "Manage Ollama Wowdels",
 	"Manage Pipelines": "",
@@ -307,6 +320,7 @@
 	"Name your model": "",
 	"New Chat": "New Bark",
 	"New Password": "New Barkword",
+	"No documents found": "",
 	"No results found": "",
 	"No search query generated": "",
 	"No source available": "No source available",
@@ -323,6 +337,7 @@
 	"Ollama": "",
 	"Ollama API": "",
 	"Ollama API disabled": "",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Ollama Version",
 	"On": "On",
 	"Only": "Only",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "",
 	"PDF Extract Images (OCR)": "PDF Extract Wowmages (OCR)",
 	"pending": "pending",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Permission denied when accessing microphone: {{error}}",
 	"Personalization": "Personalization",
 	"Pipelines": "",
@@ -367,6 +384,7 @@
 	"Read Aloud": "",
 	"Record voice": "Record Bark",
 	"Redirecting you to OpenWebUI Community": "Redirecting you to OpenWebUI Community",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "",
 	"Regenerate": "",
 	"Release Notes": "Release Borks",
@@ -378,12 +396,14 @@
 	"Reranking Model": "",
 	"Reranking model disabled": "",
 	"Reranking model set to \"{{reranking_model}}\"": "",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "Reset Vector Storage",
 	"Response AutoCopy to Clipboard": "Copy Bark Auto Bark",
 	"Role": "Role",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Rosé Pine Dawn",
 	"RTL": "",
+	"Running": "",
 	"Save": "Save much wow",
 	"Save & Create": "Save & Create much create",
 	"Save & Update": "Save & Update much update",
@@ -397,34 +417,39 @@
 	"Search Documents": "Search Documents much find",
 	"Search Models": "",
 	"Search Prompts": "Search Prompts much wow",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "",
 	"Searched {{count}} sites_one": "",
 	"Searched {{count}} sites_other": "",
-	"Searching the web for '{{searchQuery}}'": "",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "",
 	"See readme.md for instructions": "See readme.md for instructions wow",
 	"See what's new": "See what's new so amaze",
 	"Seed": "Seed very plant",
 	"Select a base model": "",
+	"Select a engine": "",
 	"Select a mode": "Select a mode very choose",
 	"Select a model": "Select a model much choice",
 	"Select a pipeline": "",
 	"Select a pipeline url": "",
 	"Select an Ollama instance": "Select an Ollama instance very choose",
+	"Select Documents": "",
 	"Select model": "Select model much choice",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "",
 	"Send": "",
 	"Send a Message": "Send a Message much message",
 	"Send message": "Send message very send",
 	"September": "",
 	"Serper API Key": "",
+	"Serply API Key": "",
 	"Serpstack API Key": "",
 	"Server connection verified": "Server connection verified much secure",
 	"Set as default": "Set as default very default",
 	"Set Default Model": "Set Default Model much model",
 	"Set embedding model (e.g. {{model}})": "",
 	"Set Image Size": "Set Image Size very size",
-	"Set Model": "Set Model so speak",
 	"Set reranking model (e.g. {{model}})": "",
 	"Set Steps": "Set Steps so many steps",
 	"Set Task Model": "",
@@ -448,8 +473,8 @@
 	"Source": "Source",
 	"Speech recognition error: {{error}}": "Speech recognition error: {{error}} so error",
 	"Speech-to-Text Engine": "Speech-to-Text Engine much speak",
-	"SpeechRecognition API is not supported in this browser.": "SpeechRecognition API is not supported in this browser. Much sad.",
 	"Stop Sequence": "Stop Sequence much stop",
+	"STT Model": "",
 	"STT Settings": "STT Settings very settings",
 	"Submit": "Submit much submit",
 	"Subtitle (e.g. about the Roman Empire)": "",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "",
 	"Theme": "Theme much theme",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "This ensures that your valuable conversations are securely saved to your backend database. Thank you! Much secure!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "This setting does not sync across browsers or devices. Very not sync.",
 	"Thorough explanation": "",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement. Much tip!",
@@ -480,6 +507,8 @@
 	"to": "to very to",
 	"To access the available model names for downloading,": "To access the available model names for downloading, much access",
 	"To access the GGUF models available for downloading,": "To access the GGUF models available for downloading, much access",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "to chat input. Very chat.",
 	"Today": "",
 	"Toggle settings": "Toggle settings much toggle",
@@ -487,7 +516,9 @@
 	"Top K": "Top K very top",
 	"Top P": "Top P very top",
 	"Trouble accessing Ollama?": "Trouble accessing Ollama? Much trouble?",
+	"TTS Model": "",
 	"TTS Settings": "TTS Settings much settings",
+	"TTS Voice": "",
 	"Type": "",
 	"Type Hugging Face Resolve (Download) URL": "Type Hugging Face Resolve (Download) URL much download",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Uh-oh! There was an issue connecting to {{provider}}. Much uh-oh!",
@@ -496,6 +527,7 @@
 	"Update password": "Update password much change",
 	"Upload a GGUF model": "Upload a GGUF model very upload",
 	"Upload Files": "",
+	"Upload Pipeline": "",
 	"Upload Progress": "Upload Progress much progress",
 	"URL Mode": "URL Mode much mode",
 	"Use '#' in the prompt input to load and select your documents.": "Use '#' in the prompt input to load and select your documents. Much use.",
@@ -514,6 +546,7 @@
 	"Warning": "",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "",
 	"Web": "Web very web",
+	"Web API": "",
 	"Web Loader Settings": "",
 	"Web Params": "",
 	"Web Search": "",
@@ -524,17 +557,20 @@
 	"WebUI will make requests to": "WebUI will make requests to much request",
 	"What’s New in": "What’s New in much new",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "When history is turned off, new chats on this browser won't appear in your history on any of your devices. Much history.",
-	"Whisper (Local)": "Whisper (Local) much whisper",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "",
 	"Write a prompt suggestion (e.g. Who are you?)": "Write a prompt suggestion (e.g. Who are you?) much suggest",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Write a summary in 50 words that summarizes [topic or keyword]. Much summarize.",
 	"Yesterday": "",
 	"You": "",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "",
 	"You have no archived conversations.": "",
 	"You have shared this chat": "",
 	"You're a helpful assistant.": "You're a helpful assistant. Much helpful.",
 	"You're now logged in.": "You're now logged in. Much logged.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "",
 	"Youtube Loader Settings": ""
 }

src/lib/i18n/locales/en-GB/translation.json

@@ -12,7 +12,9 @@
 	"a user": "",
 	"About": "",
 	"Account": "",
+	"Account Activation Pending": "",
 	"Accurate information": "",
+	"Active Users": "",
 	"Add": "",
 	"Add a model id": "",
 	"Add a short description about what this model does": "",
@@ -28,6 +30,7 @@
 	"Add User": "",
 	"Adjusting these settings will apply changes universally to all users.": "",
 	"admin": "",
+	"Admin": "",
 	"Admin Panel": "",
 	"Admin Settings": "",
 	"Advanced Parameters": "",
@@ -58,7 +61,6 @@
 	"Audio": "",
 	"August": "",
 	"Auto-playback response": "",
-	"Auto-send input after 3 sec.": "",
 	"AUTOMATIC1111 Base URL": "",
 	"AUTOMATIC1111 Base URL is required.": "",
 	"available!": "",
@@ -70,6 +72,9 @@
 	"Being lazy": "",
 	"Brave Search API Key": "",
 	"Bypass SSL verification for Websites": "",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "",
 	"Capabilities": "",
 	"Change Password": "",
@@ -87,10 +92,12 @@
 	"Chunk Params": "",
 	"Chunk Size": "",
 	"Citation": "",
+	"Clear memory": "",
 	"Click here for help.": "",
 	"Click here to": "",
 	"Click here to select": "",
 	"Click here to select a csv file.": "",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "",
 	"click here.": "",
 	"Click on the user role button to change a user's role.": "",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "",
 	"Confirm Password": "",
 	"Connections": "",
+	"Contact Admin for WebUI Access": "",
 	"Content": "",
 	"Context Length": "",
 	"Continue Response": "",
-	"Conversation Mode": "",
 	"Copied shared chat URL to clipboard!": "",
 	"Copy": "",
 	"Copy last code block": "",
 	"Copy last response": "",
 	"Copy Link": "",
 	"Copying to clipboard was successful!": "",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "",
 	"Create a model": "",
 	"Create Account": "",
 	"Create new key": "",
@@ -126,12 +132,12 @@
 	"Custom": "",
 	"Customize models for a specific purpose": "",
 	"Dark": "",
+	"Dashboard": "",
 	"Database": "",
 	"December": "",
 	"Default": "",
 	"Default (Automatic1111)": "",
 	"Default (SentenceTransformers)": "",
-	"Default (Web API)": "",
 	"Default Model": "",
 	"Default model updated": "",
 	"Default Prompt Suggestions": "",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "",
 	"Discover, download, and explore custom prompts": "",
 	"Discover, download, and explore model presets": "",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "",
 	"Document": "",
 	"Document Settings": "",
@@ -194,6 +201,7 @@
 	"Enter Score": "",
 	"Enter Searxng Query URL": "",
 	"Enter Serper API Key": "",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "",
 	"Enter stop sequence": "",
 	"Enter Top K": "",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "",
 	"Export Models": "",
 	"Export Prompts": "",
+	"External Models": "",
 	"Failed to create API Key.": "",
 	"Failed to read clipboard contents": "",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "",
 	"Format your variables using square brackets like this:": "",
 	"Frequency Penalty": "",
-	"Full Screen Mode": "",
 	"General": "",
 	"General Settings": "",
+	"Generate Image": "",
 	"Generating search query": "",
 	"Generation Info": "",
 	"Good Response": "",
@@ -252,6 +261,7 @@
 	"Info": "",
 	"Input commands": "",
 	"Install from Github URL": "",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "",
 	"Invalid Tag": "",
 	"January": "",
@@ -264,14 +274,17 @@
 	"JWT Token": "",
 	"Keep Alive": "",
 	"Keyboard shortcuts": "",
+	"Knowledge": "",
 	"Language": "",
 	"Last Active": "",
 	"Light": "",
 	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "",
+	"Local Models": "",
 	"LTR": "",
 	"Made by OpenWebUI Community": "",
 	"Make sure to enclose them with": "",
+	"Manage": "",
 	"Manage Models": "",
 	"Manage Ollama Models": "",
 	"Manage Pipelines": "",
@@ -307,6 +320,7 @@
 	"Name your model": "",
 	"New Chat": "",
 	"New Password": "",
+	"No documents found": "",
 	"No results found": "",
 	"No search query generated": "",
 	"No source available": "",
@@ -323,6 +337,7 @@
 	"Ollama": "",
 	"Ollama API": "",
 	"Ollama API disabled": "",
+	"Ollama API is disabled": "",
 	"Ollama Version": "",
 	"On": "",
 	"Only": "",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "",
 	"PDF Extract Images (OCR)": "",
 	"pending": "",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "",
 	"Personalization": "",
 	"Pipelines": "",
@@ -367,6 +384,7 @@
 	"Read Aloud": "",
 	"Record voice": "",
 	"Redirecting you to OpenWebUI Community": "",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "",
 	"Regenerate": "",
 	"Release Notes": "",
@@ -378,12 +396,14 @@
 	"Reranking Model": "",
 	"Reranking model disabled": "",
 	"Reranking model set to \"{{reranking_model}}\"": "",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "",
 	"Response AutoCopy to Clipboard": "",
 	"Role": "",
 	"Rosé Pine": "",
 	"Rosé Pine Dawn": "",
 	"RTL": "",
+	"Running": "",
 	"Save": "",
 	"Save & Create": "",
 	"Save & Update": "",
@@ -397,34 +417,39 @@
 	"Search Documents": "",
 	"Search Models": "",
 	"Search Prompts": "",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "",
 	"Searched {{count}} sites_one": "",
 	"Searched {{count}} sites_other": "",
-	"Searching the web for '{{searchQuery}}'": "",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "",
 	"See readme.md for instructions": "",
 	"See what's new": "",
 	"Seed": "",
 	"Select a base model": "",
+	"Select a engine": "",
 	"Select a mode": "",
 	"Select a model": "",
 	"Select a pipeline": "",
 	"Select a pipeline url": "",
 	"Select an Ollama instance": "",
+	"Select Documents": "",
 	"Select model": "",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "",
 	"Send": "",
 	"Send a Message": "",
 	"Send message": "",
 	"September": "",
 	"Serper API Key": "",
+	"Serply API Key": "",
 	"Serpstack API Key": "",
 	"Server connection verified": "",
 	"Set as default": "",
 	"Set Default Model": "",
 	"Set embedding model (e.g. {{model}})": "",
 	"Set Image Size": "",
-	"Set Model": "",
 	"Set reranking model (e.g. {{model}})": "",
 	"Set Steps": "",
 	"Set Task Model": "",
@@ -448,8 +473,8 @@
 	"Source": "",
 	"Speech recognition error: {{error}}": "",
 	"Speech-to-Text Engine": "",
-	"SpeechRecognition API is not supported in this browser.": "",
 	"Stop Sequence": "",
+	"STT Model": "",
 	"STT Settings": "",
 	"Submit": "",
 	"Subtitle (e.g. about the Roman Empire)": "",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "",
 	"Theme": "",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "",
 	"Thorough explanation": "",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "",
@@ -480,6 +507,8 @@
 	"to": "",
 	"To access the available model names for downloading,": "",
 	"To access the GGUF models available for downloading,": "",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "",
 	"Today": "",
 	"Toggle settings": "",
@@ -487,7 +516,9 @@
 	"Top K": "",
 	"Top P": "",
 	"Trouble accessing Ollama?": "",
+	"TTS Model": "",
 	"TTS Settings": "",
+	"TTS Voice": "",
 	"Type": "",
 	"Type Hugging Face Resolve (Download) URL": "",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "",
@@ -496,6 +527,7 @@
 	"Update password": "",
 	"Upload a GGUF model": "",
 	"Upload Files": "",
+	"Upload Pipeline": "",
 	"Upload Progress": "",
 	"URL Mode": "",
 	"Use '#' in the prompt input to load and select your documents.": "",
@@ -514,6 +546,7 @@
 	"Warning": "",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "",
 	"Web": "",
+	"Web API": "",
 	"Web Loader Settings": "",
 	"Web Params": "",
 	"Web Search": "",
@@ -525,16 +558,19 @@
 	"What’s New in": "",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "",
 	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "",
 	"Write a prompt suggestion (e.g. Who are you?)": "",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "",
 	"Yesterday": "",
 	"You": "",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "",
 	"You have no archived conversations.": "",
 	"You have shared this chat": "",
 	"You're a helpful assistant.": "",
 	"You're now logged in.": "",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "",
 	"Youtube Loader Settings": ""
 }

src/lib/i18n/locales/en-US/translation.json

@@ -12,7 +12,9 @@
 	"a user": "",
 	"About": "",
 	"Account": "",
+	"Account Activation Pending": "",
 	"Accurate information": "",
+	"Active Users": "",
 	"Add": "",
 	"Add a model id": "",
 	"Add a short description about what this model does": "",
@@ -28,6 +30,7 @@
 	"Add User": "",
 	"Adjusting these settings will apply changes universally to all users.": "",
 	"admin": "",
+	"Admin": "",
 	"Admin Panel": "",
 	"Admin Settings": "",
 	"Advanced Parameters": "",
@@ -58,7 +61,6 @@
 	"Audio": "",
 	"August": "",
 	"Auto-playback response": "",
-	"Auto-send input after 3 sec.": "",
 	"AUTOMATIC1111 Base URL": "",
 	"AUTOMATIC1111 Base URL is required.": "",
 	"available!": "",
@@ -70,6 +72,9 @@
 	"Being lazy": "",
 	"Brave Search API Key": "",
 	"Bypass SSL verification for Websites": "",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "",
 	"Capabilities": "",
 	"Change Password": "",
@@ -87,10 +92,12 @@
 	"Chunk Params": "",
 	"Chunk Size": "",
 	"Citation": "",
+	"Clear memory": "",
 	"Click here for help.": "",
 	"Click here to": "",
 	"Click here to select": "",
 	"Click here to select a csv file.": "",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "",
 	"click here.": "",
 	"Click on the user role button to change a user's role.": "",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "",
 	"Confirm Password": "",
 	"Connections": "",
+	"Contact Admin for WebUI Access": "",
 	"Content": "",
 	"Context Length": "",
 	"Continue Response": "",
-	"Conversation Mode": "",
 	"Copied shared chat URL to clipboard!": "",
 	"Copy": "",
 	"Copy last code block": "",
 	"Copy last response": "",
 	"Copy Link": "",
 	"Copying to clipboard was successful!": "",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "",
 	"Create a model": "",
 	"Create Account": "",
 	"Create new key": "",
@@ -126,12 +132,12 @@
 	"Custom": "",
 	"Customize models for a specific purpose": "",
 	"Dark": "",
+	"Dashboard": "",
 	"Database": "",
 	"December": "",
 	"Default": "",
 	"Default (Automatic1111)": "",
 	"Default (SentenceTransformers)": "",
-	"Default (Web API)": "",
 	"Default Model": "",
 	"Default model updated": "",
 	"Default Prompt Suggestions": "",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "",
 	"Discover, download, and explore custom prompts": "",
 	"Discover, download, and explore model presets": "",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "",
 	"Document": "",
 	"Document Settings": "",
@@ -194,6 +201,7 @@
 	"Enter Score": "",
 	"Enter Searxng Query URL": "",
 	"Enter Serper API Key": "",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "",
 	"Enter stop sequence": "",
 	"Enter Top K": "",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "",
 	"Export Models": "",
 	"Export Prompts": "",
+	"External Models": "",
 	"Failed to create API Key.": "",
 	"Failed to read clipboard contents": "",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "",
 	"Format your variables using square brackets like this:": "",
 	"Frequency Penalty": "",
-	"Full Screen Mode": "",
 	"General": "",
 	"General Settings": "",
+	"Generate Image": "",
 	"Generating search query": "",
 	"Generation Info": "",
 	"Good Response": "",
@@ -252,6 +261,7 @@
 	"Info": "",
 	"Input commands": "",
 	"Install from Github URL": "",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "",
 	"Invalid Tag": "",
 	"January": "",
@@ -264,14 +274,17 @@
 	"JWT Token": "",
 	"Keep Alive": "",
 	"Keyboard shortcuts": "",
+	"Knowledge": "",
 	"Language": "",
 	"Last Active": "",
 	"Light": "",
 	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "",
+	"Local Models": "",
 	"LTR": "",
 	"Made by OpenWebUI Community": "",
 	"Make sure to enclose them with": "",
+	"Manage": "",
 	"Manage Models": "",
 	"Manage Ollama Models": "",
 	"Manage Pipelines": "",
@@ -307,6 +320,7 @@
 	"Name your model": "",
 	"New Chat": "",
 	"New Password": "",
+	"No documents found": "",
 	"No results found": "",
 	"No search query generated": "",
 	"No source available": "",
@@ -323,6 +337,7 @@
 	"Ollama": "",
 	"Ollama API": "",
 	"Ollama API disabled": "",
+	"Ollama API is disabled": "",
 	"Ollama Version": "",
 	"On": "",
 	"Only": "",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "",
 	"PDF Extract Images (OCR)": "",
 	"pending": "",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "",
 	"Personalization": "",
 	"Pipelines": "",
@@ -367,6 +384,7 @@
 	"Read Aloud": "",
 	"Record voice": "",
 	"Redirecting you to OpenWebUI Community": "",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "",
 	"Regenerate": "",
 	"Release Notes": "",
@@ -378,12 +396,14 @@
 	"Reranking Model": "",
 	"Reranking model disabled": "",
 	"Reranking model set to \"{{reranking_model}}\"": "",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "",
 	"Response AutoCopy to Clipboard": "",
 	"Role": "",
 	"Rosé Pine": "",
 	"Rosé Pine Dawn": "",
 	"RTL": "",
+	"Running": "",
 	"Save": "",
 	"Save & Create": "",
 	"Save & Update": "",
@@ -397,34 +417,39 @@
 	"Search Documents": "",
 	"Search Models": "",
 	"Search Prompts": "",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "",
 	"Searched {{count}} sites_one": "",
 	"Searched {{count}} sites_other": "",
-	"Searching the web for '{{searchQuery}}'": "",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "",
 	"See readme.md for instructions": "",
 	"See what's new": "",
 	"Seed": "",
 	"Select a base model": "",
+	"Select a engine": "",
 	"Select a mode": "",
 	"Select a model": "",
 	"Select a pipeline": "",
 	"Select a pipeline url": "",
 	"Select an Ollama instance": "",
+	"Select Documents": "",
 	"Select model": "",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "",
 	"Send": "",
 	"Send a Message": "",
 	"Send message": "",
 	"September": "",
 	"Serper API Key": "",
+	"Serply API Key": "",
 	"Serpstack API Key": "",
 	"Server connection verified": "",
 	"Set as default": "",
 	"Set Default Model": "",
 	"Set embedding model (e.g. {{model}})": "",
 	"Set Image Size": "",
-	"Set Model": "",
 	"Set reranking model (e.g. {{model}})": "",
 	"Set Steps": "",
 	"Set Task Model": "",
@@ -448,8 +473,8 @@
 	"Source": "",
 	"Speech recognition error: {{error}}": "",
 	"Speech-to-Text Engine": "",
-	"SpeechRecognition API is not supported in this browser.": "",
 	"Stop Sequence": "",
+	"STT Model": "",
 	"STT Settings": "",
 	"Submit": "",
 	"Subtitle (e.g. about the Roman Empire)": "",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "",
 	"Theme": "",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "",
 	"Thorough explanation": "",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "",
@@ -480,6 +507,8 @@
 	"to": "",
 	"To access the available model names for downloading,": "",
 	"To access the GGUF models available for downloading,": "",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "",
 	"Today": "",
 	"Toggle settings": "",
@@ -487,7 +516,9 @@
 	"Top K": "",
 	"Top P": "",
 	"Trouble accessing Ollama?": "",
+	"TTS Model": "",
 	"TTS Settings": "",
+	"TTS Voice": "",
 	"Type": "",
 	"Type Hugging Face Resolve (Download) URL": "",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "",
@@ -496,6 +527,7 @@
 	"Update password": "",
 	"Upload a GGUF model": "",
 	"Upload Files": "",
+	"Upload Pipeline": "",
 	"Upload Progress": "",
 	"URL Mode": "",
 	"Use '#' in the prompt input to load and select your documents.": "",
@@ -514,6 +546,7 @@
 	"Warning": "",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "",
 	"Web": "",
+	"Web API": "",
 	"Web Loader Settings": "",
 	"Web Params": "",
 	"Web Search": "",
@@ -525,16 +558,19 @@
 	"What’s New in": "",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "",
 	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "",
 	"Write a prompt suggestion (e.g. Who are you?)": "",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "",
 	"Yesterday": "",
 	"You": "",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "",
 	"You have no archived conversations.": "",
 	"You have shared this chat": "",
 	"You're a helpful assistant.": "",
 	"You're now logged in.": "",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "",
 	"Youtube Loader Settings": ""
 }

src/lib/i18n/locales/es-ES/translation.json

@@ -12,7 +12,9 @@
 	"a user": "un usuario",
 	"About": "Sobre nosotros",
 	"Account": "Cuenta",
+	"Account Activation Pending": "",
 	"Accurate information": "Información precisa",
+	"Active Users": "",
 	"Add": "Agregar",
 	"Add a model id": "Adición de un identificador de modelo",
 	"Add a short description about what this model does": "Agregue una breve descripción sobre lo que hace este modelo",
@@ -28,6 +30,7 @@
 	"Add User": "Agregar Usuario",
 	"Adjusting these settings will apply changes universally to all users.": "Ajustar estas opciones aplicará los cambios universalmente a todos los usuarios.",
 	"admin": "admin",
+	"Admin": "",
 	"Admin Panel": "Panel de Administración",
 	"Admin Settings": "Configuración de Administrador",
 	"Advanced Parameters": "Parámetros Avanzados",
@@ -58,7 +61,6 @@
 	"Audio": "Audio",
 	"August": "Agosto",
 	"Auto-playback response": "Respuesta de reproducción automática",
-	"Auto-send input after 3 sec.": "Envía la información entrada automáticamente luego de 3 segundos.",
 	"AUTOMATIC1111 Base URL": "Dirección URL de AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "La dirección URL de AUTOMATIC1111 es requerida.",
 	"available!": "¡disponible!",
@@ -70,6 +72,9 @@
 	"Being lazy": "Ser perezoso",
 	"Brave Search API Key": "Clave de API de Brave Search",
 	"Bypass SSL verification for Websites": "Desactivar la verificación SSL para sitios web",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Cancelar",
 	"Capabilities": "Capacidades",
 	"Change Password": "Cambia la Contraseña",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Parámetros de fragmentos",
 	"Chunk Size": "Tamaño de fragmentos",
 	"Citation": "Cita",
+	"Clear memory": "",
 	"Click here for help.": "Presiona aquí para obtener ayuda.",
 	"Click here to": "Presiona aquí para",
 	"Click here to select": "Presiona aquí para seleccionar",
 	"Click here to select a csv file.": "Presiona aquí para seleccionar un archivo csv.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Presiona aquí para seleccionar documentos",
 	"click here.": "Presiona aquí.",
 	"Click on the user role button to change a user's role.": "Presiona en el botón de roles del usuario para cambiar su rol.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "Solicitudes simultáneas",
 	"Confirm Password": "Confirmar Contraseña",
 	"Connections": "Conexiones",
+	"Contact Admin for WebUI Access": "",
 	"Content": "Contenido",
 	"Context Length": "Longitud del contexto",
 	"Continue Response": "Continuar Respuesta",
-	"Conversation Mode": "Modo de Conversación",
 	"Copied shared chat URL to clipboard!": "¡URL de chat compartido copiado al portapapeles!",
 	"Copy": "Copiar",
 	"Copy last code block": "Copia el último bloque de código",
 	"Copy last response": "Copia la última respuesta",
 	"Copy Link": "Copiar enlace",
 	"Copying to clipboard was successful!": "¡La copia al portapapeles se ha realizado correctamente!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Cree una frase concisa de 3 a 5 palabras como encabezado para la siguiente consulta, respetando estrictamente el límite de 3 a 5 palabras y evitando el uso de la palabra 'título':",
 	"Create a model": "Crear un modelo",
 	"Create Account": "Crear una cuenta",
 	"Create new key": "Crear una nueva clave",
@@ -126,12 +132,12 @@
 	"Custom": "Personalizado",
 	"Customize models for a specific purpose": "Personalizar modelos para un propósito específico",
 	"Dark": "Oscuro",
+	"Dashboard": "",
 	"Database": "Base de datos",
 	"December": "Diciembre",
 	"Default": "Por defecto",
 	"Default (Automatic1111)": "Por defecto (Automatic1111)",
 	"Default (SentenceTransformers)": "Por defecto (SentenceTransformers)",
-	"Default (Web API)": "Por defecto (Web API)",
 	"Default Model": "Modelo predeterminado",
 	"Default model updated": "El modelo por defecto ha sido actualizado",
 	"Default Prompt Suggestions": "Sugerencias de mensajes por defecto",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "Descubre un Prompt",
 	"Discover, download, and explore custom prompts": "Descubre, descarga, y explora Prompts personalizados",
 	"Discover, download, and explore model presets": "Descubre, descarga y explora ajustes preestablecidos de modelos",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "Mostrar el nombre de usuario en lugar de Usted en el chat",
 	"Document": "Documento",
 	"Document Settings": "Configuración del Documento",
@@ -194,6 +201,7 @@
 	"Enter Score": "Ingrese la puntuación",
 	"Enter Searxng Query URL": "Introduzca la URL de consulta de Searxng",
 	"Enter Serper API Key": "Ingrese la clave API de Serper",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "Ingrese la clave API de Serpstack",
 	"Enter stop sequence": "Ingrese la secuencia de parada",
 	"Enter Top K": "Ingrese el Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "Exportar el mapeo de documentos",
 	"Export Models": "Modelos de exportación",
 	"Export Prompts": "Exportar Prompts",
+	"External Models": "",
 	"Failed to create API Key.": "No se pudo crear la clave API.",
 	"Failed to read clipboard contents": "No se pudo leer el contenido del portapapeles",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "Siguió las instrucciones perfectamente",
 	"Format your variables using square brackets like this:": "Formatea tus variables usando corchetes de la siguiente manera:",
 	"Frequency Penalty": "Penalización de frecuencia",
-	"Full Screen Mode": "Modo de Pantalla Completa",
 	"General": "General",
 	"General Settings": "Opciones Generales",
+	"Generate Image": "",
 	"Generating search query": "Generación de consultas de búsqueda",
 	"Generation Info": "Información de Generación",
 	"Good Response": "Buena Respuesta",
@@ -252,6 +261,7 @@
 	"Info": "Información",
 	"Input commands": "Ingresar comandos",
 	"Install from Github URL": "Instalar desde la URL de Github",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Interfaz",
 	"Invalid Tag": "Etiqueta Inválida",
 	"January": "Enero",
@@ -264,14 +274,17 @@
 	"JWT Token": "Token JWT",
 	"Keep Alive": "Mantener Vivo",
 	"Keyboard shortcuts": "Atajos de teclado",
+	"Knowledge": "",
 	"Language": "Lenguaje",
 	"Last Active": "Última Actividad",
 	"Light": "Claro",
-	"Listening...": "Escuchando...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "Los LLM pueden cometer errores. Verifica la información importante.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "Hecho por la comunidad de OpenWebUI",
 	"Make sure to enclose them with": "Asegúrese de adjuntarlos con",
+	"Manage": "",
 	"Manage Models": "Administrar Modelos",
 	"Manage Ollama Models": "Administrar Modelos Ollama",
 	"Manage Pipelines": "Administrar canalizaciones",
@@ -307,6 +320,7 @@
 	"Name your model": "Asigne un nombre a su modelo",
 	"New Chat": "Nuevo Chat",
 	"New Password": "Nueva Contraseña",
+	"No documents found": "",
 	"No results found": "No se han encontrado resultados",
 	"No search query generated": "No se ha generado ninguna consulta de búsqueda",
 	"No source available": "No hay fuente disponible",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama API",
 	"Ollama API disabled": "API de Ollama deshabilitada",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Versión de Ollama",
 	"On": "Activado",
 	"Only": "Solamente",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "PDF document (.pdf)",
 	"PDF Extract Images (OCR)": "Extraer imágenes de PDF (OCR)",
 	"pending": "pendiente",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Permiso denegado al acceder al micrófono: {{error}}",
 	"Personalization": "Personalización",
 	"Pipelines": "Tuberías",
@@ -367,6 +384,7 @@
 	"Read Aloud": "Leer al oído",
 	"Record voice": "Grabar voz",
 	"Redirecting you to OpenWebUI Community": "Redireccionándote a la comunidad OpenWebUI",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "Rechazado cuando no debería",
 	"Regenerate": "Regenerar",
 	"Release Notes": "Notas de la versión",
@@ -378,12 +396,14 @@
 	"Reranking Model": "Modelo de reranking",
 	"Reranking model disabled": "Modelo de reranking deshabilitado",
 	"Reranking model set to \"{{reranking_model}}\"": "Modelo de reranking establecido en \"{{reranking_model}}\"",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "Restablecer almacenamiento vectorial",
 	"Response AutoCopy to Clipboard": "Copiar respuesta automáticamente al portapapeles",
 	"Role": "Rol",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Rosé Pine Dawn",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "Guardar",
 	"Save & Create": "Guardar y Crear",
 	"Save & Update": "Guardar y Actualizar",
@@ -397,35 +417,40 @@
 	"Search Documents": "Buscar Documentos",
 	"Search Models": "Modelos de búsqueda",
 	"Search Prompts": "Buscar Prompts",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "Recuento de resultados de búsqueda",
 	"Searched {{count}} sites_one": "Buscado {{count}} sites_one",
 	"Searched {{count}} sites_many": "Buscado {{count}} sites_many",
 	"Searched {{count}} sites_other": "Buscó {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "Buscando en la web '{{searchQuery}}'",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "Searxng URL de consulta",
 	"See readme.md for instructions": "Vea el readme.md para instrucciones",
 	"See what's new": "Ver las novedades",
 	"Seed": "Seed",
 	"Select a base model": "Seleccionar un modelo base",
+	"Select a engine": "",
 	"Select a mode": "Selecciona un modo",
 	"Select a model": "Selecciona un modelo",
 	"Select a pipeline": "Selección de una canalización",
 	"Select a pipeline url": "Selección de una dirección URL de canalización",
 	"Select an Ollama instance": "Seleccione una instancia de Ollama",
+	"Select Documents": "",
 	"Select model": "Selecciona un modelo",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "Los modelos seleccionados no admiten entradas de imagen",
 	"Send": "Enviar",
 	"Send a Message": "Enviar un Mensaje",
 	"Send message": "Enviar Mensaje",
 	"September": "Septiembre",
 	"Serper API Key": "Clave API de Serper",
+	"Serply API Key": "",
 	"Serpstack API Key": "Clave API de Serpstack",
 	"Server connection verified": "Conexión del servidor verificada",
 	"Set as default": "Establecer por defecto",
 	"Set Default Model": "Establecer modelo predeterminado",
 	"Set embedding model (e.g. {{model}})": "Establecer modelo de embedding (ej. {{model}})",
 	"Set Image Size": "Establecer tamaño de imagen",
-	"Set Model": "Establecer el modelo",
 	"Set reranking model (e.g. {{model}})": "Establecer modelo de reranking (ej. {{model}})",
 	"Set Steps": "Establecer Pasos",
 	"Set Task Model": "Establecer modelo de tarea",
@@ -449,8 +474,8 @@
 	"Source": "Fuente",
 	"Speech recognition error: {{error}}": "Error de reconocimiento de voz: {{error}}",
 	"Speech-to-Text Engine": "Motor de voz a texto",
-	"SpeechRecognition API is not supported in this browser.": "La API SpeechRecognition no es compatible con este navegador.",
 	"Stop Sequence": "Detener secuencia",
+	"STT Model": "",
 	"STT Settings": "Configuraciones de STT",
 	"Submit": "Enviar",
 	"Subtitle (e.g. about the Roman Empire)": "Subtítulo (por ejemplo, sobre el Imperio Romano)",
@@ -469,7 +494,9 @@
 	"Thanks for your feedback!": "¡Gracias por tu retroalimentación!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "El puntaje debe ser un valor entre 0.0 (0%) y 1.0 (100%).",
 	"Theme": "Tema",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Esto garantiza que sus valiosas conversaciones se guarden de forma segura en su base de datos en el backend. ¡Gracias!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "Esta configuración no se sincroniza entre navegadores o dispositivos.",
 	"Thorough explanation": "Explicación exhaustiva",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Consejo: Actualice múltiples variables consecutivamente presionando la tecla tab en la entrada del chat después de cada reemplazo.",
@@ -481,6 +508,8 @@
 	"to": "para",
 	"To access the available model names for downloading,": "Para acceder a los nombres de modelos disponibles para descargar,",
 	"To access the GGUF models available for downloading,": "Para acceder a los modelos GGUF disponibles para descargar,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "a la entrada del chat.",
 	"Today": "Hoy",
 	"Toggle settings": "Alternar configuración",
@@ -488,7 +517,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "¿Problemas para acceder a Ollama?",
+	"TTS Model": "",
 	"TTS Settings": "Configuración de TTS",
+	"TTS Voice": "",
 	"Type": "Tipo",
 	"Type Hugging Face Resolve (Download) URL": "Escriba la URL (Descarga) de Hugging Face Resolve",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "¡Uh oh! Hubo un problema al conectarse a {{provider}}.",
@@ -497,6 +528,7 @@
 	"Update password": "Actualizar contraseña",
 	"Upload a GGUF model": "Subir un modelo GGUF",
 	"Upload Files": "Subir archivos",
+	"Upload Pipeline": "",
 	"Upload Progress": "Progreso de carga",
 	"URL Mode": "Modo de URL",
 	"Use '#' in the prompt input to load and select your documents.": "Utilice '#' en el prompt para cargar y seleccionar sus documentos.",
@@ -515,6 +547,7 @@
 	"Warning": "Advertencia",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Advertencia: Si actualiza o cambia su modelo de inserción, necesitará volver a importar todos los documentos.",
 	"Web": "Web",
+	"Web API": "",
 	"Web Loader Settings": "Web Loader Settings",
 	"Web Params": "Web Params",
 	"Web Search": "Búsqueda en la Web",
@@ -525,17 +558,20 @@
 	"WebUI will make requests to": "WebUI realizará solicitudes a",
 	"What’s New in": "Novedades en",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "Cuando el historial está desactivado, los nuevos chats en este navegador no aparecerán en el historial de ninguno de sus dispositivos..",
-	"Whisper (Local)": "Whisper (Local)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "Espacio de trabajo",
 	"Write a prompt suggestion (e.g. Who are you?)": "Escribe una sugerencia para un prompt (por ejemplo, ¿quién eres?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Escribe un resumen en 50 palabras que resuma [tema o palabra clave].",
 	"Yesterday": "Ayer",
 	"You": "Usted",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "No se puede clonar un modelo base",
 	"You have no archived conversations.": "No tiene conversaciones archivadas.",
 	"You have shared this chat": "Usted ha compartido esta conversación",
 	"You're a helpful assistant.": "Usted es un asistente útil.",
 	"You're now logged in.": "Usted ahora está conectado.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "Configuración del cargador de Youtube"
 }

src/lib/i18n/locales/fa-IR/translation.json

@@ -12,7 +12,9 @@
 	"a user": "یک کاربر",
 	"About": "درباره",
 	"Account": "حساب کاربری",
+	"Account Activation Pending": "",
 	"Accurate information": "اطلاعات دقیق",
+	"Active Users": "",
 	"Add": "اضافه کردن",
 	"Add a model id": "افزودن شناسه مدل",
 	"Add a short description about what this model does": "اضافه کردن توضیحات کوتاه در مورد انچه که این مدل انجام می دهد",
@@ -28,6 +30,7 @@
 	"Add User": "اضافه کردن کاربر",
 	"Adjusting these settings will apply changes universally to all users.": "با تنظیم این تنظیمات، تغییرات به طور کلی برای همه کاربران اعمال می شود.",
 	"admin": "مدیر",
+	"Admin": "",
 	"Admin Panel": "پنل مدیریت",
 	"Admin Settings": "تنظیمات مدیریت",
 	"Advanced Parameters": "پارامترهای پیشرفته",
@@ -58,7 +61,6 @@
 	"Audio": "صدا",
 	"August": "آگوست",
 	"Auto-playback response": "پخش خودکار پاسخ ",
-	"Auto-send input after 3 sec.": "به طور خودکار ورودی را پس از 3 ثانیه ارسال کن.",
 	"AUTOMATIC1111 Base URL": "پایه URL AUTOMATIC1111 ",
 	"AUTOMATIC1111 Base URL is required.": "به URL پایه AUTOMATIC1111 مورد نیاز است.",
 	"available!": "در دسترس!",
@@ -70,6 +72,9 @@
 	"Being lazy": "حالت سازنده",
 	"Brave Search API Key": "کلید API جستجوی شجاع",
 	"Bypass SSL verification for Websites": "عبور از تأیید SSL برای وب سایت ها",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "لغو",
 	"Capabilities": "قابلیت",
 	"Change Password": "تغییر رمز عبور",
@@ -87,10 +92,12 @@
 	"Chunk Params": "پارامترهای تکه",
 	"Chunk Size": "اندازه تکه",
 	"Citation": "استناد",
+	"Clear memory": "",
 	"Click here for help.": "برای کمک اینجا را کلیک کنید.",
 	"Click here to": "برای کمک اینجا را کلیک کنید.",
 	"Click here to select": "برای انتخاب اینجا کلیک کنید",
 	"Click here to select a csv file.": "برای انتخاب یک فایل csv اینجا را کلیک کنید.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "برای انتخاب اسناد اینجا را کلیک کنید.",
 	"click here.": "اینجا کلیک کنید.",
 	"Click on the user role button to change a user's role.": "برای تغییر نقش کاربر، روی دکمه نقش کاربر کلیک کنید.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "درخواست های همزمان",
 	"Confirm Password": "تایید رمز عبور",
 	"Connections": "ارتباطات",
+	"Contact Admin for WebUI Access": "",
 	"Content": "محتوا",
 	"Context Length": "طول زمینه",
 	"Continue Response": "ادامه پاسخ",
-	"Conversation Mode": "حالت مکالمه",
 	"Copied shared chat URL to clipboard!": "URL چت به کلیپ بورد کپی شد!",
 	"Copy": "کپی",
 	"Copy last code block": "کپی آخرین بلوک کد",
 	"Copy last response": "کپی آخرین پاسخ",
 	"Copy Link": "کپی لینک",
 	"Copying to clipboard was successful!": "کپی کردن در کلیپ بورد با موفقیت انجام شد!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "یک عبارت مختصر و ۳ تا ۵ کلمه ای را به عنوان سرفصل برای پرس و جو زیر ایجاد کنید، به شدت محدودیت ۳-۵ کلمه را رعایت کنید و از استفاده از کلمه 'عنوان' خودداری کنید:",
 	"Create a model": "ایجاد یک مدل",
 	"Create Account": "ساخت حساب کاربری",
 	"Create new key": "ساخت کلید جدید",
@@ -126,12 +132,12 @@
 	"Custom": "دلخواه",
 	"Customize models for a specific purpose": "سفارشی کردن مدل ها برای یک هدف خاص",
 	"Dark": "تیره",
+	"Dashboard": "",
 	"Database": "پایگاه داده",
 	"December": "دسامبر",
 	"Default": "پیشفرض",
 	"Default (Automatic1111)": "پیشفرض (Automatic1111)",
 	"Default (SentenceTransformers)": "پیشفرض (SentenceTransformers)",
-	"Default (Web API)": "پیشفرض (Web API)",
 	"Default Model": "مدل پیشفرض",
 	"Default model updated": "مدل پیشفرض به\u200cروزرسانی شد",
 	"Default Prompt Suggestions": "پیشنهادات پرامپت پیش فرض",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "یک اعلان را کشف کنید",
 	"Discover, download, and explore custom prompts": "پرامپت\u200cهای سفارشی را کشف، دانلود و کاوش کنید",
 	"Discover, download, and explore model presets": "پیش تنظیمات مدل را کشف، دانلود و کاوش کنید",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "نمایش نام کاربری به جای «شما» در چت",
 	"Document": "سند",
 	"Document Settings": "تنظیمات سند",
@@ -194,6 +201,7 @@
 	"Enter Score": "امتیاز را وارد کنید",
 	"Enter Searxng Query URL": "نشانی وب پرسوجوی Searxng را وارد کنید",
 	"Enter Serper API Key": "کلید API Serper را وارد کنید",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "کلید API Serpstack را وارد کنید",
 	"Enter stop sequence": "توالی توقف را وارد کنید",
 	"Enter Top K": "مقدار Top K را وارد کنید",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "اکسپورت از نگاشت اسناد",
 	"Export Models": "مدل های صادرات",
 	"Export Prompts": "اکسپورت از پرامپت\u200cها",
+	"External Models": "",
 	"Failed to create API Key.": "ایجاد کلید API با خطا مواجه شد.",
 	"Failed to read clipboard contents": "خواندن محتوای کلیپ بورد ناموفق بود",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "دستورالعمل ها را کاملا دنبال کرد",
 	"Format your variables using square brackets like this:": "متغیرهای خود را با استفاده از براکت مربع به شکل زیر قالب بندی کنید:",
 	"Frequency Penalty": "مجازات فرکانس",
-	"Full Screen Mode": "حالت تمام صفحه",
 	"General": "عمومی",
 	"General Settings": "تنظیمات عمومی",
+	"Generate Image": "",
 	"Generating search query": "در حال تولید پرسوجوی جستجو",
 	"Generation Info": "اطلاعات تولید",
 	"Good Response": "پاسخ خوب",
@@ -252,6 +261,7 @@
 	"Info": "اطلاعات",
 	"Input commands": "ورودی دستورات",
 	"Install from Github URL": "نصب از ادرس Github",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "رابط",
 	"Invalid Tag": "تگ نامعتبر",
 	"January": "ژانویه",
@@ -264,14 +274,17 @@
 	"JWT Token": "JWT توکن",
 	"Keep Alive": "Keep Alive",
 	"Keyboard shortcuts": "میانبرهای صفحه کلید",
+	"Knowledge": "",
 	"Language": "زبان",
 	"Last Active": "آخرین فعال",
 	"Light": "روشن",
-	"Listening...": "در حال گوش دادن...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "مدل\u200cهای زبانی بزرگ می\u200cتوانند اشتباه کنند. اطلاعات مهم را راستی\u200cآزمایی کنید.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "ساخته شده توسط OpenWebUI Community",
 	"Make sure to enclose them with": "مطمئن شوید که آنها را با این محصور کنید:",
+	"Manage": "",
 	"Manage Models": "مدیریت مدل\u200cها",
 	"Manage Ollama Models": "مدیریت مدل\u200cهای اولاما",
 	"Manage Pipelines": "مدیریت خطوط لوله",
@@ -307,6 +320,7 @@
 	"Name your model": "نام مدل خود را",
 	"New Chat": "گپ جدید",
 	"New Password": "رمز عبور جدید",
+	"No documents found": "",
 	"No results found": "نتیجه\u200cای یافت نشد",
 	"No search query generated": "پرسوجوی جستجویی ایجاد نشده است",
 	"No source available": "منبعی در دسترس نیست",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama API",
 	"Ollama API disabled": "API Ollama غیرفعال شد",
+	"Ollama API is disabled": "",
 	"Ollama Version": "نسخه اولاما",
 	"On": "روشن",
 	"Only": "فقط",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "PDF سند (.pdf)",
 	"PDF Extract Images (OCR)": "استخراج تصاویر از PDF (OCR)",
 	"pending": "در انتظار",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "هنگام دسترسی به میکروفون، اجازه داده نشد: {{error}}",
 	"Personalization": "شخصی سازی",
 	"Pipelines": "خط لوله",
@@ -367,6 +384,7 @@
 	"Read Aloud": "خواندن به صورت صوتی",
 	"Record voice": "ضبط صدا",
 	"Redirecting you to OpenWebUI Community": "در حال هدایت به OpenWebUI Community",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "رد شده زمانی که باید نباشد",
 	"Regenerate": "ری\u200cسازی",
 	"Release Notes": "یادداشت\u200cهای انتشار",
@@ -378,12 +396,14 @@
 	"Reranking Model": "مدل ری\u200cشناسی مجدد غیرفعال است",
 	"Reranking model disabled": "مدل ری\u200cشناسی مجدد غیرفعال است",
 	"Reranking model set to \"{{reranking_model}}\"": "مدل ری\u200cشناسی مجدد به \"{{reranking_model}}\" تنظیم شده است",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "بازنشانی ذخیره سازی برداری",
 	"Response AutoCopy to Clipboard": "کپی خودکار پاسخ به کلیپ بورد",
 	"Role": "نقش",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Rosé Pine Dawn",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "ذخیره",
 	"Save & Create": "ذخیره و ایجاد",
 	"Save & Update": "ذخیره و به\u200cروزرسانی",
@@ -397,34 +417,39 @@
 	"Search Documents": "جستجوی اسناد",
 	"Search Models": "مدل های جستجو",
 	"Search Prompts": "جستجوی پرامپت\u200cها",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "تعداد نتایج جستجو",
 	"Searched {{count}} sites_one": "جستجو {{count}} sites_one",
 	"Searched {{count}} sites_other": "جستجو {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "جستجو در وب برای '{searchQuery}}'",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "نشانی وب جستجوی Searxng",
 	"See readme.md for instructions": "برای مشاهده دستورالعمل\u200cها به readme.md مراجعه کنید",
 	"See what's new": "ببینید موارد جدید چه بوده",
 	"Seed": "Seed",
 	"Select a base model": "انتخاب یک مدل پایه",
+	"Select a engine": "",
 	"Select a mode": "یک حالت انتخاب کنید",
 	"Select a model": "انتخاب یک مدل",
 	"Select a pipeline": "انتخاب یک خط لوله",
 	"Select a pipeline url": "یک ادرس خط لوله را انتخاب کنید",
 	"Select an Ollama instance": "انتخاب یک نمونه از اولاما",
+	"Select Documents": "",
 	"Select model": "انتخاب یک مدل",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "مدل) های (انتخاب شده ورودیهای تصویر را پشتیبانی نمیکند",
 	"Send": "ارسال",
 	"Send a Message": "ارسال یک پیام",
 	"Send message": "ارسال پیام",
 	"September": "سپتامبر",
 	"Serper API Key": "کلید API Serper",
+	"Serply API Key": "",
 	"Serpstack API Key": "کلید API Serpstack",
 	"Server connection verified": "اتصال سرور تأیید شد",
 	"Set as default": "تنظیم به عنوان پیشفرض",
 	"Set Default Model": "تنظیم مدل پیش فرض",
 	"Set embedding model (e.g. {{model}})": "تنظیم مدل پیچشی (برای مثال {{model}})",
 	"Set Image Size": "تنظیم اندازه تصویر",
-	"Set Model": "تنظیم مدل",
 	"Set reranking model (e.g. {{model}})": "تنظیم مدل ری\u200cراینگ (برای مثال {{model}})",
 	"Set Steps": "تنظیم گام\u200cها",
 	"Set Task Model": "تنظیم مدل تکلیف",
@@ -448,8 +473,8 @@
 	"Source": "منبع",
 	"Speech recognition error: {{error}}": "خطای تشخیص گفتار: {{error}}",
 	"Speech-to-Text Engine": "موتور گفتار به متن",
-	"SpeechRecognition API is not supported in this browser.": "API تشخیص گفتار در این مرورگر پشتیبانی نمی شود.",
 	"Stop Sequence": "توالی توقف",
+	"STT Model": "",
 	"STT Settings": "STT تنظیمات",
 	"Submit": "ارسال",
 	"Subtitle (e.g. about the Roman Empire)": "زیرنویس (برای مثال: درباره رمانی)",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "با تشکر از بازخورد شما!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "امتیاز باید یک مقدار بین 0.0 (0%) و 1.0 (100%) باشد.",
 	"Theme": "قالب",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "این تضمین می کند که مکالمات ارزشمند شما به طور ایمن در پایگاه داده بکند ذخیره می شود. تشکر!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "این تنظیم در مرورگرها یا دستگاه\u200cها همگام\u200cسازی نمی\u200cشود.",
 	"Thorough explanation": "توضیح کامل",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "با فشردن کلید Tab در ورودی چت پس از هر بار تعویض، چندین متغیر را به صورت متوالی به روزرسانی کنید.",
@@ -480,6 +507,8 @@
 	"to": "به",
 	"To access the available model names for downloading,": "برای دسترسی به نام مدل های موجود برای دانلود،",
 	"To access the GGUF models available for downloading,": "برای دسترسی به مدل\u200cهای GGUF موجود برای دانلود،",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "در ورودی گپ.",
 	"Today": "امروز",
 	"Toggle settings": "نمایش/عدم نمایش تنظیمات",
@@ -487,7 +516,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "در دسترسی به اولاما مشکل دارید؟",
+	"TTS Model": "",
 	"TTS Settings": "تنظیمات TTS",
+	"TTS Voice": "",
 	"Type": "نوع",
 	"Type Hugging Face Resolve (Download) URL": "مقدار URL دانلود (Resolve) Hugging Face را وارد کنید",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "اوه اوه! مشکلی در اتصال به {{provider}} وجود داشت.",
@@ -496,6 +527,7 @@
 	"Update password": "به روزرسانی رمزعبور",
 	"Upload a GGUF model": "آپلود یک مدل GGUF",
 	"Upload Files": "بارگذاری پروندهها",
+	"Upload Pipeline": "",
 	"Upload Progress": "پیشرفت آپلود",
 	"URL Mode": "حالت URL",
 	"Use '#' in the prompt input to load and select your documents.": "در پرامپت از '#' برای لود و انتخاب اسناد خود استفاده کنید.",
@@ -514,6 +546,7 @@
 	"Warning": "هشدار",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "هشدار: اگر شما به روز کنید یا تغییر دهید مدل شما، باید تمام سند ها را مجددا وارد کنید.",
 	"Web": "وب",
+	"Web API": "",
 	"Web Loader Settings": "تنظیمات لودر وب",
 	"Web Params": "پارامترهای وب",
 	"Web Search": "جستجوی وب",
@@ -524,17 +557,20 @@
 	"WebUI will make requests to": "WebUI درخواست\u200cها را ارسال خواهد کرد به",
 	"What’s New in": "موارد جدید در",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "وقتی سابقه خاموش است، چت\u200cهای جدید در این مرورگر در سابقه شما در هیچ یک از دستگاه\u200cهایتان ظاهر نمی\u200cشوند.",
-	"Whisper (Local)": "ویسپر (محلی)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "محیط کار",
 	"Write a prompt suggestion (e.g. Who are you?)": "یک پیشنهاد پرامپت بنویسید (مثلاً شما کی هستید؟)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "خلاصه ای در 50 کلمه بنویسید که [موضوع یا کلمه کلیدی] را خلاصه کند.",
 	"Yesterday": "دیروز",
 	"You": "شما",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "شما نمیتوانید یک مدل پایه را کلون کنید",
 	"You have no archived conversations.": "شما هیچ گفتگوی ذخیره شده ندارید.",
 	"You have shared this chat": "شما این گفتگو را به اشتراک گذاشته اید",
 	"You're a helpful assistant.": "تو یک دستیار سودمند هستی.",
 	"You're now logged in.": "شما اکنون وارد شده\u200cاید.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "یوتیوب",
 	"Youtube Loader Settings": "تنظیمات لودر یوتیوب"
 }

src/lib/i18n/locales/fi-FI/translation.json

@@ -12,7 +12,9 @@
 	"a user": "käyttäjä",
 	"About": "Tietoja",
 	"Account": "Tili",
+	"Account Activation Pending": "",
 	"Accurate information": "Tarkkaa tietoa",
+	"Active Users": "",
 	"Add": "Lisää",
 	"Add a model id": "Mallitunnuksen lisääminen",
 	"Add a short description about what this model does": "Lisää lyhyt kuvaus siitä, mitä tämä malli tekee",
@@ -28,6 +30,7 @@
 	"Add User": "Lisää käyttäjä",
 	"Adjusting these settings will apply changes universally to all users.": "Näiden asetusten säätäminen vaikuttaa kaikkiin käyttäjiin.",
 	"admin": "hallinta",
+	"Admin": "",
 	"Admin Panel": "Hallintapaneeli",
 	"Admin Settings": "Hallinta-asetukset",
 	"Advanced Parameters": "Edistyneet parametrit",
@@ -58,7 +61,6 @@
 	"Audio": "Ääni",
 	"August": "elokuu",
 	"Auto-playback response": "Soita vastaus automaattisesti",
-	"Auto-send input after 3 sec.": "Lähetä syöte automaattisesti 3 sekunnin kuluttua",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111-perus-URL",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111-perus-URL vaaditaan.",
 	"available!": "saatavilla!",
@@ -70,6 +72,9 @@
 	"Being lazy": "Oli laiska",
 	"Brave Search API Key": "Brave Search API -avain",
 	"Bypass SSL verification for Websites": "Ohita SSL-varmennus verkkosivustoille",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Peruuta",
 	"Capabilities": "Ominaisuuksia",
 	"Change Password": "Vaihda salasana",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Osien parametrit",
 	"Chunk Size": "Osien koko",
 	"Citation": "Sitaatti",
+	"Clear memory": "",
 	"Click here for help.": "Klikkaa tästä saadaksesi apua.",
 	"Click here to": "Klikkaa tästä",
 	"Click here to select": "Klikkaa tästä valitaksesi",
 	"Click here to select a csv file.": "Klikkaa tästä valitaksesi CSV-tiedosto.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Klikkaa tästä valitaksesi asiakirjoja.",
 	"click here.": "klikkaa tästä.",
 	"Click on the user role button to change a user's role.": "Klikkaa käyttäjän roolipainiketta vaihtaaksesi käyttäjän roolia.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "Samanaikaiset pyynnöt",
 	"Confirm Password": "Vahvista salasana",
 	"Connections": "Yhteydet",
+	"Contact Admin for WebUI Access": "",
 	"Content": "Sisältö",
 	"Context Length": "Kontekstin pituus",
 	"Continue Response": "Jatka vastausta",
-	"Conversation Mode": "Keskustelutila",
 	"Copied shared chat URL to clipboard!": "Jaettu keskustelulinkki kopioitu leikepöydälle!",
 	"Copy": "Kopioi",
 	"Copy last code block": "Kopioi viimeisin koodilohko",
 	"Copy last response": "Kopioi viimeisin vastaus",
 	"Copy Link": "Kopioi linkki",
 	"Copying to clipboard was successful!": "Kopioiminen leikepöydälle onnistui!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Luo tiivis, 3-5 sanan lause otsikoksi seuraavalle kyselylle, noudattaen tiukasti 3-5 sanan rajoitusta ja välttäen sanan 'otsikko' käyttöä:",
 	"Create a model": "Mallin luominen",
 	"Create Account": "Luo tili",
 	"Create new key": "Luo uusi avain",
@@ -126,12 +132,12 @@
 	"Custom": "Mukautettu",
 	"Customize models for a specific purpose": "Mallien mukauttaminen tiettyyn tarkoitukseen",
 	"Dark": "Tumma",
+	"Dashboard": "",
 	"Database": "Tietokanta",
 	"December": "joulukuu",
 	"Default": "Oletus",
 	"Default (Automatic1111)": "Oletus (AUTOMATIC1111)",
 	"Default (SentenceTransformers)": "Oletus (SentenceTransformers)",
-	"Default (Web API)": "Oletus (web-API)",
 	"Default Model": "Oletusmalli",
 	"Default model updated": "Oletusmalli päivitetty",
 	"Default Prompt Suggestions": "Oletuskehotteiden ehdotukset",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "Löydä kehote",
 	"Discover, download, and explore custom prompts": "Löydä ja lataa mukautettuja kehotteita",
 	"Discover, download, and explore model presets": "Löydä ja lataa mallien esiasetuksia",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "Näytä käyttäjänimi keskustelussa",
 	"Document": "Asiakirja",
 	"Document Settings": "Asiakirja-asetukset",
@@ -194,6 +201,7 @@
 	"Enter Score": "Syötä pisteet",
 	"Enter Searxng Query URL": "Kirjoita Searxng-kyselyn URL-osoite",
 	"Enter Serper API Key": "Anna Serper API -avain",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "Anna Serpstack API -avain",
 	"Enter stop sequence": "Syötä lopetussekvenssi",
 	"Enter Top K": "Syötä Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "Vie asiakirjakartoitus",
 	"Export Models": "Vie malleja",
 	"Export Prompts": "Vie kehotteet",
+	"External Models": "",
 	"Failed to create API Key.": "API-avaimen luonti epäonnistui.",
 	"Failed to read clipboard contents": "Leikepöydän sisällön lukeminen epäonnistui",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "Noudatti ohjeita täydellisesti",
 	"Format your variables using square brackets like this:": "Muotoile muuttujat hakasulkeilla näin:",
 	"Frequency Penalty": "Taajuussakko",
-	"Full Screen Mode": "Koko näytön tila",
 	"General": "Yleinen",
 	"General Settings": "Yleisasetukset",
+	"Generate Image": "",
 	"Generating search query": "Hakukyselyn luominen",
 	"Generation Info": "Generointitiedot",
 	"Good Response": "Hyvä vastaus",
@@ -252,6 +261,7 @@
 	"Info": "Info",
 	"Input commands": "Syötä komennot",
 	"Install from Github URL": "Asenna Githubin URL-osoitteesta",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Käyttöliittymä",
 	"Invalid Tag": "Virheellinen tagi",
 	"January": "tammikuu",
@@ -264,14 +274,17 @@
 	"JWT Token": "JWT-token",
 	"Keep Alive": "Pysy aktiivisena",
 	"Keyboard shortcuts": "Pikanäppäimet",
+	"Knowledge": "",
 	"Language": "Kieli",
 	"Last Active": "Viimeksi aktiivinen",
 	"Light": "Vaalea",
-	"Listening...": "Kuunnellaan...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "Kielimallit voivat tehdä virheitä. Varmista tärkeät tiedot.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "Tehnyt OpenWebUI-yhteisö",
 	"Make sure to enclose them with": "Varmista, että suljet ne",
+	"Manage": "",
 	"Manage Models": "Hallitse malleja",
 	"Manage Ollama Models": "Hallitse Ollama-malleja",
 	"Manage Pipelines": "Hallitse putkia",
@@ -307,6 +320,7 @@
 	"Name your model": "Mallin nimeäminen",
 	"New Chat": "Uusi keskustelu",
 	"New Password": "Uusi salasana",
+	"No documents found": "",
 	"No results found": "Ei tuloksia",
 	"No search query generated": "Hakukyselyä ei luotu",
 	"No source available": "Ei lähdettä saatavilla",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama API",
 	"Ollama API disabled": "Ollama API poistettu käytöstä",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Ollama-versio",
 	"On": "Päällä",
 	"Only": "Vain",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "PDF-tiedosto (.pdf)",
 	"PDF Extract Images (OCR)": "PDF-tiedoston kuvien erottelu (OCR)",
 	"pending": "odottaa",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Mikrofonin käyttöoikeus evätty: {{error}}",
 	"Personalization": "Henkilökohtaisuus",
 	"Pipelines": "Putkistot",
@@ -367,6 +384,7 @@
 	"Read Aloud": "Lue ääneen",
 	"Record voice": "Nauhoita ääni",
 	"Redirecting you to OpenWebUI Community": "Ohjataan sinut OpenWebUI-yhteisöön",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "Kieltäytyi, vaikka ei olisi pitänyt",
 	"Regenerate": "Uudelleenluo",
 	"Release Notes": "Julkaisutiedot",
@@ -378,12 +396,14 @@
 	"Reranking Model": "Uudelleenpisteytysmalli",
 	"Reranking model disabled": "Uudelleenpisteytysmalli poistettu käytöstä",
 	"Reranking model set to \"{{reranking_model}}\"": "\"{{reranking_model}}\" valittu uudelleenpisteytysmalliksi",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "Tyhjennä vektorivarasto",
 	"Response AutoCopy to Clipboard": "Vastauksen automaattikopiointi leikepöydälle",
 	"Role": "Rooli",
 	"Rosé Pine": "Rosee-mänty",
 	"Rosé Pine Dawn": "Aamuinen Rosee-mänty",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "Tallenna",
 	"Save & Create": "Tallenna ja luo",
 	"Save & Update": "Tallenna ja päivitä",
@@ -397,34 +417,39 @@
 	"Search Documents": "Hae asiakirjoja",
 	"Search Models": "Hae malleja",
 	"Search Prompts": "Hae kehotteita",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "Hakutulosten määrä",
 	"Searched {{count}} sites_one": "Haettu {{count}} sites_one",
 	"Searched {{count}} sites_other": "Haku {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "Haku verkosta hakusanalla {{searchQuery}}",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "Searxng-kyselyn URL-osoite",
 	"See readme.md for instructions": "Katso lisää ohjeita readme.md:stä",
 	"See what's new": "Katso, mitä uutta",
 	"Seed": "Siemen",
 	"Select a base model": "Valitse perusmalli",
+	"Select a engine": "",
 	"Select a mode": "Valitse tila",
 	"Select a model": "Valitse malli",
 	"Select a pipeline": "Valitse putki",
 	"Select a pipeline url": "Valitse putken URL-osoite",
 	"Select an Ollama instance": "Valitse Ollama-instanssi",
+	"Select Documents": "",
 	"Select model": "Valitse malli",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "Valitut mallit eivät tue kuvasyötteitä",
 	"Send": "Lähetä",
 	"Send a Message": "Lähetä viesti",
 	"Send message": "Lähetä viesti",
 	"September": "syyskuu",
 	"Serper API Key": "Serper API -avain",
+	"Serply API Key": "",
 	"Serpstack API Key": "Serpstack API -avain",
 	"Server connection verified": "Palvelinyhteys varmennettu",
 	"Set as default": "Aseta oletukseksi",
 	"Set Default Model": "Aseta oletusmalli",
 	"Set embedding model (e.g. {{model}})": "Aseta upotusmalli (esim. {{model}})",
 	"Set Image Size": "Aseta kuvan koko",
-	"Set Model": "Aseta malli",
 	"Set reranking model (e.g. {{model}})": "Aseta uudelleenpisteytysmalli (esim. {{model}})",
 	"Set Steps": "Aseta askelmäärä",
 	"Set Task Model": "Aseta tehtävämalli",
@@ -448,8 +473,8 @@
 	"Source": "Lähde",
 	"Speech recognition error: {{error}}": "Puheentunnistusvirhe: {{error}}",
 	"Speech-to-Text Engine": "Puheentunnistusmoottori",
-	"SpeechRecognition API is not supported in this browser.": "SpeechRecognition-rajapinta ei ole tuettu tässä selaimessa.",
 	"Stop Sequence": "Lopetussekvenssi",
+	"STT Model": "",
 	"STT Settings": "Puheentunnistusasetukset",
 	"Submit": "Lähetä",
 	"Subtitle (e.g. about the Roman Empire)": "Alaotsikko (esim. Rooman valtakunnasta)",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "Kiitos palautteestasi!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "Pisteytyksen tulee olla arvo välillä 0.0 (0%) ja 1.0 (100%).",
 	"Theme": "Teema",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Tämä varmistaa, että arvokkaat keskustelusi tallennetaan turvallisesti backend-tietokantaasi. Kiitos!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "Tämä asetus ei synkronoidu selainten tai laitteiden välillä.",
 	"Thorough explanation": "Perusteellinen selitys",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Vinkki: Päivitä useita muuttujapaikkoja peräkkäin painamalla tabulaattoria keskustelusyötteessä jokaisen korvauksen jälkeen.",
@@ -480,6 +507,8 @@
 	"to": "->",
 	"To access the available model names for downloading,": "Päästäksesi käsiksi ladattavissa oleviin mallinimiin,",
 	"To access the GGUF models available for downloading,": "Päästäksesi käsiksi ladattavissa oleviin GGUF-malleihin,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "keskustelusyötteeseen.",
 	"Today": "Tänään",
 	"Toggle settings": "Kytke asetukset",
@@ -487,7 +516,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "Ongelmia Ollama-yhteydessä?",
+	"TTS Model": "",
 	"TTS Settings": "Puheentuottamisasetukset",
+	"TTS Voice": "",
 	"Type": "Tyyppi",
 	"Type Hugging Face Resolve (Download) URL": "Kirjoita Hugging Face -resolve-osoite",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Voi ei! Yhteysongelma {{provider}}:n kanssa.",
@@ -496,6 +527,7 @@
 	"Update password": "Päivitä salasana",
 	"Upload a GGUF model": "Lataa GGUF-malli",
 	"Upload Files": "Lataa tiedostoja",
+	"Upload Pipeline": "",
 	"Upload Progress": "Latauksen eteneminen",
 	"URL Mode": "URL-tila",
 	"Use '#' in the prompt input to load and select your documents.": "Käytä '#' syötteessä ladataksesi ja valitaksesi asiakirjoja.",
@@ -514,6 +546,7 @@
 	"Warning": "Varoitus",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Varoitus: Jos päivität tai vaihdat upotusmallia, sinun on tuotava kaikki asiakirjat uudelleen.",
 	"Web": "Web",
+	"Web API": "",
 	"Web Loader Settings": "Web Loader asetukset",
 	"Web Params": "Web-parametrit",
 	"Web Search": "Web-haku",
@@ -524,17 +557,20 @@
 	"WebUI will make requests to": "WebUI tekee pyyntöjä",
 	"What’s New in": "Mitä uutta",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "Kun historia on pois päältä, uudet keskustelut tässä selaimessa eivät näy historiassasi millään laitteellasi.",
-	"Whisper (Local)": "Whisper (paikallinen)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "Työtilat",
 	"Write a prompt suggestion (e.g. Who are you?)": "Kirjoita ehdotettu kehote (esim. Kuka olet?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Kirjoita 50 sanan yhteenveto, joka tiivistää [aihe tai avainsana].",
 	"Yesterday": "Eilen",
 	"You": "Sinä",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "Perusmallia ei voi kloonata",
 	"You have no archived conversations.": "Sinulla ei ole arkistoituja keskusteluja.",
 	"You have shared this chat": "Olet jakanut tämän keskustelun",
 	"You're a helpful assistant.": "Olet avulias apulainen.",
 	"You're now logged in.": "Olet nyt kirjautunut sisään.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "Youtube Loader-asetukset"
 }

src/lib/i18n/locales/fr-CA/translation.json

@@ -12,7 +12,9 @@
 	"a user": "un utilisateur",
 	"About": "À propos",
 	"Account": "Compte",
+	"Account Activation Pending": "",
 	"Accurate information": "Information précise",
+	"Active Users": "",
 	"Add": "Ajouter",
 	"Add a model id": "Ajouter un id de modèle",
 	"Add a short description about what this model does": "Ajoutez une brève description de ce que fait ce modèle",
@@ -28,6 +30,7 @@
 	"Add User": "Ajouter un utilisateur",
 	"Adjusting these settings will apply changes universally to all users.": "L'ajustement de ces paramètres appliquera les changements à tous les utilisateurs.",
 	"admin": "Administrateur",
+	"Admin": "",
 	"Admin Panel": "Panneau d'administration",
 	"Admin Settings": "Paramètres d'administration",
 	"Advanced Parameters": "Paramètres avancés",
@@ -58,7 +61,6 @@
 	"Audio": "Audio",
 	"August": "Août",
 	"Auto-playback response": "Réponse en lecture automatique",
-	"Auto-send input after 3 sec.": "Envoyer automatiquement l'entrée après 3 sec.",
 	"AUTOMATIC1111 Base URL": "URL de base AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "L'URL de base AUTOMATIC1111 est requise.",
 	"available!": "disponible !",
@@ -70,6 +72,9 @@
 	"Being lazy": "En manque de temps",
 	"Brave Search API Key": "Clé d’API de recherche brave",
 	"Bypass SSL verification for Websites": "Parcourir la vérification SSL pour les sites Web",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Annuler",
 	"Capabilities": "Capacités",
 	"Change Password": "Changer le mot de passe",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Paramètres de bloc",
 	"Chunk Size": "Taille de bloc",
 	"Citation": "Citations",
+	"Clear memory": "",
 	"Click here for help.": "Cliquez ici pour de l'aide.",
 	"Click here to": "Cliquez ici pour",
 	"Click here to select": "Cliquez ici pour sélectionner",
 	"Click here to select a csv file.": "Cliquez ici pour sélectionner un fichier csv.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Cliquez ici pour sélectionner des documents.",
 	"click here.": "cliquez ici.",
 	"Click on the user role button to change a user's role.": "Cliquez sur le bouton de rôle d'utilisateur pour changer le rôle d'un utilisateur.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "Demandes simultanées",
 	"Confirm Password": "Confirmer le mot de passe",
 	"Connections": "Connexions",
+	"Contact Admin for WebUI Access": "",
 	"Content": "Contenu",
 	"Context Length": "Longueur du contexte",
 	"Continue Response": "Continuer la réponse",
-	"Conversation Mode": "Mode de conversation",
 	"Copied shared chat URL to clipboard!": "URL de chat partagé copié dans le presse-papier !",
 	"Copy": "Copier",
 	"Copy last code block": "Copier le dernier bloc de code",
 	"Copy last response": "Copier la dernière réponse",
 	"Copy Link": "Copier le lien",
 	"Copying to clipboard was successful!": "La copie dans le presse-papiers a réussi !",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Créez une phrase concise de 3 à 5 mots comme en-tête pour la requête suivante, en respectant strictement la limite de 3 à 5 mots et en évitant l'utilisation du mot 'titre' :",
 	"Create a model": "Créer un modèle",
 	"Create Account": "Créer un compte",
 	"Create new key": "Créer une nouvelle clé",
@@ -126,12 +132,12 @@
 	"Custom": "Personnalisé",
 	"Customize models for a specific purpose": "Personnaliser les modèles dans un but spécifique",
 	"Dark": "Sombre",
+	"Dashboard": "",
 	"Database": "Base de données",
 	"December": "Décembre",
 	"Default": "Par défaut",
 	"Default (Automatic1111)": "Par défaut (Automatic1111)",
 	"Default (SentenceTransformers)": "Par défaut (SentenceTransformers)",
-	"Default (Web API)": "Par défaut (API Web)",
 	"Default Model": "Modèle par défaut",
 	"Default model updated": "Modèle par défaut mis à jour",
 	"Default Prompt Suggestions": "Suggestions de prompt par défaut",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "Découvrir un prompt",
 	"Discover, download, and explore custom prompts": "Découvrir, télécharger et explorer des prompts personnalisés",
 	"Discover, download, and explore model presets": "Découvrir, télécharger et explorer des préconfigurations de modèles",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "Afficher le nom d'utilisateur au lieu de 'Vous' dans la Discussion",
 	"Document": "Document",
 	"Document Settings": "Paramètres du document",
@@ -194,6 +201,7 @@
 	"Enter Score": "Entrez le score",
 	"Enter Searxng Query URL": "Entrez l’URL de requête Searxng",
 	"Enter Serper API Key": "Entrez la clé API Serper",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "Entrez dans la clé API Serpstack",
 	"Enter stop sequence": "Entrez la séquence de fin",
 	"Enter Top K": "Entrez Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "Exporter le mappage des documents",
 	"Export Models": "Modèles d’exportation",
 	"Export Prompts": "Exporter les prompts",
+	"External Models": "",
 	"Failed to create API Key.": "Impossible de créer la clé API.",
 	"Failed to read clipboard contents": "Échec de la lecture du contenu du presse-papiers",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "Suivi des instructions parfaitement",
 	"Format your variables using square brackets like this:": "Formatez vos variables en utilisant des crochets comme ceci :",
 	"Frequency Penalty": "Pénalité de fréquence",
-	"Full Screen Mode": "Mode plein écran",
 	"General": "Général",
 	"General Settings": "Paramètres généraux",
+	"Generate Image": "",
 	"Generating search query": "Génération d’une requête de recherche",
 	"Generation Info": "Informations de génération",
 	"Good Response": "Bonne réponse",
@@ -252,6 +261,7 @@
 	"Info": "L’info",
 	"Input commands": "Entrez des commandes d'entrée",
 	"Install from Github URL": "Installer à partir de l’URL Github",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Interface",
 	"Invalid Tag": "Tag invalide",
 	"January": "Janvier",
@@ -264,14 +274,17 @@
 	"JWT Token": "Jeton JWT",
 	"Keep Alive": "Garder actif",
 	"Keyboard shortcuts": "Raccourcis clavier",
+	"Knowledge": "",
 	"Language": "Langue",
 	"Last Active": "Dernière activité",
 	"Light": "Lumière",
-	"Listening...": "Écoute...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "Les LLMs peuvent faire des erreurs. Vérifiez les informations importantes.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "Réalisé par la communauté OpenWebUI",
 	"Make sure to enclose them with": "Assurez-vous de les entourer avec",
+	"Manage": "",
 	"Manage Models": "Gérer les modèles",
 	"Manage Ollama Models": "Gérer les modèles Ollama",
 	"Manage Pipelines": "Gérer les pipelines",
@@ -307,6 +320,7 @@
 	"Name your model": "Nommez votre modèle",
 	"New Chat": "Nouvelle discussion",
 	"New Password": "Nouveau mot de passe",
+	"No documents found": "",
 	"No results found": "Aucun résultat trouvé",
 	"No search query generated": "Aucune requête de recherche générée",
 	"No source available": "Aucune source disponible",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama API",
 	"Ollama API disabled": "API Ollama désactivée",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Version Ollama",
 	"On": "Activé",
 	"Only": "Seulement",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "Document PDF (.pdf)",
 	"PDF Extract Images (OCR)": "Extraction d'images PDF (OCR)",
 	"pending": "en attente",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Permission refusée lors de l'accès au microphone : {{error}}",
 	"Personalization": "Personnalisation",
 	"Pipelines": "Pipelines",
@@ -367,6 +384,7 @@
 	"Read Aloud": "Lire à l'échelle",
 	"Record voice": "Enregistrer la voix",
 	"Redirecting you to OpenWebUI Community": "Vous redirige vers la communauté OpenWebUI",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "Refusé quand il ne devrait pas l'être",
 	"Regenerate": "Régénérer",
 	"Release Notes": "Notes de version",
@@ -378,12 +396,14 @@
 	"Reranking Model": "Modèle de reranking",
 	"Reranking model disabled": "Modèle de reranking désactivé",
 	"Reranking model set to \"{{reranking_model}}\"": "Modèle de reranking défini sur \"{{reranking_model}}\"",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "Réinitialiser le stockage vectoriel",
 	"Response AutoCopy to Clipboard": "Copie automatique de la réponse vers le presse-papiers",
 	"Role": "Rôle",
 	"Rosé Pine": "Pin Rosé",
 	"Rosé Pine Dawn": "Aube Pin Rosé",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "Enregistrer",
 	"Save & Create": "Enregistrer & Créer",
 	"Save & Update": "Enregistrer & Mettre à jour",
@@ -397,35 +417,40 @@
 	"Search Documents": "Rechercher des documents",
 	"Search Models": "Modèles de recherche",
 	"Search Prompts": "Rechercher des prompts",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "Nombre de résultats de la recherche",
 	"Searched {{count}} sites_one": "Recherche dans {{count}} sites_one",
 	"Searched {{count}} sites_many": "Recherche dans {{count}} sites_many",
 	"Searched {{count}} sites_other": "Recherche dans {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "Recherche sur le Web pour '{{searchQuery}}'",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "URL de la requête Searxng",
 	"See readme.md for instructions": "Voir readme.md pour les instructions",
 	"See what's new": "Voir les nouveautés",
 	"Seed": "Graine",
 	"Select a base model": "Sélectionner un modèle de base",
+	"Select a engine": "",
 	"Select a mode": "Sélectionnez un mode",
 	"Select a model": "Sélectionnez un modèle",
 	"Select a pipeline": "Sélectionner un pipeline",
 	"Select a pipeline url": "Sélectionnez une URL de pipeline",
 	"Select an Ollama instance": "Sélectionner une instance Ollama",
+	"Select Documents": "",
 	"Select model": "Sélectionnez un modèle",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "Les modèles sélectionnés ne prennent pas en charge les entrées d’image",
 	"Send": "Envoyer",
 	"Send a Message": "Envoyer un message",
 	"Send message": "Envoyer un message",
 	"September": "Septembre",
 	"Serper API Key": "Clé API Serper",
+	"Serply API Key": "",
 	"Serpstack API Key": "Clé API Serpstack",
 	"Server connection verified": "Connexion au serveur vérifiée",
 	"Set as default": "Définir par défaut",
 	"Set Default Model": "Définir le modèle par défaut",
 	"Set embedding model (e.g. {{model}})": "Définir le modèle d'embedding (par exemple {{model}})",
 	"Set Image Size": "Définir la taille de l'image",
-	"Set Model": "Configurer le modèle",
 	"Set reranking model (e.g. {{model}})": "Définir le modèle de reranking (par exemple {{model}})",
 	"Set Steps": "Définir les étapes",
 	"Set Task Model": "Définir le modèle de tâche",
@@ -449,8 +474,8 @@
 	"Source": "Source",
 	"Speech recognition error: {{error}}": "Erreur de reconnaissance vocale : {{error}}",
 	"Speech-to-Text Engine": "Moteur reconnaissance vocale",
-	"SpeechRecognition API is not supported in this browser.": "L'API SpeechRecognition n'est pas prise en charge dans ce navigateur.",
 	"Stop Sequence": "Séquence d'arrêt",
+	"STT Model": "",
 	"STT Settings": "Paramètres de STT",
 	"Submit": "Soumettre",
 	"Subtitle (e.g. about the Roman Empire)": "Sous-titre (par exemple, sur l'empire romain)",
@@ -469,7 +494,9 @@
 	"Thanks for your feedback!": "Merci pour votre feedback!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "Le score doit être une valeur entre 0.0 (0%) et 1.0 (100%).",
 	"Theme": "Thème",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Cela garantit que vos précieuses conversations sont enregistrées en toute sécurité dans votre base de données backend. Merci !",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "Ce réglage ne se synchronise pas entre les navigateurs ou les appareils.",
 	"Thorough explanation": "Explication approfondie",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Astuce : Mettez à jour plusieurs emplacements de variables consécutivement en appuyant sur la touche tabulation dans l'entrée de chat après chaque remplacement.",
@@ -481,6 +508,8 @@
 	"to": "à",
 	"To access the available model names for downloading,": "Pour accéder aux noms de modèles disponibles pour le téléchargement,",
 	"To access the GGUF models available for downloading,": "Pour accéder aux modèles GGUF disponibles pour le téléchargement,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "à l'entrée du chat.",
 	"Today": "Aujourd'hui",
 	"Toggle settings": "Basculer les paramètres",
@@ -488,7 +517,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "Des problèmes pour accéder à Ollama ?",
+	"TTS Model": "",
 	"TTS Settings": "Paramètres TTS",
+	"TTS Voice": "",
 	"Type": "Type",
 	"Type Hugging Face Resolve (Download) URL": "Entrez l'URL de résolution (téléchargement) Hugging Face",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Uh-oh ! Il y a eu un problème de connexion à {{provider}}.",
@@ -497,6 +528,7 @@
 	"Update password": "Mettre à jour le mot de passe",
 	"Upload a GGUF model": "Téléverser un modèle GGUF",
 	"Upload Files": "Télécharger des fichiers",
+	"Upload Pipeline": "",
 	"Upload Progress": "Progression du Téléversement",
 	"URL Mode": "Mode URL",
 	"Use '#' in the prompt input to load and select your documents.": "Utilisez '#' dans l'entrée de prompt pour charger et sélectionner vos documents.",
@@ -515,6 +547,7 @@
 	"Warning": "Avertissement",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Attention : Si vous mettez à jour ou changez votre modèle d'intégration, vous devrez réimporter tous les documents.",
 	"Web": "Web",
+	"Web API": "",
 	"Web Loader Settings": "Paramètres du chargeur Web",
 	"Web Params": "Paramètres Web",
 	"Web Search": "Recherche sur le Web",
@@ -525,17 +558,20 @@
 	"WebUI will make requests to": "WebUI effectuera des demandes à",
 	"What’s New in": "Quoi de neuf dans",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "Lorsque l'historique est désactivé, les nouvelles discussions sur ce navigateur n'apparaîtront pas dans votre historique sur aucun de vos appareils.",
-	"Whisper (Local)": "Whisper (Local)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "Espace de travail",
 	"Write a prompt suggestion (e.g. Who are you?)": "Rédigez une suggestion de prompt (p. ex. Qui êtes-vous ?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Rédigez un résumé en 50 mots qui résume [sujet ou mot-clé].",
 	"Yesterday": "hier",
 	"You": "Vous",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "Vous ne pouvez pas cloner un modèle de base",
 	"You have no archived conversations.": "Vous n'avez aucune conversation archivée.",
 	"You have shared this chat": "Vous avez partagé cette conversation",
 	"You're a helpful assistant.": "Vous êtes un assistant utile",
 	"You're now logged in.": "Vous êtes maintenant connecté.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "Paramètres du chargeur Youtube"
 }

src/lib/i18n/locales/fr-FR/translation.json

@@ -12,7 +12,9 @@
 	"a user": "un utilisateur",
 	"About": "À Propos",
 	"Account": "Compte",
+	"Account Activation Pending": "",
 	"Accurate information": "Information précise",
+	"Active Users": "",
 	"Add": "Ajouter",
 	"Add a model id": "Ajouter un identifiant modèle",
 	"Add a short description about what this model does": "Ajouter une courte description de ce que fait ce modèle",
@@ -28,6 +30,7 @@
 	"Add User": "Ajouter un Utilisateur",
 	"Adjusting these settings will apply changes universally to all users.": "L'ajustement de ces paramètres appliquera les changements à tous les utilisateurs.",
 	"admin": "admin",
+	"Admin": "",
 	"Admin Panel": "Panneau d'Administration",
 	"Admin Settings": "Paramètres d'Administration",
 	"Advanced Parameters": "Paramètres Avancés",
@@ -58,7 +61,6 @@
 	"Audio": "Audio",
 	"August": "Août",
 	"Auto-playback response": "Réponse en lecture automatique",
-	"Auto-send input after 3 sec.": "Envoyer automatiquement l'entrée après 3 sec.",
 	"AUTOMATIC1111 Base URL": "URL de base AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "L'URL de base AUTOMATIC1111 est requise.",
 	"available!": "disponible !",
@@ -70,6 +72,9 @@
 	"Being lazy": "Est paresseux",
 	"Brave Search API Key": "Clé API Brave Search",
 	"Bypass SSL verification for Websites": "Contourner la vérification SSL pour les sites Web.",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "Annuler",
 	"Capabilities": "Capacités",
 	"Change Password": "Changer le mot de passe",
@@ -87,10 +92,12 @@
 	"Chunk Params": "Paramètres de bloc",
 	"Chunk Size": "Taille de bloc",
 	"Citation": "Citation",
+	"Clear memory": "",
 	"Click here for help.": "Cliquez ici pour de l'aide.",
 	"Click here to": "Cliquez ici pour",
 	"Click here to select": "Cliquez ici pour sélectionner",
 	"Click here to select a csv file.": "Cliquez ici pour sélectionner un fichier csv.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "Cliquez ici pour sélectionner des documents.",
 	"click here.": "cliquez ici.",
 	"Click on the user role button to change a user's role.": "Cliquez sur le bouton de rôle d'utilisateur pour changer le rôle d'un utilisateur.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "Demandes simultanées",
 	"Confirm Password": "Confirmer le mot de passe",
 	"Connections": "Connexions",
+	"Contact Admin for WebUI Access": "",
 	"Content": "Contenu",
 	"Context Length": "Longueur du contexte",
 	"Continue Response": "Continuer la Réponse",
-	"Conversation Mode": "Mode de conversation",
 	"Copied shared chat URL to clipboard!": "URL du chat copié dans le presse-papiers !",
 	"Copy": "Copier",
 	"Copy last code block": "Copier le dernier bloc de code",
 	"Copy last response": "Copier la dernière réponse",
 	"Copy Link": "Copier le Lien",
 	"Copying to clipboard was successful!": "La copie dans le presse-papiers a réussi !",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "Créez une phrase concise de 3-5 mots comme en-tête pour la requête suivante, en respectant strictement la limite de 3-5 mots et en évitant l'utilisation du mot 'titre' :",
 	"Create a model": "Créer un modèle",
 	"Create Account": "Créer un compte",
 	"Create new key": "Créer une nouvelle clé",
@@ -126,12 +132,12 @@
 	"Custom": "Personnalisé",
 	"Customize models for a specific purpose": "Personnaliser les modèles pour un objectif spécifique",
 	"Dark": "Sombre",
+	"Dashboard": "",
 	"Database": "Base de données",
 	"December": "Décembre",
 	"Default": "Par défaut",
 	"Default (Automatic1111)": "Par défaut (Automatic1111)",
 	"Default (SentenceTransformers)": "Par défaut (SentenceTransformers)",
-	"Default (Web API)": "Par défaut (API Web)",
 	"Default Model": "Modèle par défaut",
 	"Default model updated": "Modèle par défaut mis à jour",
 	"Default Prompt Suggestions": "Suggestions de prompt par défaut",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "Découvrir un prompt",
 	"Discover, download, and explore custom prompts": "Découvrir, télécharger et explorer des prompts personnalisés",
 	"Discover, download, and explore model presets": "Découvrir, télécharger et explorer des préconfigurations de modèles",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "Afficher le nom d'utilisateur au lieu de 'Vous' dans le Chat",
 	"Document": "Document",
 	"Document Settings": "Paramètres du document",
@@ -194,6 +201,7 @@
 	"Enter Score": "Entrez le Score",
 	"Enter Searxng Query URL": "Entrez l’URL de la requête Searxng",
 	"Enter Serper API Key": "Entrez la clé API Serper",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "Entrez la clé API Serpstack",
 	"Enter stop sequence": "Entrez la séquence de fin",
 	"Enter Top K": "Entrez Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "Exporter la Correspondance des Documents",
 	"Export Models": "Exporter les Modèles",
 	"Export Prompts": "Exporter les Prompts",
+	"External Models": "",
 	"Failed to create API Key.": "Échec de la création de la clé d'API.",
 	"Failed to read clipboard contents": "Échec de la lecture du contenu du presse-papiers",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "A suivi les instructions parfaitement",
 	"Format your variables using square brackets like this:": "Formatez vos variables en utilisant des crochets comme ceci :",
 	"Frequency Penalty": "Pénalité de fréquence",
-	"Full Screen Mode": "Mode plein écran",
 	"General": "Général",
 	"General Settings": "Paramètres Généraux",
+	"Generate Image": "",
 	"Generating search query": "Génération d’une requête de recherche",
 	"Generation Info": "Informations de la Génération",
 	"Good Response": "Bonne Réponse",
@@ -252,6 +261,7 @@
 	"Info": "Info",
 	"Input commands": "Entrez les commandes d'entrée",
 	"Install from Github URL": "Installer à partir de l’URL Github",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "Interface",
 	"Invalid Tag": "Tag Invalide",
 	"January": "Janvier",
@@ -264,14 +274,17 @@
 	"JWT Token": "Jeton JWT",
 	"Keep Alive": "Rester en vie",
 	"Keyboard shortcuts": "Raccourcis clavier",
+	"Knowledge": "",
 	"Language": "Langue",
 	"Last Active": "Dernier Activité",
 	"Light": "Clair",
-	"Listening...": "Écoute...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "Les LLMs peuvent faire des erreurs. Vérifiez les informations importantes.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "Réalisé par la communauté OpenWebUI",
 	"Make sure to enclose them with": "Assurez-vous de les entourer avec",
+	"Manage": "",
 	"Manage Models": "Gérer les modèles",
 	"Manage Ollama Models": "Gérer les modèles Ollama",
 	"Manage Pipelines": "Gérer les pipelines",
@@ -307,6 +320,7 @@
 	"Name your model": "Nommez votre modèle",
 	"New Chat": "Nouveau chat",
 	"New Password": "Nouveau mot de passe",
+	"No documents found": "",
 	"No results found": "Aucun résultat",
 	"No search query generated": "Aucune requête de recherche générée",
 	"No source available": "Aucune source disponible",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "API Ollama",
 	"Ollama API disabled": "API Ollama désactivée",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Version Ollama",
 	"On": "Activé",
 	"Only": "Seulement",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "Document PDF (.pdf)",
 	"PDF Extract Images (OCR)": "Extraction d'images PDF (OCR)",
 	"pending": "en attente",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "Permission refusée lors de l'accès au microphone : {{error}}",
 	"Personalization": "Personnalisation",
 	"Pipelines": "Pipelines",
@@ -367,6 +384,7 @@
 	"Read Aloud": "Lire à Voix Haute",
 	"Record voice": "Enregistrer la voix",
 	"Redirecting you to OpenWebUI Community": "Redirection vers la communauté OpenWebUI",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "Refuse quand il ne devrait pas",
 	"Regenerate": "Regénérer",
 	"Release Notes": "Notes de Version",
@@ -378,12 +396,14 @@
 	"Reranking Model": "Modèle de Reclassement",
 	"Reranking model disabled": "Modèle de Reclassement Désactivé",
 	"Reranking model set to \"{{reranking_model}}\"": "Modèle de reclassement défini sur \"{{reranking_model}}\"",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "Réinitialiser le Stockage de Vecteur",
 	"Response AutoCopy to Clipboard": "Copie Automatique de la Réponse dans le Presse-papiers",
 	"Role": "Rôle",
 	"Rosé Pine": "Pin Rosé",
 	"Rosé Pine Dawn": "Aube Pin Rosé",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "Enregistrer",
 	"Save & Create": "Enregistrer & Créer",
 	"Save & Update": "Enregistrer & Mettre à jour",
@@ -397,35 +417,40 @@
 	"Search Documents": "Rechercher des Documents",
 	"Search Models": "Rechercher des modèles",
 	"Search Prompts": "Rechercher des Prompts",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "Nombre de résultats de recherche",
 	"Searched {{count}} sites_one": "Recherché {{count}} sites_one",
 	"Searched {{count}} sites_many": "Recherché {{count}} sites_many",
 	"Searched {{count}} sites_other": "Recherché {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "Recherche sur le web pour '{{searchQuery}}'",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "URL de requête Searxng",
 	"See readme.md for instructions": "Voir readme.md pour les instructions",
 	"See what's new": "Voir les nouveautés",
 	"Seed": "Graine",
 	"Select a base model": "Sélectionner un modèle de base",
+	"Select a engine": "",
 	"Select a mode": "Sélectionner un mode",
 	"Select a model": "Sélectionner un modèle",
 	"Select a pipeline": "Sélectionner un pipeline",
 	"Select a pipeline url": "Sélectionnez une URL de pipeline",
 	"Select an Ollama instance": "Sélectionner une instance Ollama",
+	"Select Documents": "",
 	"Select model": "Sélectionner un modèle",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "Modèle(s) séléctionés ne supportent pas les entrées images",
 	"Send": "Envoyer",
 	"Send a Message": "Envoyer un message",
 	"Send message": "Envoyer un message",
 	"September": "Septembre",
 	"Serper API Key": "Clé API Serper",
+	"Serply API Key": "",
 	"Serpstack API Key": "Clé API Serpstack",
 	"Server connection verified": "Connexion au serveur vérifiée",
 	"Set as default": "Définir par défaut",
 	"Set Default Model": "Définir le Modèle par Défaut",
 	"Set embedding model (e.g. {{model}})": "Définir le modèle d'embedding (p. ex. {{model}})",
 	"Set Image Size": "Définir la Taille de l'Image",
-	"Set Model": "Définir le Modèle",
 	"Set reranking model (e.g. {{model}})": "Définir le modèle de reclassement (p. ex. {{model}})",
 	"Set Steps": "Définir les Étapes",
 	"Set Task Model": "Définir le modèle de tâche",
@@ -449,8 +474,8 @@
 	"Source": "Source",
 	"Speech recognition error: {{error}}": "Erreur de reconnaissance vocale : {{error}}",
 	"Speech-to-Text Engine": "Moteur de Reconnaissance Vocale",
-	"SpeechRecognition API is not supported in this browser.": "L'API SpeechRecognition n'est pas prise en charge dans ce navigateur.",
 	"Stop Sequence": "Séquence d'Arrêt",
+	"STT Model": "",
 	"STT Settings": "Paramètres STT",
 	"Submit": "Envoyer",
 	"Subtitle (e.g. about the Roman Empire)": "Sous-Titres (p. ex. à propos de l'Empire Romain)",
@@ -469,7 +494,9 @@
 	"Thanks for your feedback!": "Merci pour votre avis !",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "Le score devrait avoir une valeur entre 0.0 (0%) et 1.0 (100%).",
 	"Theme": "Thème",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "Cela garantit que vos précieuses conversations sont en sécurité dans votre base de données. Merci !",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "Ce paramètre ne se synchronise pas entre les navigateurs ou les appareils.",
 	"Thorough explanation": "Explication détaillée",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "Conseil : Mettez à jour plusieurs emplacements de variables consécutivement en appuyant sur la touche tab dans l'entrée de chat après chaque remplacement",
@@ -481,6 +508,8 @@
 	"to": "à",
 	"To access the available model names for downloading,": "Pour accéder aux noms de modèles disponibles pour le téléchargement,",
 	"To access the GGUF models available for downloading,": "Pour accéder aux modèles GGUF disponibles pour le téléchargement,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "à l'entrée du chat.",
 	"Today": "Aujourd'hui",
 	"Toggle settings": "Basculer les paramètres",
@@ -488,7 +517,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "Problèmes d'accès à Ollama ?",
+	"TTS Model": "",
 	"TTS Settings": "Paramètres TTS",
+	"TTS Voice": "",
 	"Type": "Type",
 	"Type Hugging Face Resolve (Download) URL": "Entrez l'URL de Résolution (Téléchargement) Hugging Face",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "Uh-oh ! Il y a eu un problème de connexion à {{provider}}.",
@@ -497,6 +528,7 @@
 	"Update password": "Mettre à Jour le Mot de Passe",
 	"Upload a GGUF model": "Téléverser un modèle GGUF",
 	"Upload Files": "Télécharger des fichiers",
+	"Upload Pipeline": "",
 	"Upload Progress": "Progression du Téléversement",
 	"URL Mode": "Mode URL",
 	"Use '#' in the prompt input to load and select your documents.": "Utilisez '#' dans l'entrée du prompt pour charger et sélectionner vos documents.",
@@ -515,6 +547,7 @@
 	"Warning": "Avertissement",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "Avertissement : Si vous mettez à jour ou modifier votre modèle d'embedding, vous devrez réimporter tous les documents.",
 	"Web": "Web",
+	"Web API": "",
 	"Web Loader Settings": "Paramètres du Chargeur Web",
 	"Web Params": "Paramètres Web",
 	"Web Search": "Recherche sur le Web",
@@ -525,17 +558,20 @@
 	"WebUI will make requests to": "WebUI effectuera des demandes à",
 	"What’s New in": "Quoi de neuf dans",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "Lorsque l'historique est désactivé, les nouveaux chats sur ce navigateur n'apparaîtront pas dans votre historique sur aucun de vos appareils.",
-	"Whisper (Local)": "Whisper (Local)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "Espace de Travail",
 	"Write a prompt suggestion (e.g. Who are you?)": "Écrivez une suggestion de prompt (e.x. Qui est-tu ?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "Ecrivez un résumé en 50 mots qui résume [sujet ou mot-clé]",
 	"Yesterday": "Hier",
 	"You": "Vous",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "Vous ne pouvez pas cloner un modèle de base",
 	"You have no archived conversations.": "Vous n'avez pas de conversations archivées",
 	"You have shared this chat": "Vous avez partagé ce chat",
 	"You're a helpful assistant.": "Vous êtes un assistant utile.",
 	"You're now logged in.": "Vous êtes maintenant connecté.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "Paramètres du Chargeur YouTube"
 }

src/lib/i18n/locales/he-IL/translation.json

@@ -12,7 +12,9 @@
 	"a user": "משתמש",
 	"About": "אודות",
 	"Account": "חשבון",
+	"Account Activation Pending": "",
 	"Accurate information": "מידע מדויק",
+	"Active Users": "",
 	"Add": "הוסף",
 	"Add a model id": "הוספת מזהה דגם",
 	"Add a short description about what this model does": "הוסף תיאור קצר אודות אופן הפעולה של מודל זה",
@@ -28,6 +30,7 @@
 	"Add User": "הוסף משתמש",
 	"Adjusting these settings will apply changes universally to all users.": "התאמת הגדרות אלו תחול על כל המשתמשים.",
 	"admin": "מנהל",
+	"Admin": "",
 	"Admin Panel": "לוח בקרה למנהל",
 	"Admin Settings": "הגדרות מנהל",
 	"Advanced Parameters": "פרמטרים מתקדמים",
@@ -58,7 +61,6 @@
 	"Audio": "אודיו",
 	"August": "אוגוסט",
 	"Auto-playback response": "תגובת השמעה אוטומטית",
-	"Auto-send input after 3 sec.": "שליחת קלט אוטומטית אחרי 3 שניות",
 	"AUTOMATIC1111 Base URL": "כתובת URL בסיסית של AUTOMATIC1111",
 	"AUTOMATIC1111 Base URL is required.": "נדרשת כתובת URL בסיסית של AUTOMATIC1111",
 	"available!": "זמין!",
@@ -70,6 +72,9 @@
 	"Being lazy": "להיות עצלן",
 	"Brave Search API Key": "מפתח API של חיפוש אמיץ",
 	"Bypass SSL verification for Websites": "עקוף אימות SSL עבור אתרים",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "בטל",
 	"Capabilities": "יכולות",
 	"Change Password": "שנה סיסמה",
@@ -87,10 +92,12 @@
 	"Chunk Params": "פרמטרי נתונים",
 	"Chunk Size": "גודל נתונים",
 	"Citation": "ציטוט",
+	"Clear memory": "",
 	"Click here for help.": "לחץ כאן לעזרה.",
 	"Click here to": "לחץ כאן כדי",
 	"Click here to select": "לחץ כאן לבחירה",
 	"Click here to select a csv file.": "לחץ כאן לבחירת קובץ csv.",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "לחץ כאן לבחירת מסמכים.",
 	"click here.": "לחץ כאן.",
 	"Click on the user role button to change a user's role.": "לחץ על כפתור תפקיד המשתמש כדי לשנות את תפקיד המשתמש.",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "בקשות בו-זמניות",
 	"Confirm Password": "אשר סיסמה",
 	"Connections": "חיבורים",
+	"Contact Admin for WebUI Access": "",
 	"Content": "תוכן",
 	"Context Length": "אורך הקשר",
 	"Continue Response": "המשך תגובה",
-	"Conversation Mode": "מצב שיחה",
 	"Copied shared chat URL to clipboard!": "העתקת כתובת URL של צ'אט משותף ללוח!",
 	"Copy": "העתק",
 	"Copy last code block": "העתק את בלוק הקוד האחרון",
 	"Copy last response": "העתק את התגובה האחרונה",
 	"Copy Link": "העתק קישור",
 	"Copying to clipboard was successful!": "ההעתקה ללוח הייתה מוצלחת!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "צור ביטוי תמציתי של 3-5 מילים ככותרת לשאילתה הבאה, תוך שמירה מדויקת על מגבלת 3-5 המילים והימנעות משימוש במילה 'כותרת':",
 	"Create a model": "יצירת מודל",
 	"Create Account": "צור חשבון",
 	"Create new key": "צור מפתח חדש",
@@ -126,12 +132,12 @@
 	"Custom": "מותאם אישית",
 	"Customize models for a specific purpose": "התאמה אישית של מודלים למטרה ספציפית",
 	"Dark": "כהה",
+	"Dashboard": "",
 	"Database": "מסד נתונים",
 	"December": "דצמבר",
 	"Default": "ברירת מחדל",
 	"Default (Automatic1111)": "ברירת מחדל (Automatic1111)",
 	"Default (SentenceTransformers)": "ברירת מחדל (SentenceTransformers)",
-	"Default (Web API)": "ברירת מחדל (Web API)",
 	"Default Model": "מודל ברירת מחדל",
 	"Default model updated": "המודל המוגדר כברירת מחדל עודכן",
 	"Default Prompt Suggestions": "הצעות ברירת מחדל לפקודות",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "גלה פקודה",
 	"Discover, download, and explore custom prompts": "גלה, הורד, וחקור פקודות מותאמות אישית",
 	"Discover, download, and explore model presets": "גלה, הורד, וחקור הגדרות מודל מוגדרות מראש",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "הצג את שם המשתמש במקום 'אתה' בצ'אט",
 	"Document": "מסמך",
 	"Document Settings": "הגדרות מסמך",
@@ -194,6 +201,7 @@
 	"Enter Score": "הזן ציון",
 	"Enter Searxng Query URL": "הזן כתובת URL של שאילתת Searxng",
 	"Enter Serper API Key": "הזן מפתח API של Serper",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "הזן מפתח API של Serpstack",
 	"Enter stop sequence": "הזן רצף עצירה",
 	"Enter Top K": "הזן Top K",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "ייצוא מיפוי מסמכים",
 	"Export Models": "ייצוא מודלים",
 	"Export Prompts": "ייצוא פקודות",
+	"External Models": "",
 	"Failed to create API Key.": "יצירת מפתח API נכשלה.",
 	"Failed to read clipboard contents": "קריאת תוכן הלוח נכשלה",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "עקב אחר ההוראות במושלמות",
 	"Format your variables using square brackets like this:": "עצב את המשתנים שלך באמצעות סוגריים מרובעים כך:",
 	"Frequency Penalty": "עונש תדירות",
-	"Full Screen Mode": "מצב מסך מלא",
 	"General": "כללי",
 	"General Settings": "הגדרות כלליות",
+	"Generate Image": "",
 	"Generating search query": "יצירת שאילתת חיפוש",
 	"Generation Info": "מידע על היצירה",
 	"Good Response": "תגובה טובה",
@@ -252,6 +261,7 @@
 	"Info": "מידע",
 	"Input commands": "פקודות קלט",
 	"Install from Github URL": "התקן מכתובת URL של Github",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "ממשק",
 	"Invalid Tag": "תג לא חוקי",
 	"January": "ינואר",
@@ -264,14 +274,17 @@
 	"JWT Token": "אסימון JWT",
 	"Keep Alive": "השאר פעיל",
 	"Keyboard shortcuts": "קיצורי מקלדת",
+	"Knowledge": "",
 	"Language": "שפה",
 	"Last Active": "פעיל לאחרונה",
 	"Light": "בהיר",
-	"Listening...": "מאזין...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "מודלים בשפה טבעית יכולים לטעות. אמת מידע חשוב.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "נוצר על ידי קהילת OpenWebUI",
 	"Make sure to enclose them with": "ודא להקיף אותם עם",
+	"Manage": "",
 	"Manage Models": "נהל מודלים",
 	"Manage Ollama Models": "נהל מודלים של Ollama",
 	"Manage Pipelines": "ניהול צינורות",
@@ -307,6 +320,7 @@
 	"Name your model": "תן שם לדגם שלך",
 	"New Chat": "צ'אט חדש",
 	"New Password": "סיסמה חדשה",
+	"No documents found": "",
 	"No results found": "לא נמצאו תוצאות",
 	"No search query generated": "לא נוצרה שאילתת חיפוש",
 	"No source available": "אין מקור זמין",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "Ollama API",
 	"Ollama API disabled": "Ollama API מושבת",
+	"Ollama API is disabled": "",
 	"Ollama Version": "גרסת Ollama",
 	"On": "פועל",
 	"Only": "רק",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "מסמך PDF (.pdf)",
 	"PDF Extract Images (OCR)": "חילוץ תמונות מ-PDF (OCR)",
 	"pending": "ממתין",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "ההרשאה נדחתה בעת גישה למיקרופון: {{error}}",
 	"Personalization": "תאור",
 	"Pipelines": "צינורות",
@@ -367,6 +384,7 @@
 	"Read Aloud": "קרא בקול",
 	"Record voice": "הקלט קול",
 	"Redirecting you to OpenWebUI Community": "מפנה אותך לקהילת OpenWebUI",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "נדחה כאשר לא היה צריך",
 	"Regenerate": "הפק מחדש",
 	"Release Notes": "הערות שחרור",
@@ -378,12 +396,14 @@
 	"Reranking Model": "מודל דירוג מחדש",
 	"Reranking model disabled": "מודל דירוג מחדש מושבת",
 	"Reranking model set to \"{{reranking_model}}\"": "מודל דירוג מחדש הוגדר ל-\"{{reranking_model}}\"",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "איפוס אחסון וקטורים",
 	"Response AutoCopy to Clipboard": "העתקה אוטומטית של תגובה ללוח",
 	"Role": "תפקיד",
 	"Rosé Pine": "Rosé Pine",
 	"Rosé Pine Dawn": "Rosé Pine Dawn",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "שמור",
 	"Save & Create": "שמור וצור",
 	"Save & Update": "שמור ועדכן",
@@ -397,35 +417,40 @@
 	"Search Documents": "חפש מסמכים",
 	"Search Models": "חיפוש מודלים",
 	"Search Prompts": "חפש פקודות",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "ספירת תוצאות חיפוש",
 	"Searched {{count}} sites_one": "חיפש {{count}} sites_one",
 	"Searched {{count}} sites_two": "חיפש {{count}} sites_two",
 	"Searched {{count}} sites_other": "חיפש {{count}} sites_other",
-	"Searching the web for '{{searchQuery}}'": "חיפוש באינטרנט אחר '{{searchQuery}}'",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "כתובת URL של שאילתת Searxng",
 	"See readme.md for instructions": "ראה את readme.md להוראות",
 	"See what's new": "ראה מה חדש",
 	"Seed": "זרע",
 	"Select a base model": "בחירת מודל בסיס",
+	"Select a engine": "",
 	"Select a mode": "בחר מצב",
 	"Select a model": "בחר מודל",
 	"Select a pipeline": "בחר קו צינור",
 	"Select a pipeline url": "בחר כתובת URL של קו צינור",
 	"Select an Ollama instance": "בחר מופע של Ollama",
+	"Select Documents": "",
 	"Select model": "בחר מודל",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "דגמים נבחרים אינם תומכים בקלט תמונה",
 	"Send": "שלח",
 	"Send a Message": "שלח הודעה",
 	"Send message": "שלח הודעה",
 	"September": "ספטמבר",
 	"Serper API Key": "מפתח Serper API",
+	"Serply API Key": "",
 	"Serpstack API Key": "מפתח API של Serpstack",
 	"Server connection verified": "החיבור לשרת אומת",
 	"Set as default": "הגדר כברירת מחדל",
 	"Set Default Model": "הגדר מודל ברירת מחדל",
 	"Set embedding model (e.g. {{model}})": "הגדר מודל הטמעה (למשל {{model}})",
 	"Set Image Size": "הגדר גודל תמונה",
-	"Set Model": "הגדר מודל",
 	"Set reranking model (e.g. {{model}})": "הגדר מודל דירוג מחדש (למשל {{model}})",
 	"Set Steps": "הגדר שלבים",
 	"Set Task Model": "הגדרת מודל משימה",
@@ -449,8 +474,8 @@
 	"Source": "מקור",
 	"Speech recognition error: {{error}}": "שגיאת תחקור שמע: {{error}}",
 	"Speech-to-Text Engine": "מנוע תחקור שמע",
-	"SpeechRecognition API is not supported in this browser.": "מנוע תחקור שמע אינו נתמך בדפדפן זה.",
 	"Stop Sequence": "סידור עצירה",
+	"STT Model": "",
 	"STT Settings": "הגדרות חקירה של TTS",
 	"Submit": "שלח",
 	"Subtitle (e.g. about the Roman Empire)": "תחקור (לדוגמה: על מעמד הרומי)",
@@ -469,7 +494,9 @@
 	"Thanks for your feedback!": "תודה על המשוב שלך!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "ציון צריך להיות ערך בין 0.0 (0%) ל-1.0 (100%)",
 	"Theme": "נושא",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "פעולה זו מבטיחה שהשיחות בעלות הערך שלך יישמרו באופן מאובטח במסד הנתונים העורפי שלך. תודה!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "הגדרה זו אינה מסתנכרנת בין דפדפנים או מכשירים.",
 	"Thorough explanation": "תיאור מפורט",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "טיפ: עדכן חריצים משתנים מרובים ברציפות על-ידי לחיצה על מקש Tab בקלט הצ'אט לאחר כל החלפה.",
@@ -481,6 +508,8 @@
 	"to": "ל",
 	"To access the available model names for downloading,": "כדי לגשת לשמות הדגמים הזמינים להורדה,",
 	"To access the GGUF models available for downloading,": "כדי לגשת לדגמי GGUF הזמינים להורדה,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "לקלטת שיחה.",
 	"Today": "היום",
 	"Toggle settings": "החלפת מצב של הגדרות",
@@ -488,7 +517,9 @@
 	"Top K": "Top K",
 	"Top P": "Top P",
 	"Trouble accessing Ollama?": "קשה לגשת לOllama?",
+	"TTS Model": "",
 	"TTS Settings": "הגדרות TTS",
+	"TTS Voice": "",
 	"Type": "סוג",
 	"Type Hugging Face Resolve (Download) URL": "הקלד כתובת URL של פתרון פנים מחבק (הורד)",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "או-הו! אירעה בעיה בהתחברות ל- {{provider}}.",
@@ -497,6 +528,7 @@
 	"Update password": "עדכן סיסמה",
 	"Upload a GGUF model": "העלה מודל GGUF",
 	"Upload Files": "העלאת קבצים",
+	"Upload Pipeline": "",
 	"Upload Progress": "תקדמות העלאה",
 	"URL Mode": "מצב URL",
 	"Use '#' in the prompt input to load and select your documents.": "השתמש ב- '#' בקלט הבקשה כדי לטעון ולבחור את המסמכים שלך.",
@@ -515,6 +547,7 @@
 	"Warning": "אזהרה",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "אזהרה: אם תעדכן או תשנה את מודל ההטבעה שלך, יהיה עליך לייבא מחדש את כל המסמכים.",
 	"Web": "רשת",
+	"Web API": "",
 	"Web Loader Settings": "הגדרות טעינת אתר",
 	"Web Params": "פרמטרים Web",
 	"Web Search": "חיפוש באינטרנט",
@@ -525,17 +558,20 @@
 	"WebUI will make requests to": "WebUI יבקש לבקש",
 	"What’s New in": "מה חדש ב",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "כאשר ההיסטוריה מושבתת, צ'אטים חדשים בדפדפן זה לא יופיעו בהיסטוריה שלך באף אחד מהמכשירים שלך.",
-	"Whisper (Local)": "ושפה (מקומית)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "סביבה",
 	"Write a prompt suggestion (e.g. Who are you?)": "כתוב הצעה מהירה (למשל, מי אתה?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "כתוב סיכום ב-50 מילים שמסכם [נושא או מילת מפתח].",
 	"Yesterday": "אתמול",
 	"You": "אתה",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "לא ניתן לשכפל מודל בסיס",
 	"You have no archived conversations.": "אין לך שיחות בארכיון.",
 	"You have shared this chat": "שיתפת את השיחה הזו",
 	"You're a helpful assistant.": "אתה עוזר מועיל.",
 	"You're now logged in.": "כעת אתה מחובר.",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "הגדרות Youtube Loader"
 }

src/lib/i18n/locales/hi-IN/translation.json

@@ -12,7 +12,9 @@
 	"a user": "एक उपयोगकर्ता",
 	"About": "हमारे बारे में",
 	"Account": "खाता",
+	"Account Activation Pending": "",
 	"Accurate information": "सटीक जानकारी",
+	"Active Users": "",
 	"Add": "जोड़ें",
 	"Add a model id": "मॉडल आईडी जोड़ना",
 	"Add a short description about what this model does": "इस मॉडल के बारे में एक संक्षिप्त विवरण जोड़ें",
@@ -28,6 +30,7 @@
 	"Add User": "उपयोगकर्ता जोड़ें",
 	"Adjusting these settings will apply changes universally to all users.": "इन सेटिंग्स को समायोजित करने से परिवर्तन सभी उपयोगकर्ताओं पर सार्वभौमिक रूप से लागू होंगे।",
 	"admin": "व्यवस्थापक",
+	"Admin": "",
 	"Admin Panel": "व्यवस्थापक पैनल",
 	"Admin Settings": "व्यवस्थापक सेटिंग्स",
 	"Advanced Parameters": "उन्नत पैरामीटर",
@@ -58,7 +61,6 @@
 	"Audio": "ऑडियो",
 	"August": "अगस्त",
 	"Auto-playback response": "ऑटो-प्लेबैक प्रतिक्रिया",
-	"Auto-send input after 3 sec.": "3 सेकंड के बाद स्वचालित रूप से इनपुट भेजें।",
 	"AUTOMATIC1111 Base URL": "AUTOMATIC1111 बेस यूआरएल",
 	"AUTOMATIC1111 Base URL is required.": "AUTOMATIC1111 का बेस यूआरएल आवश्यक है।",
 	"available!": "उपलब्ध!",
@@ -70,6 +72,9 @@
 	"Being lazy": "आलसी होना",
 	"Brave Search API Key": "Brave सर्च एपीआई कुंजी",
 	"Bypass SSL verification for Websites": "वेबसाइटों के लिए SSL सुनिश्चिती को छोड़ें",
+	"Call": "",
+	"Call feature is not supported when using Web STT engine": "",
+	"Camera": "",
 	"Cancel": "रद्द करें",
 	"Capabilities": "क्षमताओं",
 	"Change Password": "पासवर्ड बदलें",
@@ -87,10 +92,12 @@
 	"Chunk Params": "चंक पैरामीटर्स",
 	"Chunk Size": "चंक आकार",
 	"Citation": "उद्धरण",
+	"Clear memory": "",
 	"Click here for help.": "सहायता के लिए यहां क्लिक करें।",
 	"Click here to": "यहां क्लिक करें",
 	"Click here to select": "चयन करने के लिए यहां क्लिक करें।",
 	"Click here to select a csv file.": "सीएसवी फ़ाइल का चयन करने के लिए यहां क्लिक करें।",
+	"Click here to select a py file.": "",
 	"Click here to select documents.": "दस्तावेज़ चुनने के लिए यहां क्लिक करें।",
 	"click here.": "यहाँ क्लिक करें।",
 	"Click on the user role button to change a user's role.": "उपयोगकर्ता की भूमिका बदलने के लिए उपयोगकर्ता भूमिका बटन पर क्लिक करें।",
@@ -104,17 +111,16 @@
 	"Concurrent Requests": "समवर्ती अनुरोध",
 	"Confirm Password": "पासवर्ड की पुष्टि कीजिये",
 	"Connections": "सम्बन्ध",
+	"Contact Admin for WebUI Access": "",
 	"Content": "सामग्री",
 	"Context Length": "प्रसंग की लंबाई",
 	"Continue Response": "प्रतिक्रिया जारी रखें",
-	"Conversation Mode": "बातचीत का मॉड",
 	"Copied shared chat URL to clipboard!": "साझा चैट URL को क्लिपबोर्ड पर कॉपी किया गया!",
 	"Copy": "कॉपी",
 	"Copy last code block": "अंतिम कोड ब्लॉक कॉपी करें",
 	"Copy last response": "अंतिम प्रतिक्रिया कॉपी करें",
 	"Copy Link": "लिंक को कॉपी करें",
 	"Copying to clipboard was successful!": "क्लिपबोर्ड पर कॉपी बनाना सफल रहा!",
-	"Create a concise, 3-5 word phrase as a header for the following query, strictly adhering to the 3-5 word limit and avoiding the use of the word 'title':": "निम्नलिखित क्वेरी के लिए हेडर के रूप में एक संक्षिप्त, 3-5 शब्द वाक्यांश बनाएं, 3-5 शब्द सीमा का सख्ती से पालन करें और 'शीर्षक' शब्द के उपयोग से बचें:",
 	"Create a model": "एक मॉडल बनाएं",
 	"Create Account": "खाता बनाएं",
 	"Create new key": "नया क्रिप्टोग्राफिक क्षेत्र बनाएं",
@@ -126,12 +132,12 @@
 	"Custom": "कस्टम संस्करण",
 	"Customize models for a specific purpose": "एक विशिष्ट उद्देश्य के लिए मॉडल अनुकूलित करें",
 	"Dark": "डार्क",
+	"Dashboard": "",
 	"Database": "डेटाबेस",
 	"December": "डिसेंबर",
 	"Default": "डिफ़ॉल्ट",
 	"Default (Automatic1111)": "डिफ़ॉल्ट (Automatic1111)",
 	"Default (SentenceTransformers)": "डिफ़ॉल्ट (SentenceTransformers)",
-	"Default (Web API)": "डिफ़ॉल्ट (Web API)",
 	"Default Model": "डिफ़ॉल्ट मॉडल",
 	"Default model updated": "डिफ़ॉल्ट मॉडल अपडेट किया गया",
 	"Default Prompt Suggestions": "डिफ़ॉल्ट प्रॉम्प्ट सुझाव",
@@ -152,6 +158,7 @@
 	"Discover a prompt": "प्रॉम्प्ट खोजें",
 	"Discover, download, and explore custom prompts": "कस्टम प्रॉम्प्ट को खोजें, डाउनलोड करें और एक्सप्लोर करें",
 	"Discover, download, and explore model presets": "मॉडल प्रीसेट खोजें, डाउनलोड करें और एक्सप्लोर करें",
+	"Dismissible": "",
 	"Display the username instead of You in the Chat": "चैट में 'आप' के स्थान पर उपयोगकर्ता नाम प्रदर्शित करें",
 	"Document": "दस्तावेज़",
 	"Document Settings": "दस्तावेज़ सेटिंग्स",
@@ -194,6 +201,7 @@
 	"Enter Score": "स्कोर दर्ज करें",
 	"Enter Searxng Query URL": "Searxng क्वेरी URL दर्ज करें",
 	"Enter Serper API Key": "Serper API कुंजी दर्ज करें",
+	"Enter Serply API Key": "",
 	"Enter Serpstack API Key": "सर्पस्टैक एपीआई कुंजी दर्ज करें",
 	"Enter stop sequence": "स्टॉप अनुक्रम दर्ज करें",
 	"Enter Top K": "शीर्ष K दर्ज करें",
@@ -212,6 +220,7 @@
 	"Export Documents Mapping": "निर्यात दस्तावेज़ मैपिंग",
 	"Export Models": "निर्यात मॉडल",
 	"Export Prompts": "प्रॉम्प्ट निर्यात करें",
+	"External Models": "",
 	"Failed to create API Key.": "एपीआई कुंजी बनाने में विफल.",
 	"Failed to read clipboard contents": "क्लिपबोर्ड सामग्री पढ़ने में विफल",
 	"Failed to update settings": "",
@@ -225,9 +234,9 @@
 	"Followed instructions perfectly": "निर्देशों का पूर्णतः पालन किया",
 	"Format your variables using square brackets like this:": "वर्गाकार कोष्ठकों का उपयोग करके अपने चरों को इस प्रकार प्रारूपित करें :",
 	"Frequency Penalty": "फ्रीक्वेंसी पेनल्टी",
-	"Full Screen Mode": "पूर्ण स्क्रीन मोड",
 	"General": "सामान्य",
 	"General Settings": "सामान्य सेटिंग्स",
+	"Generate Image": "",
 	"Generating search query": "खोज क्वेरी जनरेट करना",
 	"Generation Info": "जनरेशन की जानकारी",
 	"Good Response": "अच्छी प्रतिक्रिया",
@@ -252,6 +261,7 @@
 	"Info": "सूचना-विषयक",
 	"Input commands": "इनपुट क命",
 	"Install from Github URL": "Github URL से इंस्टॉल करें",
+	"Instant Auto-Send After Voice Transcription": "",
 	"Interface": "इंटरफेस",
 	"Invalid Tag": "अवैध टैग",
 	"January": "जनवरी",
@@ -264,14 +274,17 @@
 	"JWT Token": "जट टोकन",
 	"Keep Alive": "क्रियाशील रहो",
 	"Keyboard shortcuts": "कीबोर्ड शॉर्टकट",
+	"Knowledge": "",
 	"Language": "भाषा",
 	"Last Active": "पिछली बार सक्रिय",
 	"Light": "सुन",
-	"Listening...": "सुन रहा हूँ...",
+	"Listening...": "",
 	"LLMs can make mistakes. Verify important information.": "एलएलएम गलतियाँ कर सकते हैं। महत्वपूर्ण जानकारी सत्यापित करें.",
+	"Local Models": "",
 	"LTR": "LTR",
 	"Made by OpenWebUI Community": "OpenWebUI समुदाय द्वारा निर्मित",
 	"Make sure to enclose them with": "उन्हें संलग्न करना सुनिश्चित करें",
+	"Manage": "",
 	"Manage Models": "मॉडल प्रबंधित करें",
 	"Manage Ollama Models": "Ollama मॉडल प्रबंधित करें",
 	"Manage Pipelines": "पाइपलाइनों का प्रबंधन करें",
@@ -307,6 +320,7 @@
 	"Name your model": "अपने मॉडल को नाम दें",
 	"New Chat": "नई चैट",
 	"New Password": "नया पासवर्ड",
+	"No documents found": "",
 	"No results found": "कोई परिणाम नहीं मिला",
 	"No search query generated": "कोई खोज क्वेरी जनरेट नहीं हुई",
 	"No source available": "कोई स्रोत उपलब्ध नहीं है",
@@ -323,6 +337,7 @@
 	"Ollama": "Ollama",
 	"Ollama API": "ओलामा एपीआई",
 	"Ollama API disabled": "ओलामा एपीआई अक्षम",
+	"Ollama API is disabled": "",
 	"Ollama Version": "Ollama Version",
 	"On": "चालू",
 	"Only": "केवल",
@@ -345,6 +360,8 @@
 	"PDF document (.pdf)": "PDF दस्तावेज़ (.pdf)",
 	"PDF Extract Images (OCR)": "PDF छवियाँ निकालें (OCR)",
 	"pending": "लंबित",
+	"Permission denied when accessing media devices": "",
+	"Permission denied when accessing microphone": "",
 	"Permission denied when accessing microphone: {{error}}": "माइक्रोफ़ोन तक पहुँचने पर अनुमति अस्वीकृत: {{error}}",
 	"Personalization": "पेरसनलाइज़मेंट",
 	"Pipelines": "पाइपलाइनों",
@@ -367,6 +384,7 @@
 	"Read Aloud": "जोर से पढ़ें",
 	"Record voice": "आवाज रिकॉर्ड करना",
 	"Redirecting you to OpenWebUI Community": "आपको OpenWebUI समुदाय पर पुनर्निर्देशित किया जा रहा है",
+	"Refer to yourself as \"User\" (e.g., \"User is learning Spanish\")": "",
 	"Refused when it shouldn't have": "जब ऐसा नहीं होना चाहिए था तो मना कर दिया",
 	"Regenerate": "पुनः जेनरेट",
 	"Release Notes": "रिलीज नोट्स",
@@ -378,12 +396,14 @@
 	"Reranking Model": "रीरैकिंग मोड",
 	"Reranking model disabled": "पुनर्रैंकिंग मॉडल अक्षम किया गया",
 	"Reranking model set to \"{{reranking_model}}\"": "रीरैंकिंग मॉडल को \"{{reranking_model}}\" पर \u200b\u200bसेट किया गया",
+	"Reset Upload Directory": "",
 	"Reset Vector Storage": "वेक्टर संग्रहण रीसेट करें",
 	"Response AutoCopy to Clipboard": "क्लिपबोर्ड पर प्रतिक्रिया ऑटोकॉपी",
 	"Role": "भूमिका",
 	"Rosé Pine": "रोसे पिन",
 	"Rosé Pine Dawn": "रोसे पिन डेन",
 	"RTL": "RTL",
+	"Running": "",
 	"Save": "सहेजें",
 	"Save & Create": "सहेजें और बनाएं",
 	"Save & Update": "सहेजें और अपडेट करें",
@@ -397,34 +417,39 @@
 	"Search Documents": "दस्तावेज़ खोजें",
 	"Search Models": "मॉडल खोजें",
 	"Search Prompts": "प्रॉम्प्ट खोजें",
+	"Search Query Generation Prompt": "",
+	"Search Query Generation Prompt Length Threshold": "",
 	"Search Result Count": "खोज परिणामों की संख्या",
 	"Searched {{count}} sites_one": "{{count}} sites_one खोजा गया",
 	"Searched {{count}} sites_other": "{{count}} sites_other खोजा गया",
-	"Searching the web for '{{searchQuery}}'": "वेब पर '{{searchQuery}}' खोजना",
+	"Searching \"{{searchQuery}}\"": "",
 	"Searxng Query URL": "Searxng क्वेरी URL",
 	"See readme.md for instructions": "निर्देशों के लिए readme.md देखें",
 	"See what's new": "देखें, क्या नया है",
 	"Seed": "सीड्\u200c",
 	"Select a base model": "एक आधार मॉडल का चयन करें",
+	"Select a engine": "",
 	"Select a mode": "एक मोड चुनें",
 	"Select a model": "एक मॉडल चुनें",
 	"Select a pipeline": "एक पाइपलाइन का चयन करें",
 	"Select a pipeline url": "एक पाइपलाइन url चुनें",
 	"Select an Ollama instance": "एक Ollama Instance चुनें",
+	"Select Documents": "",
 	"Select model": "मॉडल चुनें",
+	"Select only one model to call": "",
 	"Selected model(s) do not support image inputs": "चयनित मॉडल छवि इनपुट का समर्थन नहीं करते हैं",
 	"Send": "भेज",
 	"Send a Message": "एक संदेश भेजो",
 	"Send message": "मेसेज भेजें",
 	"September": "सितंबर",
 	"Serper API Key": "Serper API कुंजी",
+	"Serply API Key": "",
 	"Serpstack API Key": "सर्पस्टैक एपीआई कुंजी",
 	"Server connection verified": "सर्वर कनेक्शन सत्यापित",
 	"Set as default": "डिफाल्ट के रूप में सेट",
 	"Set Default Model": "डिफ़ॉल्ट मॉडल सेट करें",
 	"Set embedding model (e.g. {{model}})": "ईम्बेडिंग मॉडल सेट करें (उदाहरण: {{model}})",
 	"Set Image Size": "छवि का आकार सेट करें",
-	"Set Model": "मॉडल सेट करें",
 	"Set reranking model (e.g. {{model}})": "रीकरण मॉडल सेट करें (उदाहरण: {{model}})",
 	"Set Steps": "चरण निर्धारित करें",
 	"Set Task Model": "कार्य मॉडल सेट करें",
@@ -448,8 +473,8 @@
 	"Source": "स्रोत",
 	"Speech recognition error: {{error}}": "वाक् पहचान त्रुटि: {{error}}",
 	"Speech-to-Text Engine": "वाक्-से-पाठ इंजन",
-	"SpeechRecognition API is not supported in this browser.": "इस ब्राउज़र में SpeechRecognition API समर्थित नहीं है",
 	"Stop Sequence": "अनुक्रम रोकें",
+	"STT Model": "",
 	"STT Settings": "STT सेटिंग्स ",
 	"Submit": "सबमिट करें",
 	"Subtitle (e.g. about the Roman Empire)": "उपशीर्षक (जैसे रोमन साम्राज्य के बारे में)",
@@ -468,7 +493,9 @@
 	"Thanks for your feedback!": "आपकी प्रतिक्रिया के लिए धन्यवाद!",
 	"The score should be a value between 0.0 (0%) and 1.0 (100%).": "स्कोर का मान 0.0 (0%) और 1.0 (100%) के बीच होना चाहिए।",
 	"Theme": "थीम",
+	"Thinking...": "",
 	"This ensures that your valuable conversations are securely saved to your backend database. Thank you!": "यह सुनिश्चित करता है कि आपकी मूल्यवान बातचीत आपके बैकएंड डेटाबेस में सुरक्षित रूप से सहेजी गई है। धन्यवाद!",
+	"This is an experimental feature, it may not function as expected and is subject to change at any time.": "",
 	"This setting does not sync across browsers or devices.": "यह सेटिंग सभी ब्राउज़रों या डिवाइसों में समन्वयित नहीं होती है",
 	"Thorough explanation": "विस्तृत व्याख्या",
 	"Tip: Update multiple variable slots consecutively by pressing the tab key in the chat input after each replacement.": "टिप: प्रत्येक प्रतिस्थापन के बाद चैट इनपुट में टैब कुंजी दबाकर लगातार कई वैरिएबल स्लॉट अपडेट करें।",
@@ -480,6 +507,8 @@
 	"to": "तक",
 	"To access the available model names for downloading,": "डाउनलोड करने के लिए उपलब्ध मॉडल नामों तक पहुंचने के लिए,",
 	"To access the GGUF models available for downloading,": "डाउनलोडिंग के लिए उपलब्ध GGUF मॉडल तक पहुँचने के लिए,",
+	"To access the WebUI, please reach out to the administrator. Admins can manage user statuses from the Admin Panel.": "",
+	"To add documents here, upload them to the \"Documents\" workspace first.": "",
 	"to chat input.": "इनपुट चैट करने के लिए.",
 	"Today": "आज",
 	"Toggle settings": "सेटिंग्स टॉगल करें",
@@ -487,7 +516,9 @@
 	"Top K": "शीर्ष  K",
 	"Top P": "शीर्ष  P",
 	"Trouble accessing Ollama?": "Ollama तक पहुँचने में परेशानी हो रही है?",
+	"TTS Model": "",
 	"TTS Settings": "TTS सेटिंग्स",
+	"TTS Voice": "",
 	"Type": "प्रकार",
 	"Type Hugging Face Resolve (Download) URL": "हगिंग फेस रिज़ॉल्व (डाउनलोड) यूआरएल टाइप करें",
 	"Uh-oh! There was an issue connecting to {{provider}}.": "उह ओह! {{provider}} से कनेक्ट करने में एक समस्या थी।",
@@ -496,6 +527,7 @@
 	"Update password": "पासवर्ड अपडेट करें",
 	"Upload a GGUF model": "GGUF मॉडल अपलोड करें",
 	"Upload Files": "फ़ाइलें अपलोड करें",
+	"Upload Pipeline": "",
 	"Upload Progress": "प्रगति अपलोड करें",
 	"URL Mode": "URL मोड",
 	"Use '#' in the prompt input to load and select your documents.": "अपने दस्तावेज़ों को लोड करने और चुनने के लिए शीघ्र इनपुट में '#' का उपयोग करें।",
@@ -514,6 +546,7 @@
 	"Warning": "चेतावनी",
 	"Warning: If you update or change your embedding model, you will need to re-import all documents.": "चेतावनी: यदि आप अपने एम्बेडिंग मॉडल को अपडेट या बदलते हैं, तो आपको सभी दस्तावेज़ों को फिर से आयात करने की आवश्यकता होगी।",
 	"Web": "वेब",
+	"Web API": "",
 	"Web Loader Settings": "वेब लोडर सेटिंग्स",
 	"Web Params": "वेब पैरामीटर",
 	"Web Search": "वेब खोज",
@@ -524,17 +557,20 @@
 	"WebUI will make requests to": "WebUI अनुरोध करेगा",
 	"What’s New in": "इसमें नया क्या है",
 	"When history is turned off, new chats on this browser won't appear in your history on any of your devices.": "जब इतिहास बंद हो जाता है, तो इस ब्राउज़र पर नई चैट आपके किसी भी डिवाइस पर इतिहास में दिखाई नहीं देंगी।",
-	"Whisper (Local)": "Whisper (स्थानीय)",
+	"Whisper (Local)": "",
+	"Widescreen Mode": "",
 	"Workspace": "वर्कस्पेस",
 	"Write a prompt suggestion (e.g. Who are you?)": "एक त्वरित सुझाव लिखें (जैसे कि आप कौन हैं?)",
 	"Write a summary in 50 words that summarizes [topic or keyword].": "50 शब्दों में एक सारांश लिखें जो [विषय या कीवर्ड] का सारांश प्रस्तुत करता हो।",
 	"Yesterday": "कल",
 	"You": "आप",
+	"You can personalize your interactions with LLMs by adding memories through the 'Manage' button below, making them more helpful and tailored to you.": "",
 	"You cannot clone a base model": "आप बेस मॉडल का क्लोन नहीं बना सकते",
 	"You have no archived conversations.": "आपको कोई अंकित चैट नहीं है।",
 	"You have shared this chat": "आपने इस चैट को शेयर किया है",
 	"You're a helpful assistant.": "आप एक सहायक सहायक हैं",
 	"You're now logged in.": "अब आप लॉग इन हो गए हैं",
+	"Your account status is currently pending activation.": "",
 	"Youtube": "Youtube",
 	"Youtube Loader Settings": "यूट्यूब लोडर सेटिंग्स"
 }