Merge pull request #4434 from open-webui/dev

0.3.13

.github/ISSUE_TEMPLATE/bug_report.md

@@ -8,36 +8,43 @@ assignees: ''
 
 # Bug Report
 
-## Description
+## Installation Method
 
-**Bug Summary:**
-[Provide a brief but clear summary of the bug]
-
-**Steps to Reproduce:**
-[Outline the steps to reproduce the bug. Be as detailed as possible.]
-
-**Expected Behavior:**
-[Describe what you expected to happen.]
-
-**Actual Behavior:**
-[Describe what actually happened.]
+[Describe the method you used to install the project, e.g., git clone, Docker, pip, etc.]
 
 ## Environment
 
-- **Open WebUI Version:** [e.g., 0.1.120]
-- **Ollama (if applicable):** [e.g., 0.1.30, 0.1.32-rc1]
+- **Open WebUI Version:** [e.g., v0.3.11]
+- **Ollama (if applicable):** [e.g., v0.2.0, v0.1.32-rc1]
 
 - **Operating System:** [e.g., Windows 10, macOS Big Sur, Ubuntu 20.04]
 - **Browser (if applicable):** [e.g., Chrome 100.0, Firefox 98.0]
 
-## Reproduction Details
-
 **Confirmation:**
 
 - [ ] I have read and followed all the instructions provided in the README.md.
 - [ ] I am on the latest version of both Open WebUI and Ollama.
 - [ ] I have included the browser console logs.
 - [ ] I have included the Docker container logs.
+- [ ] I have provided the exact steps to reproduce the bug in the "Steps to Reproduce" section below.
+
+## Expected Behavior:
+
+[Describe what you expected to happen.]
+
+## Actual Behavior:
+
+[Describe what actually happened.]
+
+## Description
+
+**Bug Summary:**
+[Provide a brief but clear summary of the bug]
+
+## Reproduction Details
+
+**Steps to Reproduce:**
+[Outline the steps to reproduce the bug. Be as detailed as possible.]
 
 ## Logs and Screenshots
 
@@ -47,13 +54,9 @@ assignees: ''
 **Docker Container Logs:**
 [Include relevant Docker container logs, if applicable]
 
-**Screenshots (if applicable):**
+**Screenshots/Screen Recordings (if applicable):**
 [Attach any relevant screenshots to help illustrate the issue]
 
-## Installation Method
-
-[Describe the method you used to install the project, e.g., manual installation, Docker, package manager, etc.]
-
 ## Additional Information
 
 [Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]

.github/workflows/integration-test.yml

@@ -15,6 +15,13 @@ jobs:
     name: Run Cypress Integration Tests
     runs-on: ubuntu-latest
     steps:
+      - name: Maximize build space
+        uses: AdityaGarg8/remove-unwanted-software@v4.1
+        with:
+          remove-android: 'true'
+          remove-haskell: 'true'
+          remove-codeql: 'true'
+
       - name: Checkout Repository
         uses: actions/checkout@v4
 
@@ -26,6 +33,10 @@ jobs:
             --file docker-compose.a1111-test.yaml \
             up --detach --build
 
+      - name: Delete Docker build cache
+        run: |
+          docker builder prune --all --force
+
       - name: Wait for Ollama to be up
         timeout-minutes: 5
         run: |
@@ -35,10 +46,6 @@ jobs:
           done
           echo "Service is up!"
 
-      - name: Delete Docker build cache
-        run: |
-          docker builder prune --all --force
-
       - name: Preload Ollama model
         run: |
           docker exec ollama ollama pull qwen:0.5b-chat-v1.5-q2_K

CHANGELOG.md

@@ -5,6 +5,86 @@ 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).
 
+## [0.3.13] - 2024-08-14
+
+### Added
+
+- **🎨 Enhanced Markdown Rendering**: Significant improvements in rendering markdown, ensuring smooth and reliable display of LaTeX and Mermaid charts, enhancing user experience with more robust visual content.
+- **🔄 Auto-Install Tools & Functions Python Dependencies**: For 'Tools' and 'Functions', Open WebUI now automatically install extra python requirements specified in the frontmatter, streamlining setup processes and customization.
+- **🌀 OAuth Email Claim Customization**: Introduced an 'OAUTH_EMAIL_CLAIM' variable to allow customization of the default "email" claim within OAuth configurations, providing greater flexibility in authentication processes.
+- **📶 Websocket Reconnection**: Enhanced reliability with the capability to automatically reconnect when a websocket is closed, ensuring consistent and stable communication.
+- **🤳 Haptic Feedback on Support Devices**: Android devices now support haptic feedback for an immersive tactile experience during certain interactions.
+
+### Fixed
+
+- **🛠️ ComfyUI Performance Improvement**: Addressed an issue causing FastAPI to stall when ComfyUI image generation was active; now runs in a separate thread to prevent UI unresponsiveness.
+- **🔀 Session Handling**: Fixed an issue mandating session_id on client-side to ensure smoother session management and transitions.
+- **🖋️ Minor Bug Fixes and Format Corrections**: Various minor fixes including typo corrections, backend formatting improvements, and test amendments enhancing overall system stability and performance.
+
+### Changed
+
+- **🚀 Migration to SvelteKit 2**: Upgraded the underlying framework to SvelteKit version 2, offering enhanced speed, better code structure, and improved deployment capabilities.
+- **🧹 General Cleanup and Refactoring**: Performed broad cleanup and refactoring across the platform, improving code efficiency and maintaining high standards of code health.
+- **🚧 Integration Testing Improvements**: Modified how Cypress integration tests detect chat messages and updated sharing tests for better reliability and accuracy.
+- **📁 Standardized '.safetensors' File Extension**: Renamed the '.sft' file extension to '.safetensors' for ComfyUI workflows, standardizing file formats across the platform.
+
+### Removed
+
+- **🗑️ Deprecated Frontend Functions**: Removed frontend functions that were migrated to backend to declutter the codebase and reduce redundancy.
+
+## [0.3.12] - 2024-08-07
+
+### Added
+
+- **🔄 Sidebar Infinite Scroll**: Added an infinite scroll feature in the sidebar for more efficient chat navigation, reducing load times and enhancing user experience.
+- **🚀 Enhanced Markdown Rendering**: Support for rendering all code blocks and making images clickable for preview; codespan styling is also enhanced to improve readability and user interaction.
+- **🔒 Admin Shared Chat Visibility**: Admins no longer have default visibility over shared chats when ENABLE_ADMIN_CHAT_ACCESS is set to false, tightening security and privacy settings for users.
+- **🌍 Language Updates**: Added Malay (Bahasa Malaysia) translation and updated Catalan and Traditional Chinese translations to improve accessibility for more users.
+
+### Fixed
+
+- **📊 Markdown Rendering Issues**: Resolved issues with markdown rendering to ensure consistent and correct display across components.
+- **🛠️ Styling Issues**: Multiple fixes applied to styling throughout the application, improving the overall visual experience and interface consistency.
+- **🗃️ Modal Handling**: Fixed an issue where modals were not closing correctly in various model chat scenarios, enhancing usability and interface reliability.
+- **📄 Missing OpenAI Usage Information**: Resolved issues where usage statistics for OpenAI services were not being correctly displayed, ensuring users have access to crucial data for managing and monitoring their API consumption.
+- **🔧 Non-Streaming Support for Functions Plugin**: Fixed a functionality issue with the Functions plugin where non-streaming operations were not functioning as intended, restoring full capabilities for async and sync integration within the platform.
+- **🔄 Environment Variable Type Correction (COMFYUI_FLUX_FP8_CLIP)**: Corrected the data type of the 'COMFYUI_FLUX_FP8_CLIP' environment variable from string to boolean, ensuring environment settings apply correctly and enhance configuration management.
+
+### Changed
+
+- **🔧 Backend Dependency Updates**: Updated several backend dependencies such as boto3, pypdf, python-pptx, validators, and black, ensuring up-to-date security and performance optimizations.
+
+## [0.3.11] - 2024-08-02
+
+### Added
+
+- **📊 Model Information Display**: Added visuals for model selection, including images next to model names for more intuitive navigation.
+- **🗣 ElevenLabs Voice Adaptations**: Voice enhancements including support for ElevenLabs voice ID by name for personalized vocal interactions.
+- **⌨️ Arrow Keys Model Selection**: Users can now use arrow keys for quicker model selection, enhancing accessibility.
+- **🔍 Fuzzy Search in Model Selector**: Enhanced model selector with fuzzy search to locate models swiftly, including descriptions.
+- **🕹️ ComfyUI Flux Image Generation**: Added support for the new Flux image gen model; introduces environment controls like weight precision and CLIP model options in Settings.
+- **💾 Display File Size for Uploads**: Enhanced file interface now displays file size, preparing for upcoming upload restrictions.
+- **🎚️ Advanced Params "Min P"**: Added 'Min P' parameter in the advanced settings for customized model precision control.
+- **🔒 Enhanced OAuth**: Introduced custom redirect URI support for OAuth behind reverse proxies, enabling safer authentication processes.
+- **🖥 Enhanced Latex Rendering**: Adjustments made to latex rendering processes, now accurately detecting and presenting latex inputs from text.
+- **🌐 Internationalization**: Enhanced with new Romanian and updated Vietnamese and Ukrainian translations, helping broaden accessibility for international users.
+
+### Fixed
+
+- **🔧 Tags Handling in Document Upload**: Tags are now properly sent to the upload document handler, resolving issues with missing metadata.
+- **🖥️ Sensitive Input Fields**: Corrected browser misinterpretation of secure input fields, preventing misclassification as password fields.
+- **📂 Static Path Resolution in PDF Generation**: Fixed static paths that adjust dynamically to prevent issues across various environments.
+
+### Changed
+
+- **🎨 UI/UX Styling Enhancements**: Multiple minor styling updates for a cleaner and more intuitive user interface.
+- **🚧 Refactoring Various Components**: Numerous refactoring changes across styling, file handling, and function simplifications for clarity and performance.
+- **🎛️ User Valves Management**: Moved user valves from settings to direct chat controls for more user-friendly access during interactions.
+
+### Removed
+
+- **⚙️ Health Check Logging**: Removed verbose logging from the health checking processes to declutter logs and improve backend performance.
+
 ## [0.3.10] - 2024-07-17
 
 ### Fixed

Dockerfile

@@ -151,7 +151,7 @@ COPY --chown=$UID:$GID ./backend .
 
 EXPOSE 8080
 
-HEALTHCHECK CMD curl --silent --fail http://localhost:8080/health | jq -e '.status == true' || exit 1
+HEALTHCHECK CMD curl --silent --fail http://localhost:${PORT:-8080}/health | jq -ne 'input.status == true' || exit 1
 
 USER $UID:$GID
 

backend/apps/audio/main.py

@@ -10,12 +10,12 @@ from fastapi import (
     File,
     Form,
 )
-
 from fastapi.responses import StreamingResponse, JSONResponse, FileResponse
 
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
 
+
 import uuid
 import requests
 import hashlib
@@ -31,6 +31,7 @@ from utils.utils import (
 )
 from utils.misc import calculate_sha256
 
+
 from config import (
     SRC_LOG_LEVELS,
     CACHE_DIR,
@@ -43,6 +44,7 @@ from config import (
     AUDIO_STT_OPENAI_API_KEY,
     AUDIO_TTS_OPENAI_API_BASE_URL,
     AUDIO_TTS_OPENAI_API_KEY,
+    AUDIO_TTS_API_KEY,
     AUDIO_STT_ENGINE,
     AUDIO_STT_MODEL,
     AUDIO_TTS_ENGINE,
@@ -75,6 +77,7 @@ 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
+app.state.config.TTS_API_KEY = AUDIO_TTS_API_KEY
 
 # setting device type for whisper model
 whisper_device_type = DEVICE_TYPE if DEVICE_TYPE and DEVICE_TYPE == "cuda" else "cpu"
@@ -87,6 +90,7 @@ SPEECH_CACHE_DIR.mkdir(parents=True, exist_ok=True)
 class TTSConfigForm(BaseModel):
     OPENAI_API_BASE_URL: str
     OPENAI_API_KEY: str
+    API_KEY: str
     ENGINE: str
     MODEL: str
     VOICE: str
@@ -137,6 +141,7 @@ async def get_audio_config(user=Depends(get_admin_user)):
         "tts": {
             "OPENAI_API_BASE_URL": app.state.config.TTS_OPENAI_API_BASE_URL,
             "OPENAI_API_KEY": app.state.config.TTS_OPENAI_API_KEY,
+            "API_KEY": app.state.config.TTS_API_KEY,
             "ENGINE": app.state.config.TTS_ENGINE,
             "MODEL": app.state.config.TTS_MODEL,
             "VOICE": app.state.config.TTS_VOICE,
@@ -156,6 +161,7 @@ async def update_audio_config(
 ):
     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_API_KEY = form_data.tts.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
@@ -169,6 +175,7 @@ async def update_audio_config(
         "tts": {
             "OPENAI_API_BASE_URL": app.state.config.TTS_OPENAI_API_BASE_URL,
             "OPENAI_API_KEY": app.state.config.TTS_OPENAI_API_KEY,
+            "API_KEY": app.state.config.TTS_API_KEY,
             "ENGINE": app.state.config.TTS_ENGINE,
             "MODEL": app.state.config.TTS_MODEL,
             "VOICE": app.state.config.TTS_VOICE,
@@ -194,55 +201,111 @@ async def speech(request: Request, user=Depends(get_verified_user)):
     if file_path.is_file():
         return FileResponse(file_path)
 
-    headers = {}
-    headers["Authorization"] = f"Bearer {app.state.config.TTS_OPENAI_API_KEY}"
-    headers["Content-Type"] = "application/json"
+    if app.state.config.TTS_ENGINE == "openai":
+        headers = {}
+        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
+        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.TTS_OPENAI_API_BASE_URL}/audio/speech",
-            data=body,
-            headers=headers,
-            stream=True,
-        )
+        r = None
+        try:
+            r = requests.post(
+                url=f"{app.state.config.TTS_OPENAI_API_BASE_URL}/audio/speech",
+                data=body,
+                headers=headers,
+                stream=True,
+            )
 
-        r.raise_for_status()
+            r.raise_for_status()
 
-        # Save the streaming content to a file
-        with open(file_path, "wb") as f:
-            for chunk in r.iter_content(chunk_size=8192):
-                f.write(chunk)
+            # Save the streaming content to a file
+            with open(file_path, "wb") as f:
+                for chunk in r.iter_content(chunk_size=8192):
+                    f.write(chunk)
 
-        with open(file_body_path, "w") as f:
-            json.dump(json.loads(body.decode("utf-8")), f)
+            with open(file_body_path, "w") as f:
+                json.dump(json.loads(body.decode("utf-8")), f)
 
-        # Return the saved file
-        return FileResponse(file_path)
+            # Return the saved file
+            return FileResponse(file_path)
 
-    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}"
+        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 Exception:
+                    error_detail = f"External: {e}"
 
-        raise HTTPException(
-            status_code=r.status_code if r != None else 500,
-            detail=error_detail,
-        )
+            raise HTTPException(
+                status_code=r.status_code if r != None else 500,
+                detail=error_detail,
+            )
+
+    elif app.state.config.TTS_ENGINE == "elevenlabs":
+        payload = None
+        try:
+            payload = json.loads(body.decode("utf-8"))
+        except Exception as e:
+            log.exception(e)
+            raise HTTPException(status_code=400, detail="Invalid JSON payload")
+
+        voice_id = payload.get("voice", "")
+        url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}"
+
+        headers = {
+            "Accept": "audio/mpeg",
+            "Content-Type": "application/json",
+            "xi-api-key": app.state.config.TTS_API_KEY,
+        }
+
+        data = {
+            "text": payload["input"],
+            "model_id": app.state.config.TTS_MODEL,
+            "voice_settings": {"stability": 0.5, "similarity_boost": 0.5},
+        }
+
+        try:
+            r = requests.post(url, json=data, headers=headers)
+
+            r.raise_for_status()
+
+            # Save the streaming content to a file
+            with open(file_path, "wb") as f:
+                for chunk in r.iter_content(chunk_size=8192):
+                    f.write(chunk)
+
+            with open(file_body_path, "w") as f:
+                json.dump(json.loads(body.decode("utf-8")), f)
+
+            # Return the saved file
+            return FileResponse(file_path)
+
+        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 Exception:
+                    error_detail = f"External: {e}"
+
+            raise HTTPException(
+                status_code=r.status_code if r != None else 500,
+                detail=error_detail,
+            )
 
 
 @app.post("/transcriptions")
@@ -290,7 +353,7 @@ def transcribe(
 
             try:
                 model = WhisperModel(**whisper_kwargs)
-            except:
+            except Exception:
                 log.warning(
                     "WhisperModel initialization failed, attempting download with local_files_only=False"
                 )
@@ -358,7 +421,7 @@ def transcribe(
                         res = r.json()
                         if "error" in res:
                             error_detail = f"External: {res['error']['message']}"
-                    except:
+                    except Exception:
                         error_detail = f"External: {e}"
 
                 raise HTTPException(
@@ -373,3 +436,69 @@ def transcribe(
             status_code=status.HTTP_400_BAD_REQUEST,
             detail=ERROR_MESSAGES.DEFAULT(e),
         )
+
+
+def get_available_models() -> list[dict]:
+    if app.state.config.TTS_ENGINE == "openai":
+        return [{"id": "tts-1"}, {"id": "tts-1-hd"}]
+    elif app.state.config.TTS_ENGINE == "elevenlabs":
+        headers = {
+            "xi-api-key": app.state.config.TTS_API_KEY,
+            "Content-Type": "application/json",
+        }
+
+        try:
+            response = requests.get(
+                "https://api.elevenlabs.io/v1/models", headers=headers
+            )
+            response.raise_for_status()
+            models = response.json()
+            return [
+                {"name": model["name"], "id": model["model_id"]} for model in models
+            ]
+        except requests.RequestException as e:
+            log.error(f"Error fetching voices: {str(e)}")
+    return []
+
+
+@app.get("/models")
+async def get_models(user=Depends(get_verified_user)):
+    return {"models": get_available_models()}
+
+
+def get_available_voices() -> list[dict]:
+    if app.state.config.TTS_ENGINE == "openai":
+        return [
+            {"name": "alloy", "id": "alloy"},
+            {"name": "echo", "id": "echo"},
+            {"name": "fable", "id": "fable"},
+            {"name": "onyx", "id": "onyx"},
+            {"name": "nova", "id": "nova"},
+            {"name": "shimmer", "id": "shimmer"},
+        ]
+    elif app.state.config.TTS_ENGINE == "elevenlabs":
+        headers = {
+            "xi-api-key": app.state.config.TTS_API_KEY,
+            "Content-Type": "application/json",
+        }
+
+        try:
+            response = requests.get(
+                "https://api.elevenlabs.io/v1/voices", headers=headers
+            )
+            response.raise_for_status()
+            voices_data = response.json()
+
+            voices = []
+            for voice in voices_data.get("voices", []):
+                voices.append({"name": voice["name"], "id": voice["voice_id"]})
+            return voices
+        except requests.RequestException as e:
+            log.error(f"Error fetching voices: {str(e)}")
+
+    return []
+
+
+@app.get("/voices")
+async def get_voices(user=Depends(get_verified_user)):
+    return {"voices": get_available_voices()}

backend/apps/images/main.py

@@ -42,6 +42,9 @@ from config import (
     COMFYUI_SAMPLER,
     COMFYUI_SCHEDULER,
     COMFYUI_SD3,
+    COMFYUI_FLUX,
+    COMFYUI_FLUX_WEIGHT_DTYPE,
+    COMFYUI_FLUX_FP8_CLIP,
     IMAGES_OPENAI_API_BASE_URL,
     IMAGES_OPENAI_API_KEY,
     IMAGE_GENERATION_MODEL,
@@ -85,10 +88,13 @@ app.state.config.COMFYUI_CFG_SCALE = COMFYUI_CFG_SCALE
 app.state.config.COMFYUI_SAMPLER = COMFYUI_SAMPLER
 app.state.config.COMFYUI_SCHEDULER = COMFYUI_SCHEDULER
 app.state.config.COMFYUI_SD3 = COMFYUI_SD3
+app.state.config.COMFYUI_FLUX = COMFYUI_FLUX
+app.state.config.COMFYUI_FLUX_WEIGHT_DTYPE = COMFYUI_FLUX_WEIGHT_DTYPE
+app.state.config.COMFYUI_FLUX_FP8_CLIP = COMFYUI_FLUX_FP8_CLIP
 
 
 def get_automatic1111_api_auth():
-    if app.state.config.AUTOMATIC1111_API_AUTH == None:
+    if app.state.config.AUTOMATIC1111_API_AUTH is None:
         return ""
     else:
         auth1111_byte_string = app.state.config.AUTOMATIC1111_API_AUTH.encode("utf-8")
@@ -139,28 +145,30 @@ async def get_engine_url(user=Depends(get_admin_user)):
 async def update_engine_url(
     form_data: EngineUrlUpdateForm, user=Depends(get_admin_user)
 ):
-    if form_data.AUTOMATIC1111_BASE_URL == None:
+    if form_data.AUTOMATIC1111_BASE_URL is None:
         app.state.config.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL
     else:
         url = form_data.AUTOMATIC1111_BASE_URL.strip("/")
         try:
             r = requests.head(url)
+            r.raise_for_status()
             app.state.config.AUTOMATIC1111_BASE_URL = url
         except Exception as e:
-            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
+            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL)
 
-    if form_data.COMFYUI_BASE_URL == None:
+    if form_data.COMFYUI_BASE_URL is None:
         app.state.config.COMFYUI_BASE_URL = COMFYUI_BASE_URL
     else:
         url = form_data.COMFYUI_BASE_URL.strip("/")
 
         try:
             r = requests.head(url)
+            r.raise_for_status()
             app.state.config.COMFYUI_BASE_URL = url
         except Exception as e:
-            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e))
+            raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL)
 
-    if form_data.AUTOMATIC1111_API_AUTH == None:
+    if form_data.AUTOMATIC1111_API_AUTH is None:
         app.state.config.AUTOMATIC1111_API_AUTH = AUTOMATIC1111_API_AUTH
     else:
         app.state.config.AUTOMATIC1111_API_AUTH = form_data.AUTOMATIC1111_API_AUTH
@@ -497,9 +505,18 @@ async def image_generations(
             if app.state.config.COMFYUI_SD3 is not None:
                 data["sd3"] = app.state.config.COMFYUI_SD3
 
+            if app.state.config.COMFYUI_FLUX is not None:
+                data["flux"] = app.state.config.COMFYUI_FLUX
+
+            if app.state.config.COMFYUI_FLUX_WEIGHT_DTYPE is not None:
+                data["flux_weight_dtype"] = app.state.config.COMFYUI_FLUX_WEIGHT_DTYPE
+
+            if app.state.config.COMFYUI_FLUX_FP8_CLIP is not None:
+                data["flux_fp8_clip"] = app.state.config.COMFYUI_FLUX_FP8_CLIP
+
             data = ImageGenerationPayload(**data)
 
-            res = comfyui_generate_image(
+            res = await comfyui_generate_image(
                 app.state.config.MODEL,
                 data,
                 user.id,

backend/apps/images/utils/comfyui.py

@@ -1,5 +1,5 @@
+import asyncio
 import websocket  # NOTE: websocket-client (https://github.com/websocket-client/websocket-client)
-import uuid
 import json
 import urllib.request
 import urllib.parse
@@ -125,6 +125,135 @@ COMFYUI_DEFAULT_PROMPT = """
 }
 """
 
+FLUX_DEFAULT_PROMPT = """
+{
+    "5": {
+        "inputs": {
+            "width": 1024,
+            "height": 1024,
+            "batch_size": 1
+        },
+        "class_type": "EmptyLatentImage"
+    },
+    "6": {
+        "inputs": {
+            "text": "Input Text Here",
+            "clip": [
+                "11",
+                0
+            ]
+        },
+        "class_type": "CLIPTextEncode"
+    },
+    "8": {
+        "inputs": {
+            "samples": [
+                "13",
+                0
+            ],
+            "vae": [
+                "10",
+                0
+            ]
+        },
+        "class_type": "VAEDecode"
+    },
+    "9": {
+        "inputs": {
+            "filename_prefix": "ComfyUI",
+            "images": [
+                "8",
+                0
+            ]
+        },
+        "class_type": "SaveImage"
+    },
+    "10": {
+        "inputs": {
+            "vae_name": "ae.safetensors"
+        },
+        "class_type": "VAELoader"
+    },
+    "11": {
+        "inputs": {
+            "clip_name1": "clip_l.safetensors",
+            "clip_name2": "t5xxl_fp16.safetensors",
+            "type": "flux"
+        },
+        "class_type": "DualCLIPLoader"
+    },
+    "12": {
+        "inputs": {
+            "unet_name": "flux1-dev.safetensors",
+            "weight_dtype": "default"
+        },
+        "class_type": "UNETLoader"
+    },
+    "13": {
+        "inputs": {
+            "noise": [
+                "25",
+                0
+            ],
+            "guider": [
+                "22",
+                0
+            ],
+            "sampler": [
+                "16",
+                0
+            ],
+            "sigmas": [
+                "17",
+                0
+            ],
+            "latent_image": [
+                "5",
+                0
+            ]
+        },
+        "class_type": "SamplerCustomAdvanced"
+    },
+    "16": {
+        "inputs": {
+            "sampler_name": "euler"
+        },
+        "class_type": "KSamplerSelect"
+    },
+    "17": {
+        "inputs": {
+            "scheduler": "simple",
+            "steps": 20,
+            "denoise": 1,
+            "model": [
+                "12",
+                0
+            ]
+        },
+        "class_type": "BasicScheduler"
+    },
+    "22": {
+        "inputs": {
+            "model": [
+                "12",
+                0
+            ],
+            "conditioning": [
+                "6",
+                0
+            ]
+        },
+        "class_type": "BasicGuider"
+    },
+    "25": {
+        "inputs": {
+            "noise_seed": 778937779713005
+        },
+        "class_type": "RandomNoise"
+    }
+}
+"""
+
 
 def queue_prompt(prompt, client_id, base_url):
     log.info("queue_prompt")
@@ -194,9 +323,12 @@ class ImageGenerationPayload(BaseModel):
     sampler: Optional[str] = None
     scheduler: Optional[str] = None
     sd3: Optional[bool] = None
+    flux: Optional[bool] = None
+    flux_weight_dtype: Optional[str] = None
+    flux_fp8_clip: Optional[bool] = None
 
 
-def comfyui_generate_image(
+async def comfyui_generate_image(
     model: str, payload: ImageGenerationPayload, client_id, base_url
 ):
     ws_url = base_url.replace("http://", "ws://").replace("https://", "wss://")
@@ -215,21 +347,46 @@ def comfyui_generate_image(
     if payload.sd3:
         comfyui_prompt["5"]["class_type"] = "EmptySD3LatentImage"
 
+    if payload.steps:
+        comfyui_prompt["3"]["inputs"]["steps"] = payload.steps
+
     comfyui_prompt["4"]["inputs"]["ckpt_name"] = model
+    comfyui_prompt["7"]["inputs"]["text"] = payload.negative_prompt
+    comfyui_prompt["3"]["inputs"]["seed"] = (
+        payload.seed if payload.seed else random.randint(0, 18446744073709551614)
+    )
+
+    # as Flux uses a completely different workflow, we must treat it specially
+    if payload.flux:
+        comfyui_prompt = json.loads(FLUX_DEFAULT_PROMPT)
+        comfyui_prompt["12"]["inputs"]["unet_name"] = model
+        comfyui_prompt["25"]["inputs"]["noise_seed"] = (
+            payload.seed if payload.seed else random.randint(0, 18446744073709551614)
+        )
+
+        if payload.sampler:
+            comfyui_prompt["16"]["inputs"]["sampler_name"] = payload.sampler
+
+        if payload.steps:
+            comfyui_prompt["17"]["inputs"]["steps"] = payload.steps
+
+        if payload.scheduler:
+            comfyui_prompt["17"]["inputs"]["scheduler"] = payload.scheduler
+
+        if payload.flux_weight_dtype:
+            comfyui_prompt["12"]["inputs"]["weight_dtype"] = payload.flux_weight_dtype
+
+        if payload.flux_fp8_clip:
+            comfyui_prompt["11"]["inputs"][
+                "clip_name2"
+            ] = "t5xxl_fp8_e4m3fn.safetensors"
+
     comfyui_prompt["5"]["inputs"]["batch_size"] = payload.n
     comfyui_prompt["5"]["inputs"]["width"] = payload.width
     comfyui_prompt["5"]["inputs"]["height"] = payload.height
 
     # set the text prompt for our positive CLIPTextEncode
     comfyui_prompt["6"]["inputs"]["text"] = payload.prompt
-    comfyui_prompt["7"]["inputs"]["text"] = payload.negative_prompt
-
-    if payload.steps:
-        comfyui_prompt["3"]["inputs"]["steps"] = payload.steps
-
-    comfyui_prompt["3"]["inputs"]["seed"] = (
-        payload.seed if payload.seed else random.randint(0, 18446744073709551614)
-    )
 
     try:
         ws = websocket.WebSocket()
@@ -240,7 +397,9 @@ def comfyui_generate_image(
         return None
 
     try:
-        images = get_images(ws, comfyui_prompt, client_id, base_url)
+        images = await asyncio.to_thread(
+            get_images, ws, comfyui_prompt, client_id, base_url
+        )
     except Exception as e:
         log.exception(f"Error while receiving images: {e}")
         images = None

backend/apps/ollama/main.py

@@ -1,47 +1,36 @@
 from fastapi import (
     FastAPI,
     Request,
-    Response,
     HTTPException,
     Depends,
-    status,
     UploadFile,
     File,
-    BackgroundTasks,
 )
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse
-from fastapi.concurrency import run_in_threadpool
 
 from pydantic import BaseModel, ConfigDict
 
 import os
 import re
-import copy
 import random
 import requests
 import json
-import uuid
 import aiohttp
 import asyncio
 import logging
 import time
 from urllib.parse import urlparse
-from typing import Optional, List, Union
+from typing import Optional, Union
 
 from starlette.background import BackgroundTask
 
 from apps.webui.models.models import Models
-from apps.webui.models.users import Users
 from constants import ERROR_MESSAGES
 from utils.utils import (
-    decode_token,
-    get_current_user,
     get_verified_user,
     get_admin_user,
 )
-from utils.task import prompt_template
-
 
 from config import (
     SRC_LOG_LEVELS,
@@ -53,7 +42,12 @@ from config import (
     UPLOAD_DIR,
     AppConfig,
 )
-from utils.misc import calculate_sha256, add_or_update_system_message
+from utils.misc import (
+    calculate_sha256,
+    apply_model_params_to_body_ollama,
+    apply_model_params_to_body_openai,
+    apply_model_system_prompt_to_body,
+)
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["OLLAMA"])
@@ -120,7 +114,7 @@ async def get_ollama_api_urls(user=Depends(get_admin_user)):
 
 
 class UrlUpdateForm(BaseModel):
-    urls: List[str]
+    urls: list[str]
 
 
 @app.post("/urls/update")
@@ -183,7 +177,7 @@ async def post_streaming_url(url: str, payload: str, stream: bool = True):
                 res = await r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except:
+            except Exception:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -238,7 +232,7 @@ async def get_all_models():
 async def get_ollama_tags(
     url_idx: Optional[int] = None, user=Depends(get_verified_user)
 ):
-    if url_idx == None:
+    if url_idx is None:
         models = await get_all_models()
 
         if app.state.config.ENABLE_MODEL_FILTER:
@@ -269,7 +263,7 @@ async def get_ollama_tags(
                     res = r.json()
                     if "error" in res:
                         error_detail = f"Ollama: {res['error']}"
-                except:
+                except Exception:
                     error_detail = f"Ollama: {e}"
 
             raise HTTPException(
@@ -282,8 +276,7 @@ async def get_ollama_tags(
 @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 is None:
             # returns lowest version
             tasks = [
                 fetch_url(f"{url}/api/version")
@@ -323,7 +316,7 @@ async def get_ollama_versions(url_idx: Optional[int] = None):
                         res = r.json()
                         if "error" in res:
                             error_detail = f"Ollama: {res['error']}"
-                    except:
+                    except Exception:
                         error_detail = f"Ollama: {e}"
 
                 raise HTTPException(
@@ -346,8 +339,6 @@ async def pull_model(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
-    r = None
-
     # Admin should be able to pull models from any source
     payload = {**form_data.model_dump(exclude_none=True), "insecure": True}
 
@@ -367,7 +358,7 @@ async def push_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-    if url_idx == None:
+    if url_idx is None:
         if form_data.name in app.state.MODELS:
             url_idx = app.state.MODELS[form_data.name]["urls"][0]
         else:
@@ -417,7 +408,7 @@ async def copy_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-    if url_idx == None:
+    if url_idx is None:
         if form_data.source in app.state.MODELS:
             url_idx = app.state.MODELS[form_data.source]["urls"][0]
         else:
@@ -428,13 +419,13 @@ async def copy_model(
 
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
+    r = requests.request(
+        method="POST",
+        url=f"{url}/api/copy",
+        data=form_data.model_dump_json(exclude_none=True).encode(),
+    )
 
     try:
-        r = requests.request(
-            method="POST",
-            url=f"{url}/api/copy",
-            data=form_data.model_dump_json(exclude_none=True).encode(),
-        )
         r.raise_for_status()
 
         log.debug(f"r.text: {r.text}")
@@ -448,7 +439,7 @@ async def copy_model(
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except:
+            except Exception:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -464,7 +455,7 @@ async def delete_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-    if url_idx == None:
+    if url_idx is None:
         if form_data.name in app.state.MODELS:
             url_idx = app.state.MODELS[form_data.name]["urls"][0]
         else:
@@ -476,12 +467,12 @@ async def delete_model(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
+    r = requests.request(
+        method="DELETE",
+        url=f"{url}/api/delete",
+        data=form_data.model_dump_json(exclude_none=True).encode(),
+    )
     try:
-        r = requests.request(
-            method="DELETE",
-            url=f"{url}/api/delete",
-            data=form_data.model_dump_json(exclude_none=True).encode(),
-        )
         r.raise_for_status()
 
         log.debug(f"r.text: {r.text}")
@@ -495,7 +486,7 @@ async def delete_model(
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except:
+            except Exception:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -516,12 +507,12 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_verified_us
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
+    r = requests.request(
+        method="POST",
+        url=f"{url}/api/show",
+        data=form_data.model_dump_json(exclude_none=True).encode(),
+    )
     try:
-        r = requests.request(
-            method="POST",
-            url=f"{url}/api/show",
-            data=form_data.model_dump_json(exclude_none=True).encode(),
-        )
         r.raise_for_status()
 
         return r.json()
@@ -533,7 +524,7 @@ async def show_model_info(form_data: ModelNameForm, user=Depends(get_verified_us
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except:
+            except Exception:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -556,7 +547,7 @@ async def generate_embeddings(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    if url_idx == None:
+    if url_idx is None:
         model = form_data.model
 
         if ":" not in model:
@@ -573,12 +564,12 @@ async def generate_embeddings(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
+    r = requests.request(
+        method="POST",
+        url=f"{url}/api/embeddings",
+        data=form_data.model_dump_json(exclude_none=True).encode(),
+    )
     try:
-        r = requests.request(
-            method="POST",
-            url=f"{url}/api/embeddings",
-            data=form_data.model_dump_json(exclude_none=True).encode(),
-        )
         r.raise_for_status()
 
         return r.json()
@@ -590,7 +581,7 @@ async def generate_embeddings(
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except:
+            except Exception:
                 error_detail = f"Ollama: {e}"
 
         raise HTTPException(
@@ -603,10 +594,9 @@ def generate_ollama_embeddings(
     form_data: GenerateEmbeddingsForm,
     url_idx: Optional[int] = None,
 ):
-
     log.info(f"generate_ollama_embeddings {form_data}")
 
-    if url_idx == None:
+    if url_idx is None:
         model = form_data.model
 
         if ":" not in model:
@@ -623,12 +613,12 @@ def generate_ollama_embeddings(
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
     log.info(f"url: {url}")
 
+    r = requests.request(
+        method="POST",
+        url=f"{url}/api/embeddings",
+        data=form_data.model_dump_json(exclude_none=True).encode(),
+    )
     try:
-        r = requests.request(
-            method="POST",
-            url=f"{url}/api/embeddings",
-            data=form_data.model_dump_json(exclude_none=True).encode(),
-        )
         r.raise_for_status()
 
         data = r.json()
@@ -638,7 +628,7 @@ def generate_ollama_embeddings(
         if "embedding" in data:
             return data["embedding"]
         else:
-            raise "Something went wrong :/"
+            raise Exception("Something went wrong :/")
     except Exception as e:
         log.exception(e)
         error_detail = "Open WebUI: Server Connection Error"
@@ -647,16 +637,16 @@ def generate_ollama_embeddings(
                 res = r.json()
                 if "error" in res:
                     error_detail = f"Ollama: {res['error']}"
-            except:
+            except Exception:
                 error_detail = f"Ollama: {e}"
 
-        raise error_detail
+        raise Exception(error_detail)
 
 
 class GenerateCompletionForm(BaseModel):
     model: str
     prompt: str
-    images: Optional[List[str]] = None
+    images: Optional[list[str]] = None
     format: Optional[str] = None
     options: Optional[dict] = None
     system: Optional[str] = None
@@ -674,8 +664,7 @@ async def generate_completion(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-
-    if url_idx == None:
+    if url_idx is None:
         model = form_data.model
 
         if ":" not in model:
@@ -700,12 +689,12 @@ async def generate_completion(
 class ChatMessage(BaseModel):
     role: str
     content: str
-    images: Optional[List[str]] = None
+    images: Optional[list[str]] = None
 
 
 class GenerateChatCompletionForm(BaseModel):
     model: str
-    messages: List[ChatMessage]
+    messages: list[ChatMessage]
     format: Optional[str] = None
     options: Optional[dict] = None
     template: Optional[str] = None
@@ -713,6 +702,18 @@ class GenerateChatCompletionForm(BaseModel):
     keep_alive: Optional[Union[int, str]] = None
 
 
+def get_ollama_url(url_idx: Optional[int], model: str):
+    if url_idx is None:
+        if model not in app.state.MODELS:
+            raise HTTPException(
+                status_code=400,
+                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(model),
+            )
+        url_idx = random.choice(app.state.MODELS[model]["urls"])
+    url = app.state.config.OLLAMA_BASE_URLS[url_idx]
+    return url
+
+
 @app.post("/api/chat")
 @app.post("/api/chat/{url_idx}")
 async def generate_chat_completion(
@@ -720,12 +721,7 @@ async def generate_chat_completion(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-
-    log.debug(
-        "form_data.model_dump_json(exclude_none=True).encode(): {0} ".format(
-            form_data.model_dump_json(exclude_none=True).encode()
-        )
-    )
+    log.debug(f"{form_data.model_dump_json(exclude_none=True).encode()}=")
 
     payload = {
         **form_data.model_dump(exclude_none=True, exclude=["metadata"]),
@@ -740,179 +736,21 @@ async def generate_chat_completion(
         if model_info.base_model_id:
             payload["model"] = model_info.base_model_id
 
-        model_info.params = model_info.params.model_dump()
+        params = model_info.params.model_dump()
 
-        if model_info.params:
+        if params:
             if payload.get("options") is None:
                 payload["options"] = {}
 
-            if (
-                model_info.params.get("mirostat", None)
-                and payload["options"].get("mirostat") is None
-            ):
-                payload["options"]["mirostat"] = model_info.params.get("mirostat", None)
-
-            if (
-                model_info.params.get("mirostat_eta", None)
-                and payload["options"].get("mirostat_eta") is None
-            ):
-                payload["options"]["mirostat_eta"] = model_info.params.get(
-                    "mirostat_eta", None
-                )
-
-            if (
-                model_info.params.get("mirostat_tau", None)
-                and payload["options"].get("mirostat_tau") is None
-            ):
-                payload["options"]["mirostat_tau"] = model_info.params.get(
-                    "mirostat_tau", None
-                )
-
-            if (
-                model_info.params.get("num_ctx", None)
-                and payload["options"].get("num_ctx") is None
-            ):
-                payload["options"]["num_ctx"] = model_info.params.get("num_ctx", None)
-
-            if (
-                model_info.params.get("num_batch", None)
-                and payload["options"].get("num_batch") is None
-            ):
-                payload["options"]["num_batch"] = model_info.params.get(
-                    "num_batch", None
-                )
-
-            if (
-                model_info.params.get("num_keep", None)
-                and payload["options"].get("num_keep") is None
-            ):
-                payload["options"]["num_keep"] = model_info.params.get("num_keep", None)
-
-            if (
-                model_info.params.get("repeat_last_n", None)
-                and payload["options"].get("repeat_last_n") is None
-            ):
-                payload["options"]["repeat_last_n"] = model_info.params.get(
-                    "repeat_last_n", None
-                )
-
-            if (
-                model_info.params.get("frequency_penalty", None)
-                and payload["options"].get("frequency_penalty") is None
-            ):
-                payload["options"]["repeat_penalty"] = model_info.params.get(
-                    "frequency_penalty", None
-                )
-
-            if (
-                model_info.params.get("temperature", None)
-                and payload["options"].get("temperature") is None
-            ):
-                payload["options"]["temperature"] = model_info.params.get(
-                    "temperature", None
-                )
-
-            if (
-                model_info.params.get("seed", None)
-                and payload["options"].get("seed") is None
-            ):
-                payload["options"]["seed"] = model_info.params.get("seed", None)
-
-            if (
-                model_info.params.get("stop", None)
-                and payload["options"].get("stop") is None
-            ):
-                payload["options"]["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("tfs_z", None)
-                and payload["options"].get("tfs_z") is None
-            ):
-                payload["options"]["tfs_z"] = model_info.params.get("tfs_z", None)
-
-            if (
-                model_info.params.get("max_tokens", None)
-                and payload["options"].get("max_tokens") is None
-            ):
-                payload["options"]["num_predict"] = model_info.params.get(
-                    "max_tokens", None
-                )
-
-            if (
-                model_info.params.get("top_k", None)
-                and payload["options"].get("top_k") is None
-            ):
-                payload["options"]["top_k"] = model_info.params.get("top_k", None)
-
-            if (
-                model_info.params.get("top_p", None)
-                and payload["options"].get("top_p") is None
-            ):
-                payload["options"]["top_p"] = model_info.params.get("top_p", None)
-
-            if (
-                model_info.params.get("use_mmap", None)
-                and payload["options"].get("use_mmap") is None
-            ):
-                payload["options"]["use_mmap"] = model_info.params.get("use_mmap", None)
-
-            if (
-                model_info.params.get("use_mlock", None)
-                and payload["options"].get("use_mlock") is None
-            ):
-                payload["options"]["use_mlock"] = model_info.params.get(
-                    "use_mlock", None
-                )
-
-            if (
-                model_info.params.get("num_thread", None)
-                and payload["options"].get("num_thread") is None
-            ):
-                payload["options"]["num_thread"] = model_info.params.get(
-                    "num_thread", None
-                )
-
-        system = model_info.params.get("system", None)
-        if system:
-            system = prompt_template(
-                system,
-                **(
-                    {
-                        "user_name": user.name,
-                        "user_location": (
-                            user.info.get("location") if user.info else None
-                        ),
-                    }
-                    if user
-                    else {}
-                ),
+            payload["options"] = apply_model_params_to_body_ollama(
+                params, payload["options"]
             )
+            payload = apply_model_system_prompt_to_body(params, payload, user)
 
-            if payload.get("messages"):
-                payload["messages"] = add_or_update_system_message(
-                    system, payload["messages"]
-                )
+    if ":" not in payload["model"]:
+        payload["model"] = f"{payload['model']}:latest"
 
-    if url_idx == None:
-        if ":" not in payload["model"]:
-            payload["model"] = f"{payload['model']}:latest"
-
-        if payload["model"] in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[payload["model"]]["urls"])
-        else:
-            raise HTTPException(
-                status_code=400,
-                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
-            )
-
-    url = app.state.config.OLLAMA_BASE_URLS[url_idx]
+    url = get_ollama_url(url_idx, payload["model"])
     log.info(f"url: {url}")
     log.debug(payload)
 
@@ -934,7 +772,7 @@ class OpenAIChatMessage(BaseModel):
 
 class OpenAIChatCompletionForm(BaseModel):
     model: str
-    messages: List[OpenAIChatMessage]
+    messages: list[OpenAIChatMessage]
 
     model_config = ConfigDict(extra="allow")
 
@@ -946,83 +784,28 @@ async def generate_openai_chat_completion(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    form_data = OpenAIChatCompletionForm(**form_data)
-    payload = {**form_data.model_dump(exclude_none=True, exclude=["metadata"])}
-
+    completion_form = OpenAIChatCompletionForm(**form_data)
+    payload = {**completion_form.model_dump(exclude_none=True, exclude=["metadata"])}
     if "metadata" in payload:
         del payload["metadata"]
 
-    model_id = form_data.model
+    model_id = completion_form.model
     model_info = Models.get_model_by_id(model_id)
 
     if model_info:
         if model_info.base_model_id:
             payload["model"] = model_info.base_model_id
 
-        model_info.params = model_info.params.model_dump()
+        params = model_info.params.model_dump()
 
-        if model_info.params:
-            payload["temperature"] = model_info.params.get("temperature", None)
-            payload["top_p"] = model_info.params.get("top_p", None)
-            payload["max_tokens"] = model_info.params.get("max_tokens", None)
-            payload["frequency_penalty"] = model_info.params.get(
-                "frequency_penalty", None
-            )
-            payload["seed"] = model_info.params.get("seed", 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 params:
+            payload = apply_model_params_to_body_openai(params, payload)
+            payload = apply_model_system_prompt_to_body(params, payload, user)
 
-        system = model_info.params.get("system", None)
+    if ":" not in payload["model"]:
+        payload["model"] = f"{payload['model']}:latest"
 
-        if system:
-            system = prompt_template(
-                system,
-                **(
-                    {
-                        "user_name": user.name,
-                        "user_location": (
-                            user.info.get("location") if user.info else None
-                        ),
-                    }
-                    if user
-                    else {}
-                ),
-            )
-            # 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"] = system + message["content"]
-                        break
-                else:
-                    payload["messages"].insert(
-                        0,
-                        {
-                            "role": "system",
-                            "content": system,
-                        },
-                    )
-
-    if url_idx == None:
-        if ":" not in payload["model"]:
-            payload["model"] = f"{payload['model']}:latest"
-
-        if payload["model"] in app.state.MODELS:
-            url_idx = random.choice(app.state.MODELS[payload["model"]]["urls"])
-        else:
-            raise HTTPException(
-                status_code=400,
-                detail=ERROR_MESSAGES.MODEL_NOT_FOUND(form_data.model),
-            )
-
-    url = app.state.config.OLLAMA_BASE_URLS[url_idx]
+    url = get_ollama_url(url_idx, payload["model"])
     log.info(f"url: {url}")
 
     return await post_streaming_url(
@@ -1038,7 +821,7 @@ async def get_openai_models(
     url_idx: Optional[int] = None,
     user=Depends(get_verified_user),
 ):
-    if url_idx == None:
+    if url_idx is None:
         models = await get_all_models()
 
         if app.state.config.ENABLE_MODEL_FILTER:
@@ -1093,7 +876,7 @@ async def get_openai_models(
                     res = r.json()
                     if "error" in res:
                         error_detail = f"Ollama: {res['error']}"
-                except:
+                except Exception:
                     error_detail = f"Ollama: {e}"
 
             raise HTTPException(
@@ -1119,7 +902,6 @@ def parse_huggingface_url(hf_url):
         path_components = parsed_url.path.split("/")
 
         # Extract the desired output
-        user_repo = "/".join(path_components[1:3])
         model_file = path_components[-1]
 
         return model_file
@@ -1184,7 +966,6 @@ async def download_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-
     allowed_hosts = ["https://huggingface.co/", "https://github.com/"]
 
     if not any(form_data.url.startswith(host) for host in allowed_hosts):
@@ -1193,7 +974,7 @@ async def download_model(
             detail="Invalid file_url. Only URLs from allowed hosts are permitted.",
         )
 
-    if url_idx == None:
+    if url_idx is None:
         url_idx = 0
     url = app.state.config.OLLAMA_BASE_URLS[url_idx]
 
@@ -1216,7 +997,7 @@ def upload_model(
     url_idx: Optional[int] = None,
     user=Depends(get_admin_user),
 ):
-    if url_idx == None:
+    if url_idx is None:
         url_idx = 0
     ollama_url = app.state.config.OLLAMA_BASE_URLS[url_idx]
 

backend/apps/openai/main.py

@@ -1,6 +1,6 @@
-from fastapi import FastAPI, Request, Response, HTTPException, Depends
+from fastapi import FastAPI, Request, HTTPException, Depends
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import StreamingResponse, JSONResponse, FileResponse
+from fastapi.responses import StreamingResponse, FileResponse
 
 import requests
 import aiohttp
@@ -12,16 +12,15 @@ from pydantic import BaseModel
 from starlette.background import BackgroundTask
 
 from apps.webui.models.models import Models
-from apps.webui.models.users import Users
 from constants import ERROR_MESSAGES
 from utils.utils import (
-    decode_token,
-    get_verified_user,
     get_verified_user,
     get_admin_user,
 )
-from utils.task import prompt_template
-from utils.misc import add_or_update_system_message
+from utils.misc import (
+    apply_model_params_to_body_openai,
+    apply_model_system_prompt_to_body,
+)
 
 from config import (
     SRC_LOG_LEVELS,
@@ -34,7 +33,7 @@ from config import (
     MODEL_FILTER_LIST,
     AppConfig,
 )
-from typing import List, Optional
+from typing import Optional, Literal, overload
 
 
 import hashlib
@@ -69,8 +68,6 @@ app.state.MODELS = {}
 async def check_url(request: Request, call_next):
     if len(app.state.MODELS) == 0:
         await get_all_models()
-    else:
-        pass
 
     response = await call_next(request)
     return response
@@ -92,11 +89,11 @@ async def update_config(form_data: OpenAIConfigForm, user=Depends(get_admin_user
 
 
 class UrlsUpdateForm(BaseModel):
-    urls: List[str]
+    urls: list[str]
 
 
 class KeysUpdateForm(BaseModel):
-    keys: List[str]
+    keys: list[str]
 
 
 @app.get("/urls")
@@ -175,7 +172,7 @@ async def speech(request: Request, user=Depends(get_verified_user)):
                     res = r.json()
                     if "error" in res:
                         error_detail = f"External: {res['error']}"
-                except:
+                except Exception:
                     error_detail = f"External: {e}"
 
             raise HTTPException(
@@ -234,64 +231,68 @@ def merge_models_lists(model_lists):
     return merged_list
 
 
-async def get_all_models(raw: bool = False):
+def is_openai_api_disabled():
+    api_keys = app.state.config.OPENAI_API_KEYS
+    no_keys = len(api_keys) == 1 and api_keys[0] == ""
+    return no_keys or not app.state.config.ENABLE_OPENAI_API
+
+
+async def get_all_models_raw() -> list:
+    if is_openai_api_disabled():
+        return []
+
+    # Check if API KEYS length is same than API URLS length
+    num_urls = len(app.state.config.OPENAI_API_BASE_URLS)
+    num_keys = len(app.state.config.OPENAI_API_KEYS)
+
+    if num_keys != num_urls:
+        # if there are more keys than urls, remove the extra keys
+        if num_keys > num_urls:
+            new_keys = app.state.config.OPENAI_API_KEYS[:num_urls]
+            app.state.config.OPENAI_API_KEYS = new_keys
+        # if there are more urls than keys, add empty keys
+        else:
+            app.state.config.OPENAI_API_KEYS += [""] * (num_urls - num_keys)
+
+    tasks = [
+        fetch_url(f"{url}/models", app.state.config.OPENAI_API_KEYS[idx])
+        for idx, url in enumerate(app.state.config.OPENAI_API_BASE_URLS)
+    ]
+
+    responses = await asyncio.gather(*tasks)
+    log.debug(f"get_all_models:responses() {responses}")
+
+    return responses
+
+
+@overload
+async def get_all_models(raw: Literal[True]) -> list: ...
+
+
+@overload
+async def get_all_models(raw: Literal[False] = False) -> dict[str, list]: ...
+
+
+async def get_all_models(raw=False) -> dict[str, list] | list:
     log.info("get_all_models()")
+    if is_openai_api_disabled():
+        return [] if raw else {"data": []}
 
-    if (
-        len(app.state.config.OPENAI_API_KEYS) == 1
-        and app.state.config.OPENAI_API_KEYS[0] == ""
-    ) or not app.state.config.ENABLE_OPENAI_API:
-        models = {"data": []}
-    else:
-        # Check if API KEYS length is same than API URLS length
-        if len(app.state.config.OPENAI_API_KEYS) != len(
-            app.state.config.OPENAI_API_BASE_URLS
-        ):
-            # if there are more keys than urls, remove the extra keys
-            if len(app.state.config.OPENAI_API_KEYS) > len(
-                app.state.config.OPENAI_API_BASE_URLS
-            ):
-                app.state.config.OPENAI_API_KEYS = app.state.config.OPENAI_API_KEYS[
-                    : len(app.state.config.OPENAI_API_BASE_URLS)
-                ]
-            # if there are more urls than keys, add empty keys
-            else:
-                app.state.config.OPENAI_API_KEYS += [
-                    ""
-                    for _ in range(
-                        len(app.state.config.OPENAI_API_BASE_URLS)
-                        - len(app.state.config.OPENAI_API_KEYS)
-                    )
-                ]
+    responses = await get_all_models_raw()
+    if raw:
+        return responses
 
-        tasks = [
-            fetch_url(f"{url}/models", app.state.config.OPENAI_API_KEYS[idx])
-            for idx, url in enumerate(app.state.config.OPENAI_API_BASE_URLS)
-        ]
+    def extract_data(response):
+        if response and "data" in response:
+            return response["data"]
+        if isinstance(response, list):
+            return response
+        return None
 
-        responses = await asyncio.gather(*tasks)
-        log.debug(f"get_all_models:responses() {responses}")
+    models = {"data": merge_models_lists(map(extract_data, responses))}
 
-        if raw:
-            return responses
-
-        models = {
-            "data": merge_models_lists(
-                list(
-                    map(
-                        lambda response: (
-                            response["data"]
-                            if (response and "data" in response)
-                            else (response if isinstance(response, list) else None)
-                        ),
-                        responses,
-                    )
-                )
-            )
-        }
-
-        log.debug(f"models: {models}")
-        app.state.MODELS = {model["id"]: model for model in models["data"]}
+    log.debug(f"models: {models}")
+    app.state.MODELS = {model["id"]: model for model in models["data"]}
 
     return models
 
@@ -299,7 +300,7 @@ async def get_all_models(raw: bool = False):
 @app.get("/models")
 @app.get("/models/{url_idx}")
 async def get_models(url_idx: Optional[int] = None, user=Depends(get_verified_user)):
-    if url_idx == None:
+    if url_idx is None:
         models = await get_all_models()
         if app.state.config.ENABLE_MODEL_FILTER:
             if user.role == "user":
@@ -340,7 +341,7 @@ async def get_models(url_idx: Optional[int] = None, user=Depends(get_verified_us
                     res = r.json()
                     if "error" in res:
                         error_detail = f"External: {res['error']}"
-                except:
+                except Exception:
                     error_detail = f"External: {e}"
 
             raise HTTPException(
@@ -358,6 +359,7 @@ async def generate_chat_completion(
 ):
     idx = 0
     payload = {**form_data}
+
     if "metadata" in payload:
         del payload["metadata"]
 
@@ -368,67 +370,9 @@ async def generate_chat_completion(
         if model_info.base_model_id:
             payload["model"] = model_info.base_model_id
 
-        model_info.params = model_info.params.model_dump()
-
-        if model_info.params:
-            if (
-                model_info.params.get("temperature", None)
-                and payload.get("temperature") is None
-            ):
-                payload["temperature"] = float(model_info.params.get("temperature"))
-
-            if model_info.params.get("top_p", None) and payload.get("top_p") is None:
-                payload["top_p"] = int(model_info.params.get("top_p", None))
-
-            if (
-                model_info.params.get("max_tokens", None)
-                and payload.get("max_tokens") is None
-            ):
-                payload["max_tokens"] = int(model_info.params.get("max_tokens", None))
-
-            if (
-                model_info.params.get("frequency_penalty", None)
-                and payload.get("frequency_penalty") is None
-            ):
-                payload["frequency_penalty"] = int(
-                    model_info.params.get("frequency_penalty", None)
-                )
-
-            if model_info.params.get("seed", None) and payload.get("seed") is None:
-                payload["seed"] = model_info.params.get("seed", None)
-
-            if model_info.params.get("stop", None) and payload.get("stop") is 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
-                )
-
-        system = model_info.params.get("system", None)
-        if system:
-            system = prompt_template(
-                system,
-                **(
-                    {
-                        "user_name": user.name,
-                        "user_location": (
-                            user.info.get("location") if user.info else None
-                        ),
-                    }
-                    if user
-                    else {}
-                ),
-            )
-            if payload.get("messages"):
-                payload["messages"] = add_or_update_system_message(
-                    system, payload["messages"]
-                )
-
-    else:
-        pass
+        params = model_info.params.model_dump()
+        payload = apply_model_params_to_body_openai(params, payload)
+        payload = apply_model_system_prompt_to_body(params, payload, user)
 
     model = app.state.MODELS[payload.get("model")]
     idx = model["urlIdx"]
@@ -441,13 +385,6 @@ async def generate_chat_completion(
             "role": user.role,
         }
 
-    # 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)
 
@@ -459,6 +396,9 @@ async def generate_chat_completion(
     headers = {}
     headers["Authorization"] = f"Bearer {key}"
     headers["Content-Type"] = "application/json"
+    if "openrouter.ai" in app.state.config.OPENAI_API_BASE_URLS[idx]:
+        headers["HTTP-Referer"] = "https://openwebui.com/"
+        headers["X-Title"] = "Open WebUI"
 
     r = None
     session = None
@@ -500,7 +440,7 @@ async def generate_chat_completion(
                 print(res)
                 if "error" in res:
                     error_detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
-            except:
+            except Exception:
                 error_detail = f"External: {e}"
         raise HTTPException(status_code=r.status if r else 500, detail=error_detail)
     finally:
@@ -563,7 +503,7 @@ async def proxy(path: str, request: Request, user=Depends(get_verified_user)):
                 print(res)
                 if "error" in res:
                     error_detail = f"External: {res['error']['message'] if 'message' in res['error'] else res['error']}"
-            except:
+            except Exception:
                 error_detail = f"External: {e}"
         raise HTTPException(status_code=r.status if r else 500, detail=error_detail)
     finally:

backend/apps/rag/main.py

@@ -13,7 +13,7 @@ import os, shutil, logging, re
 from datetime import datetime
 
 from pathlib import Path
-from typing import List, Union, Sequence, Iterator, Any
+from typing import Union, Sequence, Iterator, Any
 
 from chromadb.utils.batch_utils import create_batches
 from langchain_core.documents import Document
@@ -376,7 +376,7 @@ async def update_reranking_config(
     try:
         app.state.config.RAG_RERANKING_MODEL = form_data.reranking_model
 
-        update_reranking_model(app.state.config.RAG_RERANKING_MODEL), True
+        update_reranking_model(app.state.config.RAG_RERANKING_MODEL, True)
 
         return {
             "status": True,
@@ -439,7 +439,7 @@ class ChunkParamUpdateForm(BaseModel):
 
 
 class YoutubeLoaderConfig(BaseModel):
-    language: List[str]
+    language: list[str]
     translation: Optional[str] = None
 
 
@@ -642,7 +642,7 @@ def query_doc_handler(
 
 
 class QueryCollectionsForm(BaseModel):
-    collection_names: List[str]
+    collection_names: list[str]
     query: str
     k: Optional[int] = None
     r: Optional[float] = None
@@ -1021,7 +1021,7 @@ class TikaLoader:
         self.file_path = file_path
         self.mime_type = mime_type
 
-    def load(self) -> List[Document]:
+    def load(self) -> list[Document]:
         with open(self.file_path, "rb") as f:
             data = f.read()
 
@@ -1099,6 +1099,13 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
         "vue",
         "svelte",
         "msg",
+        "ex",
+        "exs",
+        "erl",
+        "tsx",
+        "jsx",
+        "hs",
+        "lhs",
     ]
 
     if (
@@ -1178,7 +1185,7 @@ def store_doc(
             f.close()
 
         f = open(file_path, "rb")
-        if collection_name == None:
+        if collection_name is None:
             collection_name = calculate_sha256(f)[:63]
         f.close()
 
@@ -1231,7 +1238,7 @@ def process_doc(
         f = open(file_path, "rb")
 
         collection_name = form_data.collection_name
-        if collection_name == None:
+        if collection_name is None:
             collection_name = calculate_sha256(f)[:63]
         f.close()
 
@@ -1289,7 +1296,7 @@ def store_text(
 ):
 
     collection_name = form_data.collection_name
-    if collection_name == None:
+    if collection_name is None:
         collection_name = calculate_sha256_string(form_data.content)
 
     result = store_text_in_vector_db(
@@ -1332,7 +1339,7 @@ def scan_docs_dir(user=Depends(get_admin_user)):
                         sanitized_filename = sanitize_filename(filename)
                         doc = Documents.get_doc_by_name(sanitized_filename)
 
-                        if doc == None:
+                        if doc is None:
                             doc = Documents.insert_new_doc(
                                 user.id,
                                 DocumentForm(

backend/apps/rag/search/brave.py

@@ -1,5 +1,5 @@
 import logging
-from typing import List, Optional
+from typing import Optional
 import requests
 
 from apps.rag.search.main import SearchResult, get_filtered_results
@@ -10,7 +10,7 @@ log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_brave(
-    api_key: str, query: str, count: int, filter_list: Optional[List[str]] = None
+    api_key: str, query: str, count: int, filter_list: Optional[list[str]] = None
 ) -> list[SearchResult]:
     """Search using Brave's Search API and return the results as a list of SearchResult objects.
 

backend/apps/rag/search/duckduckgo.py

@@ -1,5 +1,5 @@
 import logging
-from typing import List, Optional
+from typing import Optional
 from apps.rag.search.main import SearchResult, get_filtered_results
 from duckduckgo_search import DDGS
 from config import SRC_LOG_LEVELS
@@ -9,7 +9,7 @@ log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_duckduckgo(
-    query: str, count: int, filter_list: Optional[List[str]] = None
+    query: str, count: int, filter_list: Optional[list[str]] = None
 ) -> list[SearchResult]:
     """
     Search using DuckDuckGo's Search API and return the results as a list of SearchResult objects.
@@ -18,7 +18,7 @@ def search_duckduckgo(
         count (int): The number of results to return
 
     Returns:
-        List[SearchResult]: A list of search results
+        list[SearchResult]: A list of search results
     """
     # Use the DDGS context manager to create a DDGS object
     with DDGS() as ddgs:

backend/apps/rag/search/google_pse.py

@@ -1,6 +1,6 @@
 import json
 import logging
-from typing import List, Optional
+from typing import Optional
 import requests
 
 from apps.rag.search.main import SearchResult, get_filtered_results
@@ -15,7 +15,7 @@ def search_google_pse(
     search_engine_id: str,
     query: str,
     count: int,
-    filter_list: Optional[List[str]] = None,
+    filter_list: Optional[list[str]] = None,
 ) -> list[SearchResult]:
     """Search using Google's Programmable Search Engine API and return the results as a list of SearchResult objects.
 

backend/apps/rag/search/jina_search.py

@@ -17,7 +17,7 @@ def search_jina(query: str, count: int) -> list[SearchResult]:
         count (int): The number of results to return
 
     Returns:
-        List[SearchResult]: A list of search results
+        list[SearchResult]: A list of search results
     """
     jina_search_endpoint = "https://s.jina.ai/"
     headers = {

backend/apps/rag/search/searxng.py

@@ -1,7 +1,7 @@
 import logging
 import requests
 
-from typing import List, Optional
+from typing import Optional
 
 from apps.rag.search.main import SearchResult, get_filtered_results
 from config import SRC_LOG_LEVELS
@@ -14,9 +14,9 @@ def search_searxng(
     query_url: str,
     query: str,
     count: int,
-    filter_list: Optional[List[str]] = None,
+    filter_list: Optional[list[str]] = None,
     **kwargs,
-) -> List[SearchResult]:
+) -> list[SearchResult]:
     """
     Search a SearXNG instance for a given query and return the results as a list of SearchResult objects.
 
@@ -31,10 +31,10 @@ def search_searxng(
         language (str): Language filter for the search results; e.g., "en-US". Defaults to an empty string.
         safesearch (int): Safe search filter for safer web results; 0 = off, 1 = moderate, 2 = strict. Defaults to 1 (moderate).
         time_range (str): Time range for filtering results by date; e.g., "2023-04-05..today" or "all-time". Defaults to ''.
-        categories: (Optional[List[str]]): Specific categories within which the search should be performed, defaulting to an empty string if not provided.
+        categories: (Optional[list[str]]): Specific categories within which the search should be performed, defaulting to an empty string if not provided.
 
     Returns:
-        List[SearchResult]: A list of SearchResults sorted by relevance score in descending order.
+        list[SearchResult]: A list of SearchResults sorted by relevance score in descending order.
 
     Raise:
         requests.exceptions.RequestException: If a request error occurs during the search process.

backend/apps/rag/search/serper.py

@@ -1,6 +1,6 @@
 import json
 import logging
-from typing import List, Optional
+from typing import Optional
 import requests
 
 from apps.rag.search.main import SearchResult, get_filtered_results
@@ -11,7 +11,7 @@ log.setLevel(SRC_LOG_LEVELS["RAG"])
 
 
 def search_serper(
-    api_key: str, query: str, count: int, filter_list: Optional[List[str]] = None
+    api_key: str, query: str, count: int, filter_list: Optional[list[str]] = None
 ) -> list[SearchResult]:
     """Search using serper.dev's API and return the results as a list of SearchResult objects.
 

backend/apps/rag/search/serply.py

@@ -1,6 +1,6 @@
 import json
 import logging
-from typing import List, Optional
+from typing import Optional
 import requests
 from urllib.parse import urlencode
 
@@ -19,7 +19,7 @@ def search_serply(
     limit: int = 10,
     device_type: str = "desktop",
     proxy_location: str = "US",
-    filter_list: Optional[List[str]] = None,
+    filter_list: Optional[list[str]] = None,
 ) -> list[SearchResult]:
     """Search using serper.dev's API and return the results as a list of SearchResult objects.
 

backend/apps/rag/search/serpstack.py

@@ -1,6 +1,6 @@
 import json
 import logging
-from typing import List, Optional
+from typing import Optional
 import requests
 
 from apps.rag.search.main import SearchResult, get_filtered_results
@@ -14,7 +14,7 @@ def search_serpstack(
     api_key: str,
     query: str,
     count: int,
-    filter_list: Optional[List[str]] = None,
+    filter_list: Optional[list[str]] = None,
     https_enabled: bool = True,
 ) -> list[SearchResult]:
     """Search using serpstack.com's and return the results as a list of SearchResult objects.

backend/apps/rag/search/tavily.py

@@ -17,7 +17,7 @@ def search_tavily(api_key: str, query: str, count: int) -> list[SearchResult]:
         query (str): The query to search for
 
     Returns:
-        List[SearchResult]: A list of search results
+        list[SearchResult]: A list of search results
     """
     url = "https://api.tavily.com/search"
     data = {"query": query, "api_key": api_key}

backend/apps/rag/utils.py

@@ -2,7 +2,7 @@ import os
 import logging
 import requests
 
-from typing import List, Union
+from typing import Union
 
 from apps.ollama.main import (
     generate_ollama_embeddings,
@@ -142,7 +142,7 @@ def merge_and_sort_query_results(query_results, k, reverse=False):
 
 
 def query_collection(
-    collection_names: List[str],
+    collection_names: list[str],
     query: str,
     embedding_function,
     k: int,
@@ -157,13 +157,13 @@ def query_collection(
                 embedding_function=embedding_function,
             )
             results.append(result)
-        except:
+        except Exception:
             pass
     return merge_and_sort_query_results(results, k=k)
 
 
 def query_collection_with_hybrid_search(
-    collection_names: List[str],
+    collection_names: list[str],
     query: str,
     embedding_function,
     k: int,
@@ -182,7 +182,7 @@ def query_collection_with_hybrid_search(
                 r=r,
             )
             results.append(result)
-        except:
+        except Exception:
             pass
     return merge_and_sort_query_results(results, k=k, reverse=True)
 
@@ -411,7 +411,7 @@ class ChromaRetriever(BaseRetriever):
         query: str,
         *,
         run_manager: CallbackManagerForRetrieverRun,
-    ) -> List[Document]:
+    ) -> list[Document]:
         query_embeddings = self.embedding_function(query)
 
         results = self.collection.query(

backend/apps/socket/main.py

@@ -44,24 +44,26 @@ async def user_join(sid, data):
     print("user-join", sid, data)
 
     auth = data["auth"] if "auth" in data else None
+    if not auth or "token" not in auth:
+        return
 
-    if auth and "token" in auth:
-        data = decode_token(auth["token"])
+    data = decode_token(auth["token"])
+    if data is None or "id" not in data:
+        return
 
-        if data is not None and "id" in data:
-            user = Users.get_user_by_id(data["id"])
+    user = Users.get_user_by_id(data["id"])
+    if not user:
+        return
 
-        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]
 
-            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(f"user {user.name}({user.id}) connected with session ID {sid}")
-
-            await sio.emit("user-count", {"count": len(set(USER_POOL))})
+    await sio.emit("user-count", {"count": len(set(USER_POOL))})
 
 
 @sio.on("user-count")
@@ -80,7 +82,6 @@ def get_models_in_use():
 
 @sio.on("usage")
 async def usage(sid, data):
-
     model_id = data["model"]
 
     # Cancel previous callback if there is one
@@ -139,7 +140,7 @@ async def disconnect(sid):
         print(f"Unknown session ID {sid} disconnected")
 
 
-async def get_event_emitter(request_info):
+def get_event_emitter(request_info):
     async def __event_emitter__(event_data):
         await sio.emit(
             "chat-events",
@@ -154,7 +155,7 @@ async def get_event_emitter(request_info):
     return __event_emitter__
 
 
-async def get_event_call(request_info):
+def get_event_call(request_info):
     async def __event_call__(event_data):
         response = await sio.call(
             "chat-events",

backend/apps/webui/main.py

@@ -1,9 +1,6 @@
-from fastapi import FastAPI, Depends
-from fastapi.routing import APIRoute
+from fastapi import FastAPI
 from fastapi.responses import StreamingResponse
 from fastapi.middleware.cors import CORSMiddleware
-from starlette.middleware.sessions import SessionMiddleware
-from sqlalchemy.orm import Session
 from apps.webui.routers import (
     auths,
     users,
@@ -22,12 +19,15 @@ from apps.webui.models.functions import Functions
 from apps.webui.models.models import Models
 from apps.webui.utils import load_function_module_by_id
 
-from utils.misc import stream_message_template
-from utils.task import prompt_template
+from utils.misc import (
+    openai_chat_chunk_message_template,
+    openai_chat_completion_message_template,
+    apply_model_params_to_body_openai,
+    apply_model_system_prompt_to_body,
+)
 
 
 from config import (
-    WEBUI_BUILD_HASH,
     SHOW_ADMIN_DETAILS,
     ADMIN_EMAIL,
     WEBUI_AUTH,
@@ -35,6 +35,7 @@ from config import (
     DEFAULT_PROMPT_SUGGESTIONS,
     DEFAULT_USER_ROLE,
     ENABLE_SIGNUP,
+    ENABLE_LOGIN_FORM,
     USER_PERMISSIONS,
     WEBHOOK_URL,
     WEBUI_AUTH_TRUSTED_EMAIL_HEADER,
@@ -45,16 +46,15 @@ from config import (
     AppConfig,
     OAUTH_USERNAME_CLAIM,
     OAUTH_PICTURE_CLAIM,
+    OAUTH_EMAIL_CLAIM,
 )
 
 from apps.socket.main import get_event_call, get_event_emitter
 
 import inspect
-import uuid
-import time
 import json
 
-from typing import Iterator, Generator, Optional
+from typing import Iterator, Generator, AsyncGenerator
 from pydantic import BaseModel
 
 app = FastAPI()
@@ -64,6 +64,7 @@ origins = ["*"]
 app.state.config = AppConfig()
 
 app.state.config.ENABLE_SIGNUP = ENABLE_SIGNUP
+app.state.config.ENABLE_LOGIN_FORM = ENABLE_LOGIN_FORM
 app.state.config.JWT_EXPIRES_IN = JWT_EXPIRES_IN
 app.state.AUTH_TRUSTED_EMAIL_HEADER = WEBUI_AUTH_TRUSTED_EMAIL_HEADER
 app.state.AUTH_TRUSTED_NAME_HEADER = WEBUI_AUTH_TRUSTED_NAME_HEADER
@@ -84,6 +85,7 @@ app.state.config.ENABLE_COMMUNITY_SHARING = ENABLE_COMMUNITY_SHARING
 
 app.state.config.OAUTH_USERNAME_CLAIM = OAUTH_USERNAME_CLAIM
 app.state.config.OAUTH_PICTURE_CLAIM = OAUTH_PICTURE_CLAIM
+app.state.config.OAUTH_EMAIL_CLAIM = OAUTH_EMAIL_CLAIM
 
 app.state.MODELS = {}
 app.state.TOOLS = {}
@@ -125,60 +127,58 @@ async def get_status():
     }
 
 
+def get_function_module(pipe_id: str):
+    # Check if function is already loaded
+    if pipe_id not in app.state.FUNCTIONS:
+        function_module, _, _ = load_function_module_by_id(pipe_id)
+        app.state.FUNCTIONS[pipe_id] = function_module
+    else:
+        function_module = app.state.FUNCTIONS[pipe_id]
+
+    if hasattr(function_module, "valves") and hasattr(function_module, "Valves"):
+        valves = Functions.get_function_valves_by_id(pipe_id)
+        function_module.valves = function_module.Valves(**(valves if valves else {}))
+    return function_module
+
+
 async def get_pipe_models():
     pipes = Functions.get_functions_by_type("pipe", active_only=True)
     pipe_models = []
 
     for pipe in pipes:
-        # Check if function is already loaded
-        if pipe.id not in app.state.FUNCTIONS:
-            function_module, function_type, frontmatter = load_function_module_by_id(
-                pipe.id
-            )
-            app.state.FUNCTIONS[pipe.id] = function_module
-        else:
-            function_module = app.state.FUNCTIONS[pipe.id]
-
-        if hasattr(function_module, "valves") and hasattr(function_module, "Valves"):
-            valves = Functions.get_function_valves_by_id(pipe.id)
-            function_module.valves = function_module.Valves(
-                **(valves if valves else {})
-            )
+        function_module = get_function_module(pipe.id)
 
         # Check if function is a manifold
-        if hasattr(function_module, "type"):
-            if function_module.type == "manifold":
-                manifold_pipes = []
+        if hasattr(function_module, "pipes"):
+            manifold_pipes = []
 
-                # Check if pipes is a function or a list
-                if callable(function_module.pipes):
-                    manifold_pipes = function_module.pipes()
-                else:
-                    manifold_pipes = function_module.pipes
+            # Check if pipes is a function or a list
+            if callable(function_module.pipes):
+                manifold_pipes = function_module.pipes()
+            else:
+                manifold_pipes = function_module.pipes
 
-                for p in manifold_pipes:
-                    manifold_pipe_id = f'{pipe.id}.{p["id"]}'
-                    manifold_pipe_name = p["name"]
+            for p in manifold_pipes:
+                manifold_pipe_id = f'{pipe.id}.{p["id"]}'
+                manifold_pipe_name = p["name"]
 
-                    if hasattr(function_module, "name"):
-                        manifold_pipe_name = (
-                            f"{function_module.name}{manifold_pipe_name}"
-                        )
+                if hasattr(function_module, "name"):
+                    manifold_pipe_name = f"{function_module.name}{manifold_pipe_name}"
 
-                    pipe_flag = {"type": pipe.type}
-                    if hasattr(function_module, "ChatValves"):
-                        pipe_flag["valves_spec"] = function_module.ChatValves.schema()
+                pipe_flag = {"type": pipe.type}
+                if hasattr(function_module, "ChatValves"):
+                    pipe_flag["valves_spec"] = function_module.ChatValves.schema()
 
-                    pipe_models.append(
-                        {
-                            "id": manifold_pipe_id,
-                            "name": manifold_pipe_name,
-                            "object": "model",
-                            "created": pipe.created_at,
-                            "owned_by": "openai",
-                            "pipe": pipe_flag,
-                        }
-                    )
+                pipe_models.append(
+                    {
+                        "id": manifold_pipe_id,
+                        "name": manifold_pipe_name,
+                        "object": "model",
+                        "created": pipe.created_at,
+                        "owned_by": "openai",
+                        "pipe": pipe_flag,
+                    }
+                )
         else:
             pipe_flag = {"type": "pipe"}
             if hasattr(function_module, "ChatValves"):
@@ -198,262 +198,170 @@ async def get_pipe_models():
     return pipe_models
 
 
+async def execute_pipe(pipe, params):
+    if inspect.iscoroutinefunction(pipe):
+        return await pipe(**params)
+    else:
+        return pipe(**params)
+
+
+async def get_message_content(res: str | Generator | AsyncGenerator) -> str:
+    if isinstance(res, str):
+        return res
+    if isinstance(res, Generator):
+        return "".join(map(str, res))
+    if isinstance(res, AsyncGenerator):
+        return "".join([str(stream) async for stream in res])
+
+
+def process_line(form_data: dict, line):
+    if isinstance(line, BaseModel):
+        line = line.model_dump_json()
+        line = f"data: {line}"
+    if isinstance(line, dict):
+        line = f"data: {json.dumps(line)}"
+
+    try:
+        line = line.decode("utf-8")
+    except Exception:
+        pass
+
+    if line.startswith("data:"):
+        return f"{line}\n\n"
+    else:
+        line = openai_chat_chunk_message_template(form_data["model"], line)
+        return f"data: {json.dumps(line)}\n\n"
+
+
+def get_pipe_id(form_data: dict) -> str:
+    pipe_id = form_data["model"]
+    if "." in pipe_id:
+        pipe_id, _ = pipe_id.split(".", 1)
+    print(pipe_id)
+    return pipe_id
+
+
+def get_function_params(function_module, form_data, user, extra_params={}):
+    pipe_id = get_pipe_id(form_data)
+    # Get the signature of the function
+    sig = inspect.signature(function_module.pipe)
+    params = {"body": form_data}
+
+    for key, value in extra_params.items():
+        if key in sig.parameters:
+            params[key] = value
+
+    if "__user__" in sig.parameters:
+        __user__ = {
+            "id": user.id,
+            "email": user.email,
+            "name": user.name,
+            "role": user.role,
+        }
+
+        try:
+            if hasattr(function_module, "UserValves"):
+                __user__["valves"] = function_module.UserValves(
+                    **Functions.get_user_valves_by_id_and_user_id(pipe_id, user.id)
+                )
+        except Exception as e:
+            print(e)
+
+        params["__user__"] = __user__
+    return params
+
+
 async def generate_function_chat_completion(form_data, user):
     model_id = form_data.get("model")
     model_info = Models.get_model_by_id(model_id)
-
-    metadata = None
-    if "metadata" in form_data:
-        metadata = form_data["metadata"]
-        del form_data["metadata"]
+    metadata = form_data.pop("metadata", None)
 
     __event_emitter__ = None
     __event_call__ = None
     __task__ = None
 
     if metadata:
-        if (
-            metadata.get("session_id")
-            and metadata.get("chat_id")
-            and metadata.get("message_id")
-        ):
-            __event_emitter__ = await get_event_emitter(metadata)
-            __event_call__ = await get_event_call(metadata)
-
-        if metadata.get("task"):
-            __task__ = metadata.get("task")
+        if all(k in metadata for k in ("session_id", "chat_id", "message_id")):
+            __event_emitter__ = get_event_emitter(metadata)
+            __event_call__ = get_event_call(metadata)
+        __task__ = metadata.get("task", None)
 
     if model_info:
         if model_info.base_model_id:
             form_data["model"] = model_info.base_model_id
 
-        model_info.params = model_info.params.model_dump()
+        params = model_info.params.model_dump()
+        form_data = apply_model_params_to_body_openai(params, form_data)
+        form_data = apply_model_system_prompt_to_body(params, form_data, user)
 
-        if model_info.params:
-            if model_info.params.get("temperature", None) is not None:
-                form_data["temperature"] = float(model_info.params.get("temperature"))
+    pipe_id = get_pipe_id(form_data)
+    function_module = get_function_module(pipe_id)
 
-            if model_info.params.get("top_p", None):
-                form_data["top_p"] = int(model_info.params.get("top_p", None))
+    pipe = function_module.pipe
+    params = get_function_params(
+        function_module,
+        form_data,
+        user,
+        {
+            "__event_emitter__": __event_emitter__,
+            "__event_call__": __event_call__,
+            "__task__": __task__,
+        },
+    )
 
-            if model_info.params.get("max_tokens", None):
-                form_data["max_tokens"] = int(model_info.params.get("max_tokens", None))
-
-            if model_info.params.get("frequency_penalty", None):
-                form_data["frequency_penalty"] = int(
-                    model_info.params.get("frequency_penalty", None)
-                )
-
-            if model_info.params.get("seed", None):
-                form_data["seed"] = model_info.params.get("seed", None)
-
-            if model_info.params.get("stop", None):
-                form_data["stop"] = (
-                    [
-                        bytes(stop, "utf-8").decode("unicode_escape")
-                        for stop in model_info.params["stop"]
-                    ]
-                    if model_info.params.get("stop", None)
-                    else None
-                )
-
-        system = model_info.params.get("system", None)
-        if system:
-            system = prompt_template(
-                system,
-                **(
-                    {
-                        "user_name": user.name,
-                        "user_location": (
-                            user.info.get("location") if user.info else None
-                        ),
-                    }
-                    if user
-                    else {}
-                ),
-            )
-            # Check if the payload already has a system message
-            # If not, add a system message to the payload
-            if form_data.get("messages"):
-                for message in form_data["messages"]:
-                    if message.get("role") == "system":
-                        message["content"] = system + message["content"]
-                        break
-                else:
-                    form_data["messages"].insert(
-                        0,
-                        {
-                            "role": "system",
-                            "content": system,
-                        },
-                    )
-
-    else:
-        pass
-
-    async def job():
-        pipe_id = form_data["model"]
-        if "." in pipe_id:
-            pipe_id, sub_pipe_id = pipe_id.split(".", 1)
-        print(pipe_id)
-
-        # Check if function is already loaded
-        if pipe_id not in app.state.FUNCTIONS:
-            function_module, function_type, frontmatter = load_function_module_by_id(
-                pipe_id
-            )
-            app.state.FUNCTIONS[pipe_id] = function_module
-        else:
-            function_module = app.state.FUNCTIONS[pipe_id]
-
-        if hasattr(function_module, "valves") and hasattr(function_module, "Valves"):
-
-            valves = Functions.get_function_valves_by_id(pipe_id)
-            function_module.valves = function_module.Valves(
-                **(valves if valves else {})
-            )
-
-        pipe = function_module.pipe
-
-        # Get the signature of the function
-        sig = inspect.signature(pipe)
-        params = {"body": form_data}
-
-        if "__user__" in sig.parameters:
-            __user__ = {
-                "id": user.id,
-                "email": user.email,
-                "name": user.name,
-                "role": user.role,
-            }
+    if form_data["stream"]:
 
+        async def stream_content():
             try:
-                if hasattr(function_module, "UserValves"):
-                    __user__["valves"] = function_module.UserValves(
-                        **Functions.get_user_valves_by_id_and_user_id(pipe_id, user.id)
-                    )
-            except Exception as e:
-                print(e)
+                res = await execute_pipe(pipe, params)
 
-            params = {**params, "__user__": __user__}
-
-        if "__event_emitter__" in sig.parameters:
-            params = {**params, "__event_emitter__": __event_emitter__}
-
-        if "__event_call__" in sig.parameters:
-            params = {**params, "__event_call__": __event_call__}
-
-        if "__task__" in sig.parameters:
-            params = {**params, "__task__": __task__}
-
-        if form_data["stream"]:
-
-            async def stream_content():
-                try:
-                    if inspect.iscoroutinefunction(pipe):
-                        res = await pipe(**params)
-                    else:
-                        res = pipe(**params)
-
-                    # Directly return if the response is a StreamingResponse
-                    if isinstance(res, StreamingResponse):
-                        async for data in res.body_iterator:
-                            yield data
-                        return
-                    if isinstance(res, dict):
-                        yield f"data: {json.dumps(res)}\n\n"
-                        return
-
-                except Exception as e:
-                    print(f"Error: {e}")
-                    yield f"data: {json.dumps({'error': {'detail':str(e)}})}\n\n"
+                # Directly return if the response is a StreamingResponse
+                if isinstance(res, StreamingResponse):
+                    async for data in res.body_iterator:
+                        yield data
+                    return
+                if isinstance(res, dict):
+                    yield f"data: {json.dumps(res)}\n\n"
                     return
 
-                if isinstance(res, str):
-                    message = stream_message_template(form_data["model"], res)
-                    yield f"data: {json.dumps(message)}\n\n"
-
-                if isinstance(res, Iterator):
-                    for line in res:
-                        if isinstance(line, BaseModel):
-                            line = line.model_dump_json()
-                            line = f"data: {line}"
-                        if isinstance(line, dict):
-                            line = f"data: {json.dumps(line)}"
-
-                        try:
-                            line = line.decode("utf-8")
-                        except:
-                            pass
-
-                        if line.startswith("data:"):
-                            yield f"{line}\n\n"
-                        else:
-                            line = stream_message_template(form_data["model"], line)
-                            yield f"data: {json.dumps(line)}\n\n"
-
-                if isinstance(res, str) or isinstance(res, Generator):
-                    finish_message = {
-                        "id": f"{form_data['model']}-{str(uuid.uuid4())}",
-                        "object": "chat.completion.chunk",
-                        "created": int(time.time()),
-                        "model": form_data["model"],
-                        "choices": [
-                            {
-                                "index": 0,
-                                "delta": {},
-                                "logprobs": None,
-                                "finish_reason": "stop",
-                            }
-                        ],
-                    }
-
-                    yield f"data: {json.dumps(finish_message)}\n\n"
-                    yield f"data: [DONE]"
-
-            return StreamingResponse(stream_content(), media_type="text/event-stream")
-        else:
-
-            try:
-                if inspect.iscoroutinefunction(pipe):
-                    res = await pipe(**params)
-                else:
-                    res = pipe(**params)
-
-                if isinstance(res, StreamingResponse):
-                    return res
             except Exception as e:
                 print(f"Error: {e}")
-                return {"error": {"detail": str(e)}}
+                yield f"data: {json.dumps({'error': {'detail':str(e)}})}\n\n"
+                return
 
-            if isinstance(res, dict):
-                return res
-            elif isinstance(res, BaseModel):
-                return res.model_dump()
-            else:
-                message = ""
-                if isinstance(res, str):
-                    message = res
-                if isinstance(res, Generator):
-                    for stream in res:
-                        message = f"{message}{stream}"
+            if isinstance(res, str):
+                message = openai_chat_chunk_message_template(form_data["model"], res)
+                yield f"data: {json.dumps(message)}\n\n"
 
-                return {
-                    "id": f"{form_data['model']}-{str(uuid.uuid4())}",
-                    "object": "chat.completion",
-                    "created": int(time.time()),
-                    "model": form_data["model"],
-                    "choices": [
-                        {
-                            "index": 0,
-                            "message": {
-                                "role": "assistant",
-                                "content": message,
-                            },
-                            "logprobs": None,
-                            "finish_reason": "stop",
-                        }
-                    ],
-                }
+            if isinstance(res, Iterator):
+                for line in res:
+                    yield process_line(form_data, line)
 
-    return await job()
+            if isinstance(res, AsyncGenerator):
+                async for line in res:
+                    yield process_line(form_data, line)
+
+            if isinstance(res, str) or isinstance(res, Generator):
+                finish_message = openai_chat_chunk_message_template(
+                    form_data["model"], ""
+                )
+                finish_message["choices"][0]["finish_reason"] = "stop"
+                yield f"data: {json.dumps(finish_message)}\n\n"
+                yield "data: [DONE]"
+
+        return StreamingResponse(stream_content(), media_type="text/event-stream")
+    else:
+        try:
+            res = await execute_pipe(pipe, params)
+
+        except Exception as e:
+            print(f"Error: {e}")
+            return {"error": {"detail": str(e)}}
+
+        if isinstance(res, StreamingResponse) or isinstance(res, dict):
+            return res
+        if isinstance(res, BaseModel):
+            return res.model_dump()
+
+        message = await get_message_content(res)
+        return openai_chat_completion_message_template(form_data["model"], message)

backend/apps/webui/models/auths.py

@@ -140,7 +140,7 @@ class AuthsTable:
                         return None
                 else:
                     return None
-        except:
+        except Exception:
             return None
 
     def authenticate_user_by_api_key(self, api_key: str) -> Optional[UserModel]:
@@ -152,7 +152,7 @@ class AuthsTable:
         try:
             user = Users.get_user_by_api_key(api_key)
             return user if user else None
-        except:
+        except Exception:
             return False
 
     def authenticate_user_by_trusted_header(self, email: str) -> Optional[UserModel]:
@@ -163,7 +163,7 @@ class AuthsTable:
                 if auth:
                     user = Users.get_user_by_id(auth.id)
                     return user
-        except:
+        except Exception:
             return None
 
     def update_user_password_by_id(self, id: str, new_password: str) -> bool:
@@ -174,7 +174,7 @@ class AuthsTable:
                 )
                 db.commit()
                 return True if result == 1 else False
-        except:
+        except Exception:
             return False
 
     def update_email_by_id(self, id: str, email: str) -> bool:
@@ -183,7 +183,7 @@ class AuthsTable:
                 result = db.query(Auth).filter_by(id=id).update({"email": email})
                 db.commit()
                 return True if result == 1 else False
-        except:
+        except Exception:
             return False
 
     def delete_auth_by_id(self, id: str) -> bool:
@@ -200,7 +200,7 @@ class AuthsTable:
                     return True
                 else:
                     return False
-        except:
+        except Exception:
             return False
 
 

backend/apps/webui/models/chats.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict
-from typing import List, Union, Optional
+from typing import Union, Optional
 
 import json
 import uuid
@@ -164,7 +164,7 @@ class ChatTable:
                 db.refresh(chat)
 
                 return self.get_chat_by_id(chat.share_id)
-        except:
+        except Exception:
             return None
 
     def delete_shared_chat_by_chat_id(self, chat_id: str) -> bool:
@@ -175,7 +175,7 @@ class ChatTable:
                 db.commit()
 
                 return True
-        except:
+        except Exception:
             return False
 
     def update_chat_share_id_by_id(
@@ -189,7 +189,7 @@ class ChatTable:
                 db.commit()
                 db.refresh(chat)
                 return ChatModel.model_validate(chat)
-        except:
+        except Exception:
             return None
 
     def toggle_chat_archive_by_id(self, id: str) -> Optional[ChatModel]:
@@ -201,7 +201,7 @@ class ChatTable:
                 db.commit()
                 db.refresh(chat)
                 return ChatModel.model_validate(chat)
-        except:
+        except Exception:
             return None
 
     def archive_all_chats_by_user_id(self, user_id: str) -> bool:
@@ -210,12 +210,12 @@ class ChatTable:
                 db.query(Chat).filter_by(user_id=user_id).update({"archived": True})
                 db.commit()
                 return True
-        except:
+        except Exception:
             return False
 
     def get_archived_chat_list_by_user_id(
         self, user_id: str, skip: int = 0, limit: int = 50
-    ) -> List[ChatModel]:
+    ) -> list[ChatModel]:
         with get_db() as db:
 
             all_chats = (
@@ -233,7 +233,7 @@ class ChatTable:
         include_archived: bool = False,
         skip: int = 0,
         limit: int = 50,
-    ) -> List[ChatModel]:
+    ) -> list[ChatModel]:
         with get_db() as db:
             query = db.query(Chat).filter_by(user_id=user_id)
             if not include_archived:
@@ -245,9 +245,42 @@ class ChatTable:
             )
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
+    def get_chat_title_id_list_by_user_id(
+        self,
+        user_id: str,
+        include_archived: bool = False,
+        skip: int = 0,
+        limit: int = -1,
+    ) -> list[ChatTitleIdResponse]:
+        with get_db() as db:
+            query = db.query(Chat).filter_by(user_id=user_id)
+            if not include_archived:
+                query = query.filter_by(archived=False)
+
+            all_chats = (
+                query.order_by(Chat.updated_at.desc())
+                # limit cols
+                .with_entities(Chat.id, Chat.title, Chat.updated_at, Chat.created_at)
+                .limit(limit)
+                .offset(skip)
+                .all()
+            )
+            # result has to be destrctured from sqlalchemy `row` and mapped to a dict since the `ChatModel`is not the returned dataclass.
+            return [
+                ChatTitleIdResponse.model_validate(
+                    {
+                        "id": chat[0],
+                        "title": chat[1],
+                        "updated_at": chat[2],
+                        "created_at": chat[3],
+                    }
+                )
+                for chat in all_chats
+            ]
+
     def get_chat_list_by_chat_ids(
-        self, chat_ids: List[str], skip: int = 0, limit: int = 50
-    ) -> List[ChatModel]:
+        self, chat_ids: list[str], skip: int = 0, limit: int = 50
+    ) -> list[ChatModel]:
         with get_db() as db:
             all_chats = (
                 db.query(Chat)
@@ -264,7 +297,7 @@ class ChatTable:
 
                 chat = db.get(Chat, id)
                 return ChatModel.model_validate(chat)
-        except:
+        except Exception:
             return None
 
     def get_chat_by_share_id(self, id: str) -> Optional[ChatModel]:
@@ -286,10 +319,10 @@ class ChatTable:
 
                 chat = db.query(Chat).filter_by(id=id, user_id=user_id).first()
                 return ChatModel.model_validate(chat)
-        except:
+        except Exception:
             return None
 
-    def get_chats(self, skip: int = 0, limit: int = 50) -> List[ChatModel]:
+    def get_chats(self, skip: int = 0, limit: int = 50) -> list[ChatModel]:
         with get_db() as db:
 
             all_chats = (
@@ -299,7 +332,7 @@ class ChatTable:
             )
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
-    def get_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
+    def get_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
         with get_db() as db:
 
             all_chats = (
@@ -309,7 +342,7 @@ class ChatTable:
             )
             return [ChatModel.model_validate(chat) for chat in all_chats]
 
-    def get_archived_chats_by_user_id(self, user_id: str) -> List[ChatModel]:
+    def get_archived_chats_by_user_id(self, user_id: str) -> list[ChatModel]:
         with get_db() as db:
 
             all_chats = (
@@ -327,7 +360,7 @@ class ChatTable:
                 db.commit()
 
                 return True and self.delete_shared_chat_by_chat_id(id)
-        except:
+        except Exception:
             return False
 
     def delete_chat_by_id_and_user_id(self, id: str, user_id: str) -> bool:
@@ -338,7 +371,7 @@ class ChatTable:
                 db.commit()
 
                 return True and self.delete_shared_chat_by_chat_id(id)
-        except:
+        except Exception:
             return False
 
     def delete_chats_by_user_id(self, user_id: str) -> bool:
@@ -352,7 +385,7 @@ class ChatTable:
                 db.commit()
 
                 return True
-        except:
+        except Exception:
             return False
 
     def delete_shared_chats_by_user_id(self, user_id: str) -> bool:
@@ -367,7 +400,7 @@ class ChatTable:
                 db.commit()
 
                 return True
-        except:
+        except Exception:
             return False
 
 

backend/apps/webui/models/documents.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict
-from typing import List, Optional
+from typing import Optional
 import time
 import logging
 
@@ -93,7 +93,7 @@ class DocumentsTable:
                     return DocumentModel.model_validate(result)
                 else:
                     return None
-            except:
+            except Exception:
                 return None
 
     def get_doc_by_name(self, name: str) -> Optional[DocumentModel]:
@@ -102,10 +102,10 @@ class DocumentsTable:
 
                 document = db.query(Document).filter_by(name=name).first()
                 return DocumentModel.model_validate(document) if document else None
-        except:
+        except Exception:
             return None
 
-    def get_docs(self) -> List[DocumentModel]:
+    def get_docs(self) -> list[DocumentModel]:
         with get_db() as db:
 
             return [
@@ -160,7 +160,7 @@ class DocumentsTable:
                 db.query(Document).filter_by(name=name).delete()
                 db.commit()
                 return True
-        except:
+        except Exception:
             return False
 
 

backend/apps/webui/models/files.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict
-from typing import List, Union, Optional
+from typing import Union, Optional
 import time
 import logging
 
@@ -90,10 +90,10 @@ class FilesTable:
             try:
                 file = db.get(File, id)
                 return FileModel.model_validate(file)
-            except:
+            except Exception:
                 return None
 
-    def get_files(self) -> List[FileModel]:
+    def get_files(self) -> list[FileModel]:
         with get_db() as db:
 
             return [FileModel.model_validate(file) for file in db.query(File).all()]
@@ -107,7 +107,7 @@ class FilesTable:
                 db.commit()
 
                 return True
-            except:
+            except Exception:
                 return False
 
     def delete_all_files(self) -> bool:
@@ -119,7 +119,7 @@ class FilesTable:
                 db.commit()
 
                 return True
-            except:
+            except Exception:
                 return False
 
 

backend/apps/webui/models/functions.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict
-from typing import List, Union, Optional
+from typing import Union, Optional
 import time
 import logging
 
@@ -122,10 +122,10 @@ class FunctionsTable:
 
                 function = db.get(Function, id)
                 return FunctionModel.model_validate(function)
-        except:
+        except Exception:
             return None
 
-    def get_functions(self, active_only=False) -> List[FunctionModel]:
+    def get_functions(self, active_only=False) -> list[FunctionModel]:
         with get_db() as db:
 
             if active_only:
@@ -141,7 +141,7 @@ class FunctionsTable:
 
     def get_functions_by_type(
         self, type: str, active_only=False
-    ) -> List[FunctionModel]:
+    ) -> list[FunctionModel]:
         with get_db() as db:
 
             if active_only:
@@ -157,7 +157,7 @@ class FunctionsTable:
                     for function in db.query(Function).filter_by(type=type).all()
                 ]
 
-    def get_global_filter_functions(self) -> List[FunctionModel]:
+    def get_global_filter_functions(self) -> list[FunctionModel]:
         with get_db() as db:
 
             return [
@@ -167,7 +167,7 @@ class FunctionsTable:
                 .all()
             ]
 
-    def get_global_action_functions(self) -> List[FunctionModel]:
+    def get_global_action_functions(self) -> list[FunctionModel]:
         with get_db() as db:
             return [
                 FunctionModel.model_validate(function)
@@ -198,7 +198,7 @@ class FunctionsTable:
                 db.commit()
                 db.refresh(function)
                 return self.get_function_by_id(id)
-            except:
+            except Exception:
                 return None
 
     def get_user_valves_by_id_and_user_id(
@@ -256,7 +256,7 @@ class FunctionsTable:
                 )
                 db.commit()
                 return self.get_function_by_id(id)
-            except:
+            except Exception:
                 return None
 
     def deactivate_all_functions(self) -> Optional[bool]:
@@ -271,7 +271,7 @@ class FunctionsTable:
                 )
                 db.commit()
                 return True
-            except:
+            except Exception:
                 return None
 
     def delete_function_by_id(self, id: str) -> bool:
@@ -281,7 +281,7 @@ class FunctionsTable:
                 db.commit()
 
                 return True
-            except:
+            except Exception:
                 return False
 
 

backend/apps/webui/models/memories.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict
-from typing import List, Union, Optional
+from typing import Union, Optional
 
 from sqlalchemy import Column, String, BigInteger, Text
 
@@ -80,25 +80,25 @@ class MemoriesTable:
                 )
                 db.commit()
                 return self.get_memory_by_id(id)
-            except:
+            except Exception:
                 return None
 
-    def get_memories(self) -> List[MemoryModel]:
+    def get_memories(self) -> list[MemoryModel]:
         with get_db() as db:
 
             try:
                 memories = db.query(Memory).all()
                 return [MemoryModel.model_validate(memory) for memory in memories]
-            except:
+            except Exception:
                 return None
 
-    def get_memories_by_user_id(self, user_id: str) -> List[MemoryModel]:
+    def get_memories_by_user_id(self, user_id: str) -> list[MemoryModel]:
         with get_db() as db:
 
             try:
                 memories = db.query(Memory).filter_by(user_id=user_id).all()
                 return [MemoryModel.model_validate(memory) for memory in memories]
-            except:
+            except Exception:
                 return None
 
     def get_memory_by_id(self, id: str) -> Optional[MemoryModel]:
@@ -107,7 +107,7 @@ class MemoriesTable:
             try:
                 memory = db.get(Memory, id)
                 return MemoryModel.model_validate(memory)
-            except:
+            except Exception:
                 return None
 
     def delete_memory_by_id(self, id: str) -> bool:
@@ -119,7 +119,7 @@ class MemoriesTable:
 
                 return True
 
-            except:
+            except Exception:
                 return False
 
     def delete_memories_by_user_id(self, user_id: str) -> bool:
@@ -130,7 +130,7 @@ class MemoriesTable:
                 db.commit()
 
                 return True
-            except:
+            except Exception:
                 return False
 
     def delete_memory_by_id_and_user_id(self, id: str, user_id: str) -> bool:
@@ -141,7 +141,7 @@ class MemoriesTable:
                 db.commit()
 
                 return True
-            except:
+            except Exception:
                 return False
 
 

backend/apps/webui/models/models.py

@@ -1,13 +1,11 @@
-import json
 import logging
-from typing import Optional
+from typing import Optional, List
 
 from pydantic import BaseModel, ConfigDict
-from sqlalchemy import String, Column, BigInteger, Text
+from sqlalchemy import Column, BigInteger, Text
 
 from apps.webui.internal.db import Base, JSONField, get_db
 
-from typing import List, Union, Optional
 from config import SRC_LOG_LEVELS
 
 import time
@@ -113,7 +111,6 @@ class ModelForm(BaseModel):
 
 
 class ModelsTable:
-
     def insert_new_model(
         self, form_data: ModelForm, user_id: str
     ) -> Optional[ModelModel]:
@@ -126,9 +123,7 @@ class ModelsTable:
             }
         )
         try:
-
             with get_db() as db:
-
                 result = Model(**model.model_dump())
                 db.add(result)
                 db.commit()
@@ -142,18 +137,16 @@ class ModelsTable:
             print(e)
             return None
 
-    def get_all_models(self) -> List[ModelModel]:
+    def get_all_models(self) -> list[ModelModel]:
         with get_db() as db:
-
             return [ModelModel.model_validate(model) for model in db.query(Model).all()]
 
     def get_model_by_id(self, id: str) -> Optional[ModelModel]:
         try:
             with get_db() as db:
-
                 model = db.get(Model, id)
                 return ModelModel.model_validate(model)
-        except:
+        except Exception:
             return None
 
     def update_model_by_id(self, id: str, model: ModelForm) -> Optional[ModelModel]:
@@ -178,12 +171,11 @@ class ModelsTable:
     def delete_model_by_id(self, id: str) -> bool:
         try:
             with get_db() as db:
-
                 db.query(Model).filter_by(id=id).delete()
                 db.commit()
 
                 return True
-        except:
+        except Exception:
             return False
 
 

backend/apps/webui/models/prompts.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict
-from typing import List, Optional
+from typing import Optional
 import time
 
 from sqlalchemy import String, Column, BigInteger, Text
@@ -79,10 +79,10 @@ class PromptsTable:
 
                 prompt = db.query(Prompt).filter_by(command=command).first()
                 return PromptModel.model_validate(prompt)
-        except:
+        except Exception:
             return None
 
-    def get_prompts(self) -> List[PromptModel]:
+    def get_prompts(self) -> list[PromptModel]:
         with get_db() as db:
 
             return [
@@ -101,7 +101,7 @@ class PromptsTable:
                 prompt.timestamp = int(time.time())
                 db.commit()
                 return PromptModel.model_validate(prompt)
-        except:
+        except Exception:
             return None
 
     def delete_prompt_by_command(self, command: str) -> bool:
@@ -112,7 +112,7 @@ class PromptsTable:
                 db.commit()
 
                 return True
-        except:
+        except Exception:
             return False
 
 

backend/apps/webui/models/tags.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict
-from typing import List, Optional
+from typing import Optional
 
 import json
 import uuid
@@ -69,11 +69,11 @@ class ChatIdTagForm(BaseModel):
 
 
 class TagChatIdsResponse(BaseModel):
-    chat_ids: List[str]
+    chat_ids: list[str]
 
 
 class ChatTagsResponse(BaseModel):
-    tags: List[str]
+    tags: list[str]
 
 
 class TagTable:
@@ -109,7 +109,7 @@ class TagTable:
         self, user_id: str, form_data: ChatIdTagForm
     ) -> Optional[ChatIdTagModel]:
         tag = self.get_tag_by_name_and_user_id(form_data.tag_name, user_id)
-        if tag == None:
+        if tag is None:
             tag = self.insert_new_tag(form_data.tag_name, user_id)
 
         id = str(uuid.uuid4())
@@ -132,10 +132,10 @@ class TagTable:
                     return ChatIdTagModel.model_validate(result)
                 else:
                     return None
-        except:
+        except Exception:
             return None
 
-    def get_tags_by_user_id(self, user_id: str) -> List[TagModel]:
+    def get_tags_by_user_id(self, user_id: str) -> list[TagModel]:
         with get_db() as db:
             tag_names = [
                 chat_id_tag.tag_name
@@ -159,7 +159,7 @@ class TagTable:
 
     def get_tags_by_chat_id_and_user_id(
         self, chat_id: str, user_id: str
-    ) -> List[TagModel]:
+    ) -> list[TagModel]:
         with get_db() as db:
 
             tag_names = [
@@ -184,7 +184,7 @@ class TagTable:
 
     def get_chat_ids_by_tag_name_and_user_id(
         self, tag_name: str, user_id: str
-    ) -> List[ChatIdTagModel]:
+    ) -> list[ChatIdTagModel]:
         with get_db() as db:
 
             return [

backend/apps/webui/models/tools.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict
-from typing import List, Optional
+from typing import Optional
 import time
 import logging
 from sqlalchemy import String, Column, BigInteger, Text
@@ -45,7 +45,7 @@ class ToolModel(BaseModel):
     user_id: str
     name: str
     content: str
-    specs: List[dict]
+    specs: list[dict]
     meta: ToolMeta
     updated_at: int  # timestamp in epoch
     created_at: int  # timestamp in epoch
@@ -81,7 +81,7 @@ class ToolValves(BaseModel):
 class ToolsTable:
 
     def insert_new_tool(
-        self, user_id: str, form_data: ToolForm, specs: List[dict]
+        self, user_id: str, form_data: ToolForm, specs: list[dict]
     ) -> Optional[ToolModel]:
 
         with get_db() as db:
@@ -115,10 +115,10 @@ class ToolsTable:
 
                 tool = db.get(Tool, id)
                 return ToolModel.model_validate(tool)
-        except:
+        except Exception:
             return None
 
-    def get_tools(self) -> List[ToolModel]:
+    def get_tools(self) -> list[ToolModel]:
         with get_db() as db:
             return [ToolModel.model_validate(tool) for tool in db.query(Tool).all()]
 
@@ -141,7 +141,7 @@ class ToolsTable:
                 )
                 db.commit()
                 return self.get_tool_by_id(id)
-        except:
+        except Exception:
             return None
 
     def get_user_valves_by_id_and_user_id(
@@ -196,7 +196,7 @@ class ToolsTable:
                 tool = db.query(Tool).get(id)
                 db.refresh(tool)
                 return ToolModel.model_validate(tool)
-        except:
+        except Exception:
             return None
 
     def delete_tool_by_id(self, id: str) -> bool:
@@ -206,7 +206,7 @@ class ToolsTable:
                 db.commit()
 
                 return True
-        except:
+        except Exception:
             return False
 
 

backend/apps/webui/models/users.py

@@ -1,5 +1,5 @@
 from pydantic import BaseModel, ConfigDict, parse_obj_as
-from typing import List, Union, Optional
+from typing import Union, Optional
 import time
 
 from sqlalchemy import String, Column, BigInteger, Text
@@ -125,7 +125,7 @@ class UsersTable:
 
                 user = db.query(User).filter_by(api_key=api_key).first()
                 return UserModel.model_validate(user)
-        except:
+        except Exception:
             return None
 
     def get_user_by_email(self, email: str) -> Optional[UserModel]:
@@ -134,7 +134,7 @@ class UsersTable:
 
                 user = db.query(User).filter_by(email=email).first()
                 return UserModel.model_validate(user)
-        except:
+        except Exception:
             return None
 
     def get_user_by_oauth_sub(self, sub: str) -> Optional[UserModel]:
@@ -143,10 +143,10 @@ class UsersTable:
 
                 user = db.query(User).filter_by(oauth_sub=sub).first()
                 return UserModel.model_validate(user)
-        except:
+        except Exception:
             return None
 
-    def get_users(self, skip: int = 0, limit: int = 50) -> List[UserModel]:
+    def get_users(self, skip: int = 0, limit: int = 50) -> list[UserModel]:
         with get_db() as db:
             users = (
                 db.query(User)
@@ -164,7 +164,7 @@ class UsersTable:
             with get_db() as db:
                 user = db.query(User).order_by(User.created_at).first()
                 return UserModel.model_validate(user)
-        except:
+        except Exception:
             return None
 
     def update_user_role_by_id(self, id: str, role: str) -> Optional[UserModel]:
@@ -174,7 +174,7 @@ class UsersTable:
                 db.commit()
                 user = db.query(User).filter_by(id=id).first()
                 return UserModel.model_validate(user)
-        except:
+        except Exception:
             return None
 
     def update_user_profile_image_url_by_id(
@@ -189,7 +189,7 @@ class UsersTable:
 
                 user = db.query(User).filter_by(id=id).first()
                 return UserModel.model_validate(user)
-        except:
+        except Exception:
             return None
 
     def update_user_last_active_by_id(self, id: str) -> Optional[UserModel]:
@@ -203,7 +203,7 @@ class UsersTable:
 
                 user = db.query(User).filter_by(id=id).first()
                 return UserModel.model_validate(user)
-        except:
+        except Exception:
             return None
 
     def update_user_oauth_sub_by_id(
@@ -216,7 +216,7 @@ class UsersTable:
 
                 user = db.query(User).filter_by(id=id).first()
                 return UserModel.model_validate(user)
-        except:
+        except Exception:
             return None
 
     def update_user_by_id(self, id: str, updated: dict) -> Optional[UserModel]:
@@ -245,7 +245,7 @@ class UsersTable:
                 return True
             else:
                 return False
-        except:
+        except Exception:
             return False
 
     def update_user_api_key_by_id(self, id: str, api_key: str) -> str:
@@ -254,7 +254,7 @@ class UsersTable:
                 result = db.query(User).filter_by(id=id).update({"api_key": api_key})
                 db.commit()
                 return True if result == 1 else False
-        except:
+        except Exception:
             return False
 
     def get_user_api_key_by_id(self, id: str) -> Optional[str]:

backend/apps/webui/routers/chats.py

@@ -1,6 +1,6 @@
 from fastapi import Depends, Request, HTTPException, status
 from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from typing import Union, Optional
 from utils.utils import get_verified_user, get_admin_user
 from fastapi import APIRouter
 from pydantic import BaseModel
@@ -28,7 +28,7 @@ from apps.webui.models.tags import (
 
 from constants import ERROR_MESSAGES
 
-from config import SRC_LOG_LEVELS, ENABLE_ADMIN_EXPORT
+from config import SRC_LOG_LEVELS, ENABLE_ADMIN_EXPORT, ENABLE_ADMIN_CHAT_ACCESS
 
 log = logging.getLogger(__name__)
 log.setLevel(SRC_LOG_LEVELS["MODELS"])
@@ -40,12 +40,18 @@ router = APIRouter()
 ############################
 
 
-@router.get("/", response_model=List[ChatTitleIdResponse])
-@router.get("/list", response_model=List[ChatTitleIdResponse])
+@router.get("/", response_model=list[ChatTitleIdResponse])
+@router.get("/list", response_model=list[ChatTitleIdResponse])
 async def get_session_user_chat_list(
-    user=Depends(get_verified_user), skip: int = 0, limit: int = 50
+    user=Depends(get_verified_user), page: Optional[int] = None
 ):
-    return Chats.get_chat_list_by_user_id(user.id, skip, limit)
+    if page is not None:
+        limit = 60
+        skip = (page - 1) * limit
+
+        return Chats.get_chat_title_id_list_by_user_id(user.id, skip=skip, limit=limit)
+    else:
+        return Chats.get_chat_title_id_list_by_user_id(user.id)
 
 
 ############################
@@ -74,13 +80,18 @@ async def delete_all_user_chats(request: Request, user=Depends(get_verified_user
 ############################
 
 
-@router.get("/list/user/{user_id}", response_model=List[ChatTitleIdResponse])
+@router.get("/list/user/{user_id}", response_model=list[ChatTitleIdResponse])
 async def get_user_chat_list_by_user_id(
     user_id: str,
     user=Depends(get_admin_user),
     skip: int = 0,
     limit: int = 50,
 ):
+    if not ENABLE_ADMIN_CHAT_ACCESS:
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
     return Chats.get_chat_list_by_user_id(
         user_id, include_archived=True, skip=skip, limit=limit
     )
@@ -108,7 +119,7 @@ async def create_new_chat(form_data: ChatForm, user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/all", response_model=List[ChatResponse])
+@router.get("/all", response_model=list[ChatResponse])
 async def get_user_chats(user=Depends(get_verified_user)):
     return [
         ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
@@ -121,7 +132,7 @@ async def get_user_chats(user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/all/archived", response_model=List[ChatResponse])
+@router.get("/all/archived", response_model=list[ChatResponse])
 async def get_user_archived_chats(user=Depends(get_verified_user)):
     return [
         ChatResponse(**{**chat.model_dump(), "chat": json.loads(chat.chat)})
@@ -134,7 +145,7 @@ async def get_user_archived_chats(user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/all/db", response_model=List[ChatResponse])
+@router.get("/all/db", response_model=list[ChatResponse])
 async def get_all_user_chats_in_db(user=Depends(get_admin_user)):
     if not ENABLE_ADMIN_EXPORT:
         raise HTTPException(
@@ -152,7 +163,7 @@ async def get_all_user_chats_in_db(user=Depends(get_admin_user)):
 ############################
 
 
-@router.get("/archived", response_model=List[ChatTitleIdResponse])
+@router.get("/archived", response_model=list[ChatTitleIdResponse])
 async def get_archived_session_user_chat_list(
     user=Depends(get_verified_user), skip: int = 0, limit: int = 50
 ):
@@ -181,9 +192,9 @@ async def get_shared_chat_by_id(share_id: str, user=Depends(get_verified_user)):
             status_code=status.HTTP_401_UNAUTHORIZED, detail=ERROR_MESSAGES.NOT_FOUND
         )
 
-    if user.role == "user":
+    if user.role == "user" or (user.role == "admin" and not ENABLE_ADMIN_CHAT_ACCESS):
         chat = Chats.get_chat_by_share_id(share_id)
-    elif user.role == "admin":
+    elif user.role == "admin" and ENABLE_ADMIN_CHAT_ACCESS:
         chat = Chats.get_chat_by_id(share_id)
 
     if chat:
@@ -205,7 +216,7 @@ class TagNameForm(BaseModel):
     limit: Optional[int] = 50
 
 
-@router.post("/tags", response_model=List[ChatTitleIdResponse])
+@router.post("/tags", response_model=list[ChatTitleIdResponse])
 async def get_user_chat_list_by_tag_name(
     form_data: TagNameForm, user=Depends(get_verified_user)
 ):
@@ -230,7 +241,7 @@ async def get_user_chat_list_by_tag_name(
 ############################
 
 
-@router.get("/tags/all", response_model=List[TagModel])
+@router.get("/tags/all", response_model=list[TagModel])
 async def get_all_tags(user=Depends(get_verified_user)):
     try:
         tags = Tags.get_tags_by_user_id(user.id)
@@ -406,7 +417,7 @@ async def delete_shared_chat_by_id(id: str, user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/{id}/tags", response_model=List[TagModel])
+@router.get("/{id}/tags", response_model=list[TagModel])
 async def get_chat_tags_by_id(id: str, user=Depends(get_verified_user)):
     tags = Tags.get_tags_by_chat_id_and_user_id(id, user.id)
 

backend/apps/webui/routers/configs.py

@@ -1,7 +1,7 @@
 from fastapi import Response, Request
 from fastapi import Depends, FastAPI, HTTPException, status
 from datetime import datetime, timedelta
-from typing import List, Union
+from typing import Union
 
 from fastapi import APIRouter
 from pydantic import BaseModel
@@ -29,12 +29,12 @@ class SetDefaultModelsForm(BaseModel):
 
 
 class PromptSuggestion(BaseModel):
-    title: List[str]
+    title: list[str]
     content: str
 
 
 class SetDefaultSuggestionsForm(BaseModel):
-    suggestions: List[PromptSuggestion]
+    suggestions: list[PromptSuggestion]
 
 
 ############################
@@ -50,7 +50,7 @@ async def set_global_default_models(
     return request.app.state.config.DEFAULT_MODELS
 
 
-@router.post("/default/suggestions", response_model=List[PromptSuggestion])
+@router.post("/default/suggestions", response_model=list[PromptSuggestion])
 async def set_global_default_suggestions(
     request: Request,
     form_data: SetDefaultSuggestionsForm,
@@ -67,10 +67,10 @@ async def set_global_default_suggestions(
 
 
 class SetBannersForm(BaseModel):
-    banners: List[BannerModel]
+    banners: list[BannerModel]
 
 
-@router.post("/banners", response_model=List[BannerModel])
+@router.post("/banners", response_model=list[BannerModel])
 async def set_banners(
     request: Request,
     form_data: SetBannersForm,
@@ -81,7 +81,7 @@ async def set_banners(
     return request.app.state.config.BANNERS
 
 
-@router.get("/banners", response_model=List[BannerModel])
+@router.get("/banners", response_model=list[BannerModel])
 async def get_banners(
     request: Request,
     user=Depends(get_verified_user),

backend/apps/webui/routers/documents.py

@@ -1,6 +1,6 @@
 from fastapi import Depends, FastAPI, HTTPException, status
 from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from typing import Union, Optional
 
 from fastapi import APIRouter
 from pydantic import BaseModel
@@ -24,7 +24,7 @@ router = APIRouter()
 ############################
 
 
-@router.get("/", response_model=List[DocumentResponse])
+@router.get("/", response_model=list[DocumentResponse])
 async def get_documents(user=Depends(get_verified_user)):
     docs = [
         DocumentResponse(
@@ -46,7 +46,7 @@ async def get_documents(user=Depends(get_verified_user)):
 @router.post("/create", response_model=Optional[DocumentResponse])
 async def create_new_doc(form_data: DocumentForm, user=Depends(get_admin_user)):
     doc = Documents.get_doc_by_name(form_data.name)
-    if doc == None:
+    if doc is None:
         doc = Documents.insert_new_doc(user.id, form_data)
 
         if doc:
@@ -102,7 +102,7 @@ class TagItem(BaseModel):
 
 class TagDocumentForm(BaseModel):
     name: str
-    tags: List[dict]
+    tags: list[dict]
 
 
 @router.post("/doc/tags", response_model=Optional[DocumentResponse])

backend/apps/webui/routers/files.py

@@ -11,7 +11,7 @@ from fastapi import (
 
 
 from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from typing import Union, Optional
 from pathlib import Path
 
 from fastapi import APIRouter
@@ -104,7 +104,7 @@ def upload_file(file: UploadFile = File(...), user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/", response_model=List[FileModel])
+@router.get("/", response_model=list[FileModel])
 async def list_files(user=Depends(get_verified_user)):
     files = Files.get_files()
     return files

backend/apps/webui/routers/functions.py

@@ -1,6 +1,6 @@
 from fastapi import Depends, FastAPI, HTTPException, status, Request
 from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from typing import Union, Optional
 
 from fastapi import APIRouter
 from pydantic import BaseModel
@@ -30,7 +30,7 @@ router = APIRouter()
 ############################
 
 
-@router.get("/", response_model=List[FunctionResponse])
+@router.get("/", response_model=list[FunctionResponse])
 async def get_functions(user=Depends(get_verified_user)):
     return Functions.get_functions()
 
@@ -40,7 +40,7 @@ async def get_functions(user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/export", response_model=List[FunctionModel])
+@router.get("/export", response_model=list[FunctionModel])
 async def get_functions(user=Depends(get_admin_user)):
     return Functions.get_functions()
 
@@ -63,7 +63,7 @@ async def create_new_function(
     form_data.id = form_data.id.lower()
 
     function = Functions.get_function_by_id(form_data.id)
-    if function == None:
+    if function is None:
         function_path = os.path.join(FUNCTIONS_DIR, f"{form_data.id}.py")
         try:
             with open(function_path, "w") as function_file:
@@ -235,7 +235,7 @@ async def delete_function_by_id(
         function_path = os.path.join(FUNCTIONS_DIR, f"{id}.py")
         try:
             os.remove(function_path)
-        except:
+        except Exception:
             pass
 
     return result

backend/apps/webui/routers/memories.py

@@ -1,7 +1,7 @@
 from fastapi import Response, Request
 from fastapi import Depends, FastAPI, HTTPException, status
 from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from typing import Union, Optional
 
 from fastapi import APIRouter
 from pydantic import BaseModel
@@ -30,7 +30,7 @@ async def get_embeddings(request: Request):
 ############################
 
 
-@router.get("/", response_model=List[MemoryModel])
+@router.get("/", response_model=list[MemoryModel])
 async def get_memories(user=Depends(get_verified_user)):
     return Memories.get_memories_by_user_id(user.id)
 

backend/apps/webui/routers/models.py

@@ -1,6 +1,6 @@
 from fastapi import Depends, FastAPI, HTTPException, status, Request
 from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from typing import Union, Optional
 
 from fastapi import APIRouter
 from pydantic import BaseModel
@@ -18,7 +18,7 @@ router = APIRouter()
 ###########################
 
 
-@router.get("/", response_model=List[ModelResponse])
+@router.get("/", response_model=list[ModelResponse])
 async def get_models(user=Depends(get_verified_user)):
     return Models.get_all_models()
 

backend/apps/webui/routers/prompts.py

@@ -1,6 +1,6 @@
 from fastapi import Depends, FastAPI, HTTPException, status
 from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from typing import Union, Optional
 
 from fastapi import APIRouter
 from pydantic import BaseModel
@@ -18,7 +18,7 @@ router = APIRouter()
 ############################
 
 
-@router.get("/", response_model=List[PromptModel])
+@router.get("/", response_model=list[PromptModel])
 async def get_prompts(user=Depends(get_verified_user)):
     return Prompts.get_prompts()
 
@@ -31,7 +31,7 @@ async def get_prompts(user=Depends(get_verified_user)):
 @router.post("/create", response_model=Optional[PromptModel])
 async def create_new_prompt(form_data: PromptForm, user=Depends(get_admin_user)):
     prompt = Prompts.get_prompt_by_command(form_data.command)
-    if prompt == None:
+    if prompt is None:
         prompt = Prompts.insert_new_prompt(user.id, form_data)
 
         if prompt:

backend/apps/webui/routers/tools.py

@@ -1,12 +1,8 @@
-from fastapi import Depends, FastAPI, HTTPException, status, Request
-from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from fastapi import Depends, HTTPException, status, Request
+from typing import Optional
 
 from fastapi import APIRouter
-from pydantic import BaseModel
-import json
 
-from apps.webui.models.users import Users
 from apps.webui.models.tools import Tools, ToolForm, ToolModel, ToolResponse
 from apps.webui.utils import load_toolkit_module_by_id
 
@@ -14,7 +10,6 @@ from utils.utils import get_admin_user, get_verified_user
 from utils.tools import get_tools_specs
 from constants import ERROR_MESSAGES
 
-from importlib import util
 import os
 from pathlib import Path
 
@@ -32,7 +27,7 @@ router = APIRouter()
 ############################
 
 
-@router.get("/", response_model=List[ToolResponse])
+@router.get("/", response_model=list[ToolResponse])
 async def get_toolkits(user=Depends(get_verified_user)):
     toolkits = [toolkit for toolkit in Tools.get_tools()]
     return toolkits
@@ -43,7 +38,7 @@ async def get_toolkits(user=Depends(get_verified_user)):
 ############################
 
 
-@router.get("/export", response_model=List[ToolModel])
+@router.get("/export", response_model=list[ToolModel])
 async def get_toolkits(user=Depends(get_admin_user)):
     toolkits = [toolkit for toolkit in Tools.get_tools()]
     return toolkits
@@ -69,7 +64,7 @@ async def create_new_toolkit(
     form_data.id = form_data.id.lower()
 
     toolkit = Tools.get_tool_by_id(form_data.id)
-    if toolkit == None:
+    if toolkit is None:
         toolkit_path = os.path.join(TOOLS_DIR, f"{form_data.id}.py")
         try:
             with open(toolkit_path, "w") as tool_file:
@@ -98,7 +93,7 @@ async def create_new_toolkit(
             print(e)
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
-                detail=ERROR_MESSAGES.DEFAULT(e),
+                detail=ERROR_MESSAGES.DEFAULT(str(e)),
             )
     else:
         raise HTTPException(
@@ -170,7 +165,7 @@ async def update_toolkit_by_id(
     except Exception as e:
         raise HTTPException(
             status_code=status.HTTP_400_BAD_REQUEST,
-            detail=ERROR_MESSAGES.DEFAULT(e),
+            detail=ERROR_MESSAGES.DEFAULT(str(e)),
         )
 
 
@@ -210,7 +205,7 @@ async def get_toolkit_valves_by_id(id: str, user=Depends(get_admin_user)):
         except Exception as e:
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
-                detail=ERROR_MESSAGES.DEFAULT(e),
+                detail=ERROR_MESSAGES.DEFAULT(str(e)),
             )
     else:
         raise HTTPException(
@@ -233,7 +228,7 @@ async def get_toolkit_valves_spec_by_id(
         if id in request.app.state.TOOLS:
             toolkit_module = request.app.state.TOOLS[id]
         else:
-            toolkit_module, frontmatter = load_toolkit_module_by_id(id)
+            toolkit_module, _ = load_toolkit_module_by_id(id)
             request.app.state.TOOLS[id] = toolkit_module
 
         if hasattr(toolkit_module, "Valves"):
@@ -261,7 +256,7 @@ async def update_toolkit_valves_by_id(
         if id in request.app.state.TOOLS:
             toolkit_module = request.app.state.TOOLS[id]
         else:
-            toolkit_module, frontmatter = load_toolkit_module_by_id(id)
+            toolkit_module, _ = load_toolkit_module_by_id(id)
             request.app.state.TOOLS[id] = toolkit_module
 
         if hasattr(toolkit_module, "Valves"):
@@ -276,7 +271,7 @@ async def update_toolkit_valves_by_id(
                 print(e)
                 raise HTTPException(
                     status_code=status.HTTP_400_BAD_REQUEST,
-                    detail=ERROR_MESSAGES.DEFAULT(e),
+                    detail=ERROR_MESSAGES.DEFAULT(str(e)),
                 )
         else:
             raise HTTPException(
@@ -306,7 +301,7 @@ async def get_toolkit_user_valves_by_id(id: str, user=Depends(get_verified_user)
         except Exception as e:
             raise HTTPException(
                 status_code=status.HTTP_400_BAD_REQUEST,
-                detail=ERROR_MESSAGES.DEFAULT(e),
+                detail=ERROR_MESSAGES.DEFAULT(str(e)),
             )
     else:
         raise HTTPException(
@@ -324,7 +319,7 @@ async def get_toolkit_user_valves_spec_by_id(
         if id in request.app.state.TOOLS:
             toolkit_module = request.app.state.TOOLS[id]
         else:
-            toolkit_module, frontmatter = load_toolkit_module_by_id(id)
+            toolkit_module, _ = load_toolkit_module_by_id(id)
             request.app.state.TOOLS[id] = toolkit_module
 
         if hasattr(toolkit_module, "UserValves"):
@@ -348,7 +343,7 @@ async def update_toolkit_user_valves_by_id(
         if id in request.app.state.TOOLS:
             toolkit_module = request.app.state.TOOLS[id]
         else:
-            toolkit_module, frontmatter = load_toolkit_module_by_id(id)
+            toolkit_module, _ = load_toolkit_module_by_id(id)
             request.app.state.TOOLS[id] = toolkit_module
 
         if hasattr(toolkit_module, "UserValves"):
@@ -365,7 +360,7 @@ async def update_toolkit_user_valves_by_id(
                 print(e)
                 raise HTTPException(
                     status_code=status.HTTP_400_BAD_REQUEST,
-                    detail=ERROR_MESSAGES.DEFAULT(e),
+                    detail=ERROR_MESSAGES.DEFAULT(str(e)),
                 )
         else:
             raise HTTPException(

backend/apps/webui/routers/users.py

@@ -1,7 +1,7 @@
 from fastapi import Response, Request
 from fastapi import Depends, FastAPI, HTTPException, status
 from datetime import datetime, timedelta
-from typing import List, Union, Optional
+from typing import Union, Optional
 
 from fastapi import APIRouter
 from pydantic import BaseModel
@@ -39,7 +39,7 @@ router = APIRouter()
 ############################
 
 
-@router.get("/", response_model=List[UserModel])
+@router.get("/", response_model=list[UserModel])
 async def get_users(skip: int = 0, limit: int = 50, user=Depends(get_admin_user)):
     return Users.get_users(skip, limit)
 

backend/apps/webui/routers/utils.py

@@ -1,3 +1,6 @@
+from pathlib import Path
+import site
+
 from fastapi import APIRouter, UploadFile, File, Response
 from fastapi import Depends, HTTPException, status
 from starlette.responses import StreamingResponse, FileResponse
@@ -14,7 +17,7 @@ from utils.misc import calculate_sha256, get_gravatar_url
 
 from config import OLLAMA_BASE_URLS, DATA_DIR, UPLOAD_DIR, ENABLE_ADMIN_EXPORT
 from constants import ERROR_MESSAGES
-from typing import List
+
 
 router = APIRouter()
 
@@ -54,7 +57,7 @@ async def get_html_from_markdown(
 
 class ChatForm(BaseModel):
     title: str
-    messages: List[dict]
+    messages: list[dict]
 
 
 @router.post("/pdf")
@@ -64,8 +67,18 @@ async def download_chat_as_pdf(
     pdf = FPDF()
     pdf.add_page()
 
-    STATIC_DIR = "./static"
-    FONTS_DIR = f"{STATIC_DIR}/fonts"
+    # When running in docker, workdir is /app/backend, so fonts is in /app/backend/static/fonts
+    FONTS_DIR = Path("./static/fonts")
+
+    # Non Docker Installation
+
+    # When running using `pip install` the static directory is in the site packages.
+    if not FONTS_DIR.exists():
+        FONTS_DIR = Path(site.getsitepackages()[0]) / "static/fonts"
+    # When running using `pip install -e .` the static directory is in the site packages.
+    # This path only works if `open-webui serve` is run from the root of this project.
+    if not FONTS_DIR.exists():
+        FONTS_DIR = Path("./backend/static/fonts")
 
     pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf")
     pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf")

backend/apps/webui/utils.py

@@ -1,6 +1,8 @@
 from importlib import util
 import os
 import re
+import sys
+import subprocess
 
 from config import TOOLS_DIR, FUNCTIONS_DIR
 
@@ -52,6 +54,7 @@ def load_toolkit_module_by_id(toolkit_id):
     frontmatter = extract_frontmatter(toolkit_path)
 
     try:
+        install_frontmatter_requirements(frontmatter.get("requirements", ""))
         spec.loader.exec_module(module)
         print(f"Loaded module: {module.__name__}")
         if hasattr(module, "Tools"):
@@ -73,6 +76,7 @@ def load_function_module_by_id(function_id):
     frontmatter = extract_frontmatter(function_path)
 
     try:
+        install_frontmatter_requirements(frontmatter.get("requirements", ""))
         spec.loader.exec_module(module)
         print(f"Loaded module: {module.__name__}")
         if hasattr(module, "Pipe"):
@@ -88,3 +92,13 @@ def load_function_module_by_id(function_id):
         # Move the file to the error folder
         os.rename(function_path, f"{function_path}.error")
         raise e
+
+
+def install_frontmatter_requirements(requirements):
+    if requirements:
+        req_list = [req.strip() for req in requirements.split(",")]
+        for req in req_list:
+            print(f"Installing requirement: {req}")
+            subprocess.check_call([sys.executable, "-m", "pip", "install", req])
+    else:
+        print("No requirements found in frontmatter.")

backend/config.py

@@ -77,6 +77,16 @@ for source in log_sources:
 
 log.setLevel(SRC_LOG_LEVELS["CONFIG"])
 
+
+class EndpointFilter(logging.Filter):
+    def filter(self, record: logging.LogRecord) -> bool:
+        return record.getMessage().find("/health") == -1
+
+
+# Filter out /endpoint
+logging.getLogger("uvicorn.access").addFilter(EndpointFilter())
+
+
 WEBUI_NAME = os.environ.get("WEBUI_NAME", "Open WebUI")
 if WEBUI_NAME != "Open WebUI":
     WEBUI_NAME += " (Open WebUI)"
@@ -94,7 +104,7 @@ ENV = os.environ.get("ENV", "dev")
 
 try:
     PACKAGE_DATA = json.loads((BASE_DIR / "package.json").read_text())
-except:
+except Exception:
     try:
         PACKAGE_DATA = {"version": importlib.metadata.version("open-webui")}
     except importlib.metadata.PackageNotFoundError:
@@ -127,7 +137,7 @@ try:
     with open(str(changelog_path.absolute()), "r", encoding="utf8") as file:
         changelog_content = file.read()
 
-except:
+except Exception:
     changelog_content = (pkgutil.get_data("open_webui", "CHANGELOG.md") or b"").decode()
 
 
@@ -192,12 +202,12 @@ if RESET_CONFIG_ON_START:
         os.remove(f"{DATA_DIR}/config.json")
         with open(f"{DATA_DIR}/config.json", "w") as f:
             f.write("{}")
-    except:
+    except Exception:
         pass
 
 try:
     CONFIG_DATA = json.loads((DATA_DIR / "config.json").read_text())
-except:
+except Exception:
     CONFIG_DATA = {}
 
 
@@ -339,6 +349,12 @@ GOOGLE_OAUTH_SCOPE = PersistentConfig(
     os.environ.get("GOOGLE_OAUTH_SCOPE", "openid email profile"),
 )
 
+GOOGLE_REDIRECT_URI = PersistentConfig(
+    "GOOGLE_REDIRECT_URI",
+    "oauth.google.redirect_uri",
+    os.environ.get("GOOGLE_REDIRECT_URI", ""),
+)
+
 MICROSOFT_CLIENT_ID = PersistentConfig(
     "MICROSOFT_CLIENT_ID",
     "oauth.microsoft.client_id",
@@ -363,6 +379,12 @@ MICROSOFT_OAUTH_SCOPE = PersistentConfig(
     os.environ.get("MICROSOFT_OAUTH_SCOPE", "openid email profile"),
 )
 
+MICROSOFT_REDIRECT_URI = PersistentConfig(
+    "MICROSOFT_REDIRECT_URI",
+    "oauth.microsoft.redirect_uri",
+    os.environ.get("MICROSOFT_REDIRECT_URI", ""),
+)
+
 OAUTH_CLIENT_ID = PersistentConfig(
     "OAUTH_CLIENT_ID",
     "oauth.oidc.client_id",
@@ -381,6 +403,12 @@ OPENID_PROVIDER_URL = PersistentConfig(
     os.environ.get("OPENID_PROVIDER_URL", ""),
 )
 
+OPENID_REDIRECT_URI = PersistentConfig(
+    "OPENID_REDIRECT_URI",
+    "oauth.oidc.redirect_uri",
+    os.environ.get("OPENID_REDIRECT_URI", ""),
+)
+
 OAUTH_SCOPES = PersistentConfig(
     "OAUTH_SCOPES",
     "oauth.oidc.scopes",
@@ -405,6 +433,12 @@ OAUTH_PICTURE_CLAIM = PersistentConfig(
     os.environ.get("OAUTH_PICTURE_CLAIM", "picture"),
 )
 
+OAUTH_EMAIL_CLAIM = PersistentConfig(
+    "OAUTH_EMAIL_CLAIM",
+    "oauth.oidc.email_claim",
+    os.environ.get("OAUTH_EMAIL_CLAIM", "email"),
+)
+
 
 def load_oauth_providers():
     OAUTH_PROVIDERS.clear()
@@ -414,6 +448,7 @@ def load_oauth_providers():
             "client_secret": GOOGLE_CLIENT_SECRET.value,
             "server_metadata_url": "https://accounts.google.com/.well-known/openid-configuration",
             "scope": GOOGLE_OAUTH_SCOPE.value,
+            "redirect_uri": GOOGLE_REDIRECT_URI.value,
         }
 
     if (
@@ -426,6 +461,7 @@ def load_oauth_providers():
             "client_secret": MICROSOFT_CLIENT_SECRET.value,
             "server_metadata_url": f"https://login.microsoftonline.com/{MICROSOFT_CLIENT_TENANT_ID.value}/v2.0/.well-known/openid-configuration",
             "scope": MICROSOFT_OAUTH_SCOPE.value,
+            "redirect_uri": MICROSOFT_REDIRECT_URI.value,
         }
 
     if (
@@ -439,6 +475,7 @@ def load_oauth_providers():
             "server_metadata_url": OPENID_PROVIDER_URL.value,
             "scope": OAUTH_SCOPES.value,
             "name": OAUTH_PROVIDER_NAME.value,
+            "redirect_uri": OPENID_REDIRECT_URI.value,
         }
 
 
@@ -610,7 +647,7 @@ if AIOHTTP_CLIENT_TIMEOUT == "":
 else:
     try:
         AIOHTTP_CLIENT_TIMEOUT = int(AIOHTTP_CLIENT_TIMEOUT)
-    except:
+    except Exception:
         AIOHTTP_CLIENT_TIMEOUT = 300
 
 
@@ -690,7 +727,7 @@ try:
     OPENAI_API_KEY = OPENAI_API_KEYS.value[
         OPENAI_API_BASE_URLS.value.index("https://api.openai.com/v1")
     ]
-except:
+except Exception:
     pass
 
 OPENAI_API_BASE_URL = "https://api.openai.com/v1"
@@ -709,6 +746,12 @@ ENABLE_SIGNUP = PersistentConfig(
     ),
 )
 
+ENABLE_LOGIN_FORM = PersistentConfig(
+    "ENABLE_LOGIN_FORM",
+    "ui.ENABLE_LOGIN_FORM",
+    os.environ.get("ENABLE_LOGIN_FORM", "True").lower() == "true",
+)
+
 DEFAULT_LOCALE = PersistentConfig(
     "DEFAULT_LOCALE",
     "ui.default_locale",
@@ -787,6 +830,10 @@ WEBHOOK_URL = PersistentConfig(
 
 ENABLE_ADMIN_EXPORT = os.environ.get("ENABLE_ADMIN_EXPORT", "True").lower() == "true"
 
+ENABLE_ADMIN_CHAT_ACCESS = (
+    os.environ.get("ENABLE_ADMIN_CHAT_ACCESS", "True").lower() == "true"
+)
+
 ENABLE_COMMUNITY_SHARING = PersistentConfig(
     "ENABLE_COMMUNITY_SHARING",
     "ui.enable_community_sharing",
@@ -996,7 +1043,7 @@ RAG_EMBEDDING_MODEL = PersistentConfig(
     "rag.embedding_model",
     os.environ.get("RAG_EMBEDDING_MODEL", "sentence-transformers/all-MiniLM-L6-v2"),
 )
-log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL.value}"),
+log.info(f"Embedding model set: {RAG_EMBEDDING_MODEL.value}")
 
 RAG_EMBEDDING_MODEL_AUTO_UPDATE = (
     os.environ.get("RAG_EMBEDDING_MODEL_AUTO_UPDATE", "").lower() == "true"
@@ -1018,7 +1065,7 @@ RAG_RERANKING_MODEL = PersistentConfig(
     os.environ.get("RAG_RERANKING_MODEL", ""),
 )
 if RAG_RERANKING_MODEL.value != "":
-    log.info(f"Reranking model set: {RAG_RERANKING_MODEL.value}"),
+    log.info(f"Reranking model set: {RAG_RERANKING_MODEL.value}")
 
 RAG_RERANKING_MODEL_AUTO_UPDATE = (
     os.environ.get("RAG_RERANKING_MODEL_AUTO_UPDATE", "").lower() == "true"
@@ -1265,6 +1312,24 @@ COMFYUI_SD3 = PersistentConfig(
     os.environ.get("COMFYUI_SD3", "").lower() == "true",
 )
 
+COMFYUI_FLUX = PersistentConfig(
+    "COMFYUI_FLUX",
+    "image_generation.comfyui.flux",
+    os.environ.get("COMFYUI_FLUX", "").lower() == "true",
+)
+
+COMFYUI_FLUX_WEIGHT_DTYPE = PersistentConfig(
+    "COMFYUI_FLUX_WEIGHT_DTYPE",
+    "image_generation.comfyui.flux_weight_dtype",
+    os.getenv("COMFYUI_FLUX_WEIGHT_DTYPE", ""),
+)
+
+COMFYUI_FLUX_FP8_CLIP = PersistentConfig(
+    "COMFYUI_FLUX_FP8_CLIP",
+    "image_generation.comfyui.flux_fp8_clip",
+    os.environ.get("COMFYUI_FLUX_FP8_CLIP", "").lower() == "true",
+)
+
 IMAGES_OPENAI_API_BASE_URL = PersistentConfig(
     "IMAGES_OPENAI_API_BASE_URL",
     "image_generation.openai.api_base_url",
@@ -1329,6 +1394,11 @@ AUDIO_TTS_OPENAI_API_KEY = PersistentConfig(
     os.getenv("AUDIO_TTS_OPENAI_API_KEY", OPENAI_API_KEY),
 )
 
+AUDIO_TTS_API_KEY = PersistentConfig(
+    "AUDIO_TTS_API_KEY",
+    "audio.tts.api_key",
+    os.getenv("AUDIO_TTS_API_KEY", ""),
+)
 
 AUDIO_TTS_ENGINE = PersistentConfig(
     "AUDIO_TTS_ENGINE",

backend/main.py

@@ -13,8 +13,6 @@ import aiohttp
 import requests
 import mimetypes
 import shutil
-import os
-import uuid
 import inspect
 
 from fastapi import FastAPI, Request, Depends, status, UploadFile, File, Form
@@ -29,7 +27,7 @@ from starlette.middleware.sessions import SessionMiddleware
 from starlette.responses import StreamingResponse, Response, RedirectResponse
 
 
-from apps.socket.main import sio, app as socket_app, get_event_emitter, get_event_call
+from apps.socket.main import app as socket_app, get_event_emitter, get_event_call
 from apps.ollama.main import (
     app as ollama_app,
     get_all_models as get_ollama_models,
@@ -53,7 +51,7 @@ from apps.webui.internal.db import Session
 
 
 from pydantic import BaseModel
-from typing import List, Optional
+from typing import Optional
 
 from apps.webui.models.auths import Auths
 from apps.webui.models.models import Models
@@ -79,6 +77,7 @@ from utils.task import (
 from utils.misc import (
     get_last_user_message,
     add_or_update_system_message,
+    prepend_to_first_user_message_content,
     parse_duration,
 )
 
@@ -117,6 +116,7 @@ from config import (
     WEBUI_SECRET_KEY,
     WEBUI_SESSION_COOKIE_SAME_SITE,
     WEBUI_SESSION_COOKIE_SECURE,
+    ENABLE_ADMIN_CHAT_ACCESS,
     AppConfig,
 )
 
@@ -618,32 +618,15 @@ class ChatCompletionMiddleware(BaseHTTPMiddleware):
                     content={"detail": str(e)},
                 )
 
-            # Extract valves from the request body
-            valves = None
-            if "valves" in body:
-                valves = body["valves"]
-                del body["valves"]
+            metadata = {
+                "chat_id": body.pop("chat_id", None),
+                "message_id": body.pop("id", None),
+                "session_id": body.pop("session_id", None),
+                "valves": body.pop("valves", None),
+            }
 
-            # Extract session_id, chat_id and message_id from the request body
-            session_id = None
-            if "session_id" in body:
-                session_id = body["session_id"]
-                del body["session_id"]
-            chat_id = None
-            if "chat_id" in body:
-                chat_id = body["chat_id"]
-                del body["chat_id"]
-            message_id = None
-            if "id" in body:
-                message_id = body["id"]
-                del body["id"]
-
-            __event_emitter__ = await get_event_emitter(
-                {"chat_id": chat_id, "message_id": message_id, "session_id": session_id}
-            )
-            __event_call__ = await get_event_call(
-                {"chat_id": chat_id, "message_id": message_id, "session_id": session_id}
-            )
+            __event_emitter__ = get_event_emitter(metadata)
+            __event_call__ = get_event_call(metadata)
 
             # Initialize data_items to store additional data to be sent to the client
             data_items = []
@@ -686,24 +669,29 @@ class ChatCompletionMiddleware(BaseHTTPMiddleware):
             if len(contexts) > 0:
                 context_string = "/n".join(contexts).strip()
                 prompt = get_last_user_message(body["messages"])
-                body["messages"] = add_or_update_system_message(
-                    rag_template(
-                        rag_app.state.config.RAG_TEMPLATE, context_string, prompt
-                    ),
-                    body["messages"],
-                )
+
+                # Workaround for Ollama 2.0+ system prompt issue
+                # TODO: replace with add_or_update_system_message
+                if model["owned_by"] == "ollama":
+                    body["messages"] = prepend_to_first_user_message_content(
+                        rag_template(
+                            rag_app.state.config.RAG_TEMPLATE, context_string, prompt
+                        ),
+                        body["messages"],
+                    )
+                else:
+                    body["messages"] = add_or_update_system_message(
+                        rag_template(
+                            rag_app.state.config.RAG_TEMPLATE, context_string, prompt
+                        ),
+                        body["messages"],
+                    )
 
             # If there are citations, add them to the data_items
             if len(citations) > 0:
                 data_items.append({"citations": citations})
 
-            body["metadata"] = {
-                "session_id": session_id,
-                "chat_id": chat_id,
-                "message_id": message_id,
-                "valves": valves,
-            }
-
+            body["metadata"] = metadata
             modified_body_bytes = json.dumps(body).encode("utf-8")
             # Replace the request body with the modified one
             request._body = modified_body_bytes
@@ -970,7 +958,7 @@ async def get_all_models():
 
     custom_models = Models.get_all_models()
     for custom_model in custom_models:
-        if custom_model.base_model_id == None:
+        if custom_model.base_model_id is None:
             for model in models:
                 if (
                     custom_model.id == model["id"]
@@ -979,32 +967,15 @@ async def get_all_models():
                     model["name"] = custom_model.name
                     model["info"] = custom_model.model_dump()
 
-                    action_ids = [] + global_action_ids
+                    action_ids = []
                     if "info" in model and "meta" in model["info"]:
                         action_ids.extend(model["info"]["meta"].get("actionIds", []))
-                        action_ids = list(set(action_ids))
-                    action_ids = [
-                        action_id
-                        for action_id in action_ids
-                        if action_id in enabled_action_ids
-                    ]
-
-                    model["actions"] = []
-                    for action_id in action_ids:
-                        action = Functions.get_function_by_id(action_id)
-                        model["actions"].append(
-                            {
-                                "id": action_id,
-                                "name": action.name,
-                                "description": action.meta.description,
-                                "icon_url": action.meta.manifest.get("icon_url", None),
-                            }
-                        )
 
+                    model["action_ids"] = action_ids
         else:
             owned_by = "openai"
             pipe = None
-            actions = []
+            action_ids = []
 
             for model in models:
                 if (
@@ -1015,26 +986,8 @@ async def get_all_models():
                     if "pipe" in model:
                         pipe = model["pipe"]
 
-                    action_ids = [] + global_action_ids
                     if "info" in model and "meta" in model["info"]:
                         action_ids.extend(model["info"]["meta"].get("actionIds", []))
-                        action_ids = list(set(action_ids))
-                    action_ids = [
-                        action_id
-                        for action_id in action_ids
-                        if action_id in enabled_action_ids
-                    ]
-
-                    actions = [
-                        {
-                            "id": action_id,
-                            "name": Functions.get_function_by_id(action_id).name,
-                            "description": Functions.get_function_by_id(
-                                action_id
-                            ).meta.description,
-                        }
-                        for action_id in action_ids
-                    ]
                     break
 
             models.append(
@@ -1047,10 +1000,59 @@ async def get_all_models():
                     "info": custom_model.model_dump(),
                     "preset": True,
                     **({"pipe": pipe} if pipe is not None else {}),
-                    "actions": actions,
+                    "action_ids": action_ids,
                 }
             )
 
+    for model in models:
+        action_ids = []
+        if "action_ids" in model:
+            action_ids = model["action_ids"]
+            del model["action_ids"]
+
+        action_ids = action_ids + global_action_ids
+        action_ids = list(set(action_ids))
+        action_ids = [
+            action_id for action_id in action_ids if action_id in enabled_action_ids
+        ]
+
+        model["actions"] = []
+        for action_id in action_ids:
+            action = Functions.get_function_by_id(action_id)
+
+            if action_id in webui_app.state.FUNCTIONS:
+                function_module = webui_app.state.FUNCTIONS[action_id]
+            else:
+                function_module, _, _ = load_function_module_by_id(action_id)
+                webui_app.state.FUNCTIONS[action_id] = function_module
+
+            if hasattr(function_module, "actions"):
+                actions = function_module.actions
+                model["actions"].extend(
+                    [
+                        {
+                            "id": f"{action_id}.{_action['id']}",
+                            "name": _action.get(
+                                "name", f"{action.name} ({_action['id']})"
+                            ),
+                            "description": action.meta.description,
+                            "icon_url": _action.get(
+                                "icon_url", action.meta.manifest.get("icon_url", None)
+                            ),
+                        }
+                        for _action in actions
+                    ]
+                )
+            else:
+                model["actions"].append(
+                    {
+                        "id": action_id,
+                        "name": action.name,
+                        "description": action.meta.description,
+                        "icon_url": action.meta.manifest.get("icon_url", None),
+                    }
+                )
+
     app.state.MODELS = {model["id"]: model for model in models}
     webui_app.state.MODELS = app.state.MODELS
 
@@ -1165,13 +1167,13 @@ async def chat_completed(form_data: dict, user=Depends(get_verified_user)):
                             status_code=r.status_code,
                             content=res,
                         )
-                except:
+                except Exception:
                     pass
 
             else:
                 pass
 
-    __event_emitter__ = await get_event_emitter(
+    __event_emitter__ = get_event_emitter(
         {
             "chat_id": data["chat_id"],
             "message_id": data["id"],
@@ -1179,7 +1181,7 @@ async def chat_completed(form_data: dict, user=Depends(get_verified_user)):
         }
     )
 
-    __event_call__ = await get_event_call(
+    __event_call__ = get_event_call(
         {
             "chat_id": data["chat_id"],
             "message_id": data["id"],
@@ -1284,9 +1286,12 @@ async def chat_completed(form_data: dict, user=Depends(get_verified_user)):
 
 
 @app.post("/api/chat/actions/{action_id}")
-async def chat_completed(
-    action_id: str, form_data: dict, user=Depends(get_verified_user)
-):
+async def chat_action(action_id: str, form_data: dict, user=Depends(get_verified_user)):
+    if "." in action_id:
+        action_id, sub_action_id = action_id.split(".")
+    else:
+        sub_action_id = None
+
     action = Functions.get_function_by_id(action_id)
     if not action:
         raise HTTPException(
@@ -1303,14 +1308,14 @@ async def chat_completed(
         )
     model = app.state.MODELS[model_id]
 
-    __event_emitter__ = await get_event_emitter(
+    __event_emitter__ = get_event_emitter(
         {
             "chat_id": data["chat_id"],
             "message_id": data["id"],
             "session_id": data["session_id"],
         }
     )
-    __event_call__ = await get_event_call(
+    __event_call__ = get_event_call(
         {
             "chat_id": data["chat_id"],
             "message_id": data["id"],
@@ -1339,7 +1344,7 @@ async def chat_completed(
             # Extra parameters to be passed to the function
             extra_params = {
                 "__model__": model,
-                "__id__": action_id,
+                "__id__": sub_action_id if sub_action_id is not None else action_id,
                 "__event_emitter__": __event_emitter__,
                 "__event_call__": __event_call__,
             }
@@ -1658,7 +1663,7 @@ async def get_pipelines_list(user=Depends(get_admin_user)):
     urlIdxs = [
         idx
         for idx, response in enumerate(responses)
-        if response != None and "pipelines" in response
+        if response is not None and "pipelines" in response
     ]
 
     return {
@@ -1719,7 +1724,7 @@ async def upload_pipeline(
                 res = r.json()
                 if "detail" in res:
                     detail = res["detail"]
-            except:
+            except Exception:
                 pass
 
         raise HTTPException(
@@ -1739,7 +1744,6 @@ class AddPipelineForm(BaseModel):
 
 @app.post("/api/pipelines/add")
 async def add_pipeline(form_data: AddPipelineForm, user=Depends(get_admin_user)):
-
     r = None
     try:
         urlIdx = form_data.urlIdx
@@ -1766,7 +1770,7 @@ async def add_pipeline(form_data: AddPipelineForm, user=Depends(get_admin_user))
                 res = r.json()
                 if "detail" in res:
                     detail = res["detail"]
-            except:
+            except Exception:
                 pass
 
         raise HTTPException(
@@ -1782,7 +1786,6 @@ class DeletePipelineForm(BaseModel):
 
 @app.delete("/api/pipelines/delete")
 async def delete_pipeline(form_data: DeletePipelineForm, user=Depends(get_admin_user)):
-
     r = None
     try:
         urlIdx = form_data.urlIdx
@@ -1809,7 +1812,7 @@ async def delete_pipeline(form_data: DeletePipelineForm, user=Depends(get_admin_
                 res = r.json()
                 if "detail" in res:
                     detail = res["detail"]
-            except:
+            except Exception:
                 pass
 
         raise HTTPException(
@@ -1842,7 +1845,7 @@ async def get_pipelines(urlIdx: Optional[int] = None, user=Depends(get_admin_use
                 res = r.json()
                 if "detail" in res:
                     detail = res["detail"]
-            except:
+            except Exception:
                 pass
 
         raise HTTPException(
@@ -1857,10 +1860,8 @@ async def get_pipeline_valves(
     pipeline_id: str,
     user=Depends(get_admin_user),
 ):
-    models = await get_all_models()
     r = None
     try:
-
         url = openai_app.state.config.OPENAI_API_BASE_URLS[urlIdx]
         key = openai_app.state.config.OPENAI_API_KEYS[urlIdx]
 
@@ -1882,7 +1883,7 @@ async def get_pipeline_valves(
                 res = r.json()
                 if "detail" in res:
                     detail = res["detail"]
-            except:
+            except Exception:
                 pass
 
         raise HTTPException(
@@ -1897,8 +1898,6 @@ async def get_pipeline_valves_spec(
     pipeline_id: str,
     user=Depends(get_admin_user),
 ):
-    models = await get_all_models()
-
     r = None
     try:
         url = openai_app.state.config.OPENAI_API_BASE_URLS[urlIdx]
@@ -1921,7 +1920,7 @@ async def get_pipeline_valves_spec(
                 res = r.json()
                 if "detail" in res:
                     detail = res["detail"]
-            except:
+            except Exception:
                 pass
 
         raise HTTPException(
@@ -1937,8 +1936,6 @@ async def update_pipeline_valves(
     form_data: dict,
     user=Depends(get_admin_user),
 ):
-    models = await get_all_models()
-
     r = None
     try:
         url = openai_app.state.config.OPENAI_API_BASE_URLS[urlIdx]
@@ -1966,7 +1963,7 @@ async def update_pipeline_valves(
                 res = r.json()
                 if "detail" in res:
                     detail = res["detail"]
-            except:
+            except Exception:
                 pass
 
         raise HTTPException(
@@ -1995,10 +1992,12 @@ async def get_app_config():
             "auth": WEBUI_AUTH,
             "auth_trusted_header": bool(webui_app.state.AUTH_TRUSTED_EMAIL_HEADER),
             "enable_signup": webui_app.state.config.ENABLE_SIGNUP,
+            "enable_login_form": webui_app.state.config.ENABLE_LOGIN_FORM,
             "enable_web_search": rag_app.state.config.ENABLE_RAG_WEB_SEARCH,
             "enable_image_generation": images_app.state.config.ENABLED,
             "enable_community_sharing": webui_app.state.config.ENABLE_COMMUNITY_SHARING,
             "enable_admin_export": ENABLE_ADMIN_EXPORT,
+            "enable_admin_chat_access": ENABLE_ADMIN_CHAT_ACCESS,
         },
         "audio": {
             "tts": {
@@ -2028,7 +2027,7 @@ async def get_model_filter_config(user=Depends(get_admin_user)):
 
 class ModelFilterConfigForm(BaseModel):
     enabled: bool
-    models: List[str]
+    models: list[str]
 
 
 @app.post("/api/config/model/filter")
@@ -2066,7 +2065,7 @@ async def update_webhook_url(form_data: UrlForm, user=Depends(get_admin_user)):
 
 
 @app.get("/api/version")
-async def get_app_config():
+async def get_app_version():
     return {
         "version": VERSION,
     }
@@ -2089,7 +2088,7 @@ async def get_app_latest_release_version():
                 latest_version = data["tag_name"]
 
                 return {"current": VERSION, "latest": latest_version[1:]}
-    except aiohttp.ClientError as e:
+    except aiohttp.ClientError:
         raise HTTPException(
             status_code=status.HTTP_503_SERVICE_UNAVAILABLE,
             detail=ERROR_MESSAGES.RATE_LIMIT_EXCEEDED,
@@ -2111,6 +2110,7 @@ for provider_name, provider_config in OAUTH_PROVIDERS.items():
         client_kwargs={
             "scope": provider_config["scope"],
         },
+        redirect_uri=provider_config["redirect_uri"],
     )
 
 # SessionMiddleware is used by authlib for oauth
@@ -2128,7 +2128,10 @@ if len(OAUTH_PROVIDERS) > 0:
 async def oauth_login(provider: str, request: Request):
     if provider not in OAUTH_PROVIDERS:
         raise HTTPException(404)
-    redirect_uri = request.url_for("oauth_callback", provider=provider)
+    # If the provider has a custom redirect URL, use that, otherwise automatically generate one
+    redirect_uri = OAUTH_PROVIDERS[provider].get("redirect_uri") or request.url_for(
+        "oauth_callback", provider=provider
+    )
     return await oauth.create_client(provider).authorize_redirect(request, redirect_uri)
 
 
@@ -2155,7 +2158,8 @@ async def oauth_callback(provider: str, request: Request, response: Response):
         log.warning(f"OAuth callback failed, sub is missing: {user_data}")
         raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED)
     provider_sub = f"{provider}@{sub}"
-    email = user_data.get("email", "").lower()
+    email_claim = webui_app.state.config.OAUTH_EMAIL_CLAIM
+    email = user_data.get(email_claim, "").lower()
     # We currently mandate that email addresses are provided
     if not email:
         log.warning(f"OAuth callback failed, email is missing: {user_data}")

backend/requirements.txt

@@ -11,7 +11,8 @@ python-jose==3.3.0
 passlib[bcrypt]==1.7.4
 
 requests==2.32.3
-aiohttp==3.9.5
+aiohttp==3.10.2
+
 sqlalchemy==2.0.31
 alembic==1.13.2
 peewee==3.17.6
@@ -19,10 +20,10 @@ peewee-migrate==1.12.2
 psycopg2-binary==2.9.9
 PyMySQL==1.1.1
 bcrypt==4.1.3
-SQLAlchemy
+
 pymongo
 redis
-boto3==1.34.110
+boto3==1.34.153
 
 argon2-cffi==23.1.0
 APScheduler==3.10.4
@@ -30,50 +31,50 @@ APScheduler==3.10.4
 # AI libraries
 openai
 anthropic
-google-generativeai==0.5.4
+google-generativeai==0.7.2
 tiktoken
 
-langchain==0.2.6
-langchain-community==0.2.6
+langchain==0.2.12
+langchain-community==0.2.10
 langchain-chroma==0.1.2
 
 fake-useragent==1.5.1
-chromadb==0.5.4
+chromadb==0.5.5
 sentence-transformers==3.0.1
-pypdf==4.2.0
+pypdf==4.3.1
 docx2txt==0.8
-python-pptx==0.6.23
-unstructured==0.14.10
+python-pptx==1.0.0
+unstructured==0.15.0
 Markdown==3.6
 pypandoc==1.13
 pandas==2.2.2
 openpyxl==3.1.5
 pyxlsb==1.0.10
 xlrd==2.0.1
-validators==0.28.1
+validators==0.33.0
 psutil
 
 opencv-python-headless==4.10.0.84
-rapidocr-onnxruntime==1.3.22
+rapidocr-onnxruntime==1.3.24
 
 fpdf2==2.7.9
 rank-bm25==0.2.2
 
 faster-whisper==1.0.2
 
-PyJWT[crypto]==2.8.0
+PyJWT[crypto]==2.9.0
 authlib==1.3.1
 
-black==24.4.2
-langfuse==2.38.0
+black==24.8.0
+langfuse==2.43.3
 youtube-transcript-api==0.6.2
 pytube==15.0.0
 
 extract_msg
 pydub
-duckduckgo-search~=6.1.12
+duckduckgo-search~=6.2.1
 
 ## Tests
 docker~=7.1.0
-pytest~=8.2.2
+pytest~=8.3.2
 pytest-docker~=3.1.1

backend/start.sh

@@ -30,7 +30,6 @@ if [[ "${USE_CUDA_DOCKER,,}" == "true" ]]; then
   export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/usr/local/lib/python3.11/site-packages/torch/lib:/usr/local/lib/python3.11/site-packages/nvidia/cudnn/lib"
 fi
 
-
 # Check if SPACE_ID is set, if so, configure for space
 if [ -n "$SPACE_ID" ]; then
   echo "Configuring for HuggingFace Space deployment"

backend/utils/misc.py

@@ -1,59 +1,77 @@
 from pathlib import Path
 import hashlib
-import json
 import re
 from datetime import timedelta
-from typing import Optional, List, Tuple
+from typing import Optional, Callable
 import uuid
 import time
 
+from utils.task import prompt_template
 
-def get_last_user_message_item(messages: List[dict]) -> str:
+
+def get_last_user_message_item(messages: list[dict]) -> Optional[dict]:
     for message in reversed(messages):
         if message["role"] == "user":
             return message
     return None
 
 
-def get_last_user_message(messages: List[dict]) -> str:
-    message = get_last_user_message_item(messages)
-
-    if message is not None:
-        if isinstance(message["content"], list):
-            for item in message["content"]:
-                if item["type"] == "text":
-                    return item["text"]
+def get_content_from_message(message: dict) -> Optional[str]:
+    if isinstance(message["content"], list):
+        for item in message["content"]:
+            if item["type"] == "text":
+                return item["text"]
+    else:
         return message["content"]
     return None
 
 
-def get_last_assistant_message(messages: List[dict]) -> str:
+def get_last_user_message(messages: list[dict]) -> Optional[str]:
+    message = get_last_user_message_item(messages)
+    if message is None:
+        return None
+
+    return get_content_from_message(message)
+
+
+def get_last_assistant_message(messages: list[dict]) -> Optional[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 get_content_from_message(message)
     return None
 
 
-def get_system_message(messages: List[dict]) -> dict:
+def get_system_message(messages: list[dict]) -> Optional[dict]:
     for message in messages:
         if message["role"] == "system":
             return message
     return None
 
 
-def remove_system_message(messages: List[dict]) -> List[dict]:
+def remove_system_message(messages: list[dict]) -> list[dict]:
     return [message for message in messages if message["role"] != "system"]
 
 
-def pop_system_message(messages: List[dict]) -> Tuple[dict, List[dict]]:
+def pop_system_message(messages: list[dict]) -> tuple[Optional[dict], list[dict]]:
     return get_system_message(messages), remove_system_message(messages)
 
 
-def add_or_update_system_message(content: str, messages: List[dict]):
+def prepend_to_first_user_message_content(
+    content: str, messages: list[dict]
+) -> list[dict]:
+    for message in messages:
+        if message["role"] == "user":
+            if isinstance(message["content"], list):
+                for item in message["content"]:
+                    if item["type"] == "text":
+                        item["text"] = f"{content}\n{item['text']}"
+            else:
+                message["content"] = f"{content}\n{message['content']}"
+            break
+    return messages
+
+
+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.
@@ -72,23 +90,112 @@ def add_or_update_system_message(content: str, messages: List[dict]):
     return messages
 
 
-def stream_message_template(model: str, message: str):
+def openai_chat_message_template(model: str):
     return {
         "id": f"{model}-{str(uuid.uuid4())}",
-        "object": "chat.completion.chunk",
         "created": int(time.time()),
         "model": model,
-        "choices": [
-            {
-                "index": 0,
-                "delta": {"content": message},
-                "logprobs": None,
-                "finish_reason": None,
-            }
-        ],
+        "choices": [{"index": 0, "logprobs": None, "finish_reason": None}],
     }
 
 
+def openai_chat_chunk_message_template(model: str, message: str) -> dict:
+    template = openai_chat_message_template(model)
+    template["object"] = "chat.completion.chunk"
+    template["choices"][0]["delta"] = {"content": message}
+    return template
+
+
+def openai_chat_completion_message_template(model: str, message: str) -> dict:
+    template = openai_chat_message_template(model)
+    template["object"] = "chat.completion"
+    template["choices"][0]["message"] = {"content": message, "role": "assistant"}
+    template["choices"][0]["finish_reason"] = "stop"
+    return template
+
+
+# inplace function: form_data is modified
+def apply_model_system_prompt_to_body(params: dict, form_data: dict, user) -> dict:
+    system = params.get("system", None)
+    if not system:
+        return form_data
+
+    if user:
+        template_params = {
+            "user_name": user.name,
+            "user_location": user.info.get("location") if user.info else None,
+        }
+    else:
+        template_params = {}
+    system = prompt_template(system, **template_params)
+    form_data["messages"] = add_or_update_system_message(
+        system, form_data.get("messages", [])
+    )
+    return form_data
+
+
+# inplace function: form_data is modified
+def apply_model_params_to_body(
+    params: dict, form_data: dict, mappings: dict[str, Callable]
+) -> dict:
+    if not params:
+        return form_data
+
+    for key, cast_func in mappings.items():
+        if (value := params.get(key)) is not None:
+            form_data[key] = cast_func(value)
+
+    return form_data
+
+
+# inplace function: form_data is modified
+def apply_model_params_to_body_openai(params: dict, form_data: dict) -> dict:
+    mappings = {
+        "temperature": float,
+        "top_p": int,
+        "max_tokens": int,
+        "frequency_penalty": int,
+        "seed": lambda x: x,
+        "stop": lambda x: [bytes(s, "utf-8").decode("unicode_escape") for s in x],
+    }
+    return apply_model_params_to_body(params, form_data, mappings)
+
+
+def apply_model_params_to_body_ollama(params: dict, form_data: dict) -> dict:
+    opts = [
+        "temperature",
+        "top_p",
+        "seed",
+        "mirostat",
+        "mirostat_eta",
+        "mirostat_tau",
+        "num_ctx",
+        "num_batch",
+        "num_keep",
+        "repeat_last_n",
+        "tfs_z",
+        "top_k",
+        "min_p",
+        "use_mmap",
+        "use_mlock",
+        "num_thread",
+        "num_gpu",
+    ]
+    mappings = {i: lambda x: x for i in opts}
+    form_data = apply_model_params_to_body(params, form_data, mappings)
+
+    name_differences = {
+        "max_tokens": "num_predict",
+        "frequency_penalty": "repeat_penalty",
+    }
+
+    for key, value in name_differences.items():
+        if (param := params.get(key, None)) is not None:
+            form_data[value] = param
+
+    return form_data
+
+
 def get_gravatar_url(email):
     # Trim leading and trailing whitespace from
     # an email address and force all characters
@@ -159,7 +266,7 @@ def extract_folders_after_data_docs(path):
     tags = []
 
     folders = parts[index_docs:-1]
-    for idx, part in enumerate(folders):
+    for idx, _ in enumerate(folders):
         tags.append("/".join(folders[: idx + 1]))
 
     return tags
@@ -255,11 +362,11 @@ def parse_ollama_modelfile(model_text):
             value = param_match.group(1)
 
             try:
-                if param_type == int:
+                if param_type is int:
                     value = int(value)
-                elif param_type == float:
+                elif param_type is float:
                     value = float(value)
-                elif param_type == bool:
+                elif param_type is bool:
                     value = value.lower() == "true"
             except Exception as e:
                 print(e)

backend/utils/task.py

@@ -6,7 +6,7 @@ from typing import Optional
 
 
 def prompt_template(
-    template: str, user_name: str = None, user_location: str = None
+    template: str, user_name: Optional[str] = None, user_location: Optional[str] = None
 ) -> str:
     # Get the current date
     current_date = datetime.now()
@@ -83,7 +83,6 @@ def title_generation_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)

backend/utils/tools.py

@@ -1,5 +1,5 @@
 import inspect
-from typing import get_type_hints, List, Dict, Any
+from typing import get_type_hints
 
 
 def doc_to_dict(docstring):
@@ -16,7 +16,7 @@ def doc_to_dict(docstring):
     return ret_dict
 
 
-def get_tools_specs(tools) -> List[dict]:
+def get_tools_specs(tools) -> list[dict]:
     function_list = [
         {"name": func, "function": getattr(tools, func)}
         for func in dir(tools)

backend/utils/utils.py

@@ -1,15 +1,12 @@
 from fastapi.security import HTTPBearer, HTTPAuthorizationCredentials
 from fastapi import HTTPException, status, Depends, Request
-from sqlalchemy.orm import Session
 
 from apps.webui.models.users import Users
 
-from pydantic import BaseModel
 from typing import Union, Optional
 from constants import ERROR_MESSAGES
 from passlib.context import CryptContext
 from datetime import datetime, timedelta
-import requests
 import jwt
 import uuid
 import logging
@@ -54,7 +51,7 @@ def decode_token(token: str) -> Optional[dict]:
     try:
         decoded = jwt.decode(token, SESSION_SECRET, algorithms=[ALGORITHM])
         return decoded
-    except Exception as e:
+    except Exception:
         return None
 
 
@@ -71,7 +68,7 @@ def get_http_authorization_cred(auth_header: str):
     try:
         scheme, credentials = auth_header.split(" ")
         return HTTPAuthorizationCredentials(scheme=scheme, credentials=credentials)
-    except:
+    except Exception:
         raise ValueError(ERROR_MESSAGES.INVALID_TOKEN)
 
 
@@ -96,7 +93,7 @@ def get_current_user(
 
     # auth by jwt token
     data = decode_token(token)
-    if data != None and "id" in data:
+    if data is not None and "id" in data:
         user = Users.get_user_by_id(data["id"])
         if user is None:
             raise HTTPException(

cypress/data/example-doc.txt

@@ -0,0 +1,9 @@
+Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Pellentesque elit eget gravida cum sociis natoque. Morbi tristique senectus et netus et malesuada. Sapien nec sagittis aliquam malesuada bibendum. Amet consectetur adipiscing elit duis tristique sollicitudin. Non pulvinar neque laoreet suspendisse interdum consectetur libero. Arcu cursus vitae congue mauris rhoncus aenean vel elit scelerisque. Nec feugiat nisl pretium fusce id velit. Imperdiet proin fermentum leo vel. Arcu dui vivamus arcu felis bibendum ut tristique et egestas. Pellentesque sit amet porttitor eget dolor morbi non arcu risus. Egestas tellus rutrum tellus pellentesque eu tincidunt tortor aliquam. Et ultrices neque ornare aenean euismod.
+
+Enim nulla aliquet porttitor lacus luctus accumsan tortor posuere ac. Viverra nibh cras pulvinar mattis nunc. Lacinia at quis risus sed vulputate. Ac tortor vitae purus faucibus ornare suspendisse sed nisi lacus. Bibendum arcu vitae elementum curabitur vitae nunc. Consectetur adipiscing elit duis tristique sollicitudin nibh sit amet commodo. Velit egestas dui id ornare arcu odio ut. Et malesuada fames ac turpis egestas integer eget aliquet. Lacus suspendisse faucibus interdum posuere lorem ipsum dolor sit. Morbi tristique senectus et netus. Pretium viverra suspendisse potenti nullam ac tortor vitae. Parturient montes nascetur ridiculus mus mauris vitae. Quis viverra nibh cras pulvinar mattis nunc sed blandit libero. Euismod nisi porta lorem mollis aliquam ut porttitor leo. Mauris in aliquam sem fringilla ut morbi. Faucibus pulvinar elementum integer enim neque. Neque sodales ut etiam sit. Consectetur a erat nam at.
+
+Sed nisi lacus sed viverra tellus in hac habitasse. Proin sagittis nisl rhoncus mattis rhoncus. Risus commodo viverra maecenas accumsan lacus. Morbi quis commodo odio aenean sed adipiscing. Mollis nunc sed id semper risus in. Ultricies mi eget mauris pharetra et ultrices neque. Amet luctus venenatis lectus magna fringilla urna porttitor rhoncus. Eget magna fermentum iaculis eu non diam phasellus. Id diam maecenas ultricies mi eget mauris pharetra et ultrices. Id donec ultrices tincidunt arcu non sodales. Sed cras ornare arcu dui vivamus arcu felis bibendum ut. Urna duis convallis convallis tellus id interdum velit. Rhoncus mattis rhoncus urna neque viverra justo nec. Purus semper eget duis at tellus at urna condimentum. Et odio pellentesque diam volutpat commodo sed egestas. Blandit volutpat maecenas volutpat blandit. In egestas erat imperdiet sed euismod nisi porta lorem mollis. Est ullamcorper eget nulla facilisi etiam dignissim.
+
+Justo nec ultrices dui sapien eget mi proin sed. Purus gravida quis blandit turpis cursus in hac. Placerat orci nulla pellentesque dignissim enim sit. Morbi tristique senectus et netus et malesuada fames ac. Consequat mauris nunc congue nisi. Eu lobortis elementum nibh tellus molestie nunc non blandit. Viverra justo nec ultrices dui. Morbi non arcu risus quis. Elementum sagittis vitae et leo duis. Lectus mauris ultrices eros in cursus. Neque laoreet suspendisse interdum consectetur.
+
+Facilisis gravida neque convallis a cras. Nisl rhoncus mattis rhoncus urna neque viverra justo. Faucibus purus in massa tempor. Lacus laoreet non curabitur gravida arcu ac tortor. Tincidunt eget nullam non nisi est sit amet. Ornare lectus sit amet est placerat in egestas. Sollicitudin tempor id eu nisl nunc mi. Scelerisque viverra mauris in aliquam sem fringilla ut. Ullamcorper sit amet risus nullam. Mauris rhoncus aenean vel elit scelerisque mauris pellentesque pulvinar. Velit euismod in pellentesque massa placerat duis ultricies lacus. Pharetra magna ac placerat vestibulum lectus mauris ultrices eros in. Lorem ipsum dolor sit amet. Sit amet mauris commodo quis imperdiet. Quam pellentesque nec nam aliquam sem et tortor. Amet nisl purus in mollis nunc. Sed risus pretium quam vulputate dignissim suspendisse in est. Nisl condimentum id venenatis a condimentum. Velit euismod in pellentesque massa. Quam id leo in vitae turpis massa sed.

cypress/e2e/chat.cy.ts

@@ -38,9 +38,10 @@ describe('Settings', () => {
 			// User's message should be visible
 			cy.get('.chat-user').should('exist');
 			// Wait for the response
-			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
-				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
-				.should('exist');
+			// .chat-assistant is created after the first token is received
+			cy.get('.chat-assistant', { timeout: 10_000 }).should('exist');
+			// Generation Info is created after the stop token is received
+			cy.get('div[aria-label="Generation Info"]', { timeout: 120_000 }).should('exist');
 		});
 
 		it('user can share chat', () => {
@@ -57,21 +58,24 @@ describe('Settings', () => {
 			// User's message should be visible
 			cy.get('.chat-user').should('exist');
 			// Wait for the response
-			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
-				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
-				.should('exist');
+			// .chat-assistant is created after the first token is received
+			cy.get('.chat-assistant', { timeout: 10_000 }).should('exist');
+			// Generation Info is created after the stop token is received
+			cy.get('div[aria-label="Generation Info"]', { timeout: 120_000 }).should('exist');
 			// spy on requests
 			const spy = cy.spy();
-			cy.intercept('GET', '/api/v1/chats/*', spy);
+			cy.intercept('POST', '/api/v1/chats/**/share', spy);
 			// Open context menu
 			cy.get('#chat-context-menu-button').click();
 			// Click share button
 			cy.get('#chat-share-button').click();
 			// Check if the share dialog is visible
 			cy.get('#copy-and-share-chat-button').should('exist');
-			cy.wrap({}, { timeout: 5000 }).should(() => {
-				// Check if the request was made twice (once for to replace chat object and once more due to change event)
-				expect(spy).to.be.callCount(2);
+			// Click the copy button
+			cy.get('#copy-and-share-chat-button').click();
+			cy.wrap({}, { timeout: 5_000 }).should(() => {
+				// Check if the share request was made
+				expect(spy).to.be.callCount(1);
 			});
 		});
 
@@ -89,9 +93,10 @@ describe('Settings', () => {
 			// User's message should be visible
 			cy.get('.chat-user').should('exist');
 			// Wait for the response
-			cy.get('.chat-assistant', { timeout: 120_000 }) // .chat-assistant is created after the first token is received
-				.find('div[aria-label="Generation Info"]', { timeout: 120_000 }) // Generation Info is created after the stop token is received
-				.should('exist');
+			// .chat-assistant is created after the first token is received
+			cy.get('.chat-assistant', { timeout: 10_000 }).should('exist');
+			// Generation Info is created after the stop token is received
+			cy.get('div[aria-label="Generation Info"]', { timeout: 120_000 }).should('exist');
 			// Click on the generate image button
 			cy.get('[aria-label="Generate Image"]').click();
 			// Wait for image to be visible

cypress/e2e/documents.cy.ts

@@ -0,0 +1,46 @@
+// eslint-disable-next-line @typescript-eslint/triple-slash-reference
+/// <reference path="../support/index.d.ts" />
+
+describe('Documents', () => {
+	const timestamp = Date.now();
+
+	before(() => {
+		cy.uploadTestDocument(timestamp);
+	});
+
+	after(() => {
+		cy.deleteTestDocument(timestamp);
+	});
+
+	context('Admin', () => {
+		beforeEach(() => {
+			// Login as the admin user
+			cy.loginAdmin();
+			// Visit the home page
+			cy.visit('/workspace/documents');
+			cy.get('button').contains('#cypress-test').click();
+		});
+
+		it('can see documents', () => {
+			cy.get('div').contains(`document-test-initial-${timestamp}.txt`).should('have.length', 1);
+		});
+
+		it('can see edit button', () => {
+			cy.get('div')
+				.contains(`document-test-initial-${timestamp}.txt`)
+				.get("button[aria-label='Edit Doc']")
+				.should('exist');
+		});
+
+		it('can see delete button', () => {
+			cy.get('div')
+				.contains(`document-test-initial-${timestamp}.txt`)
+				.get("button[aria-label='Delete Doc']")
+				.should('exist');
+		});
+
+		it('can see upload button', () => {
+			cy.get("button[aria-label='Add Docs']").should('exist');
+		});
+	});
+});

cypress/support/e2e.ts

@@ -1,4 +1,6 @@
 /// <reference types="cypress" />
+// eslint-disable-next-line @typescript-eslint/triple-slash-reference
+/// <reference path="../support/index.d.ts" />
 
 export const adminUser = {
 	name: 'Admin User',
@@ -10,6 +12,9 @@ const login = (email: string, password: string) => {
 	return cy.session(
 		email,
 		() => {
+			// Make sure to test against us english to have stable tests,
+			// regardless on local language preferences
+			localStorage.setItem('locale', 'en-US');
 			// Visit auth page
 			cy.visit('/auth');
 			// Fill out the form
@@ -68,6 +73,50 @@ Cypress.Commands.add('register', (name, email, password) => register(name, email
 Cypress.Commands.add('registerAdmin', () => registerAdmin());
 Cypress.Commands.add('loginAdmin', () => loginAdmin());
 
+Cypress.Commands.add('uploadTestDocument', (suffix: any) => {
+	// Login as admin
+	cy.loginAdmin();
+	// upload example document
+	cy.visit('/workspace/documents');
+	// Create a document
+	cy.get("button[aria-label='Add Docs']").click();
+	cy.readFile('cypress/data/example-doc.txt').then((text) => {
+		// select file
+		cy.get('#upload-doc-input').selectFile(
+			{
+				contents: Cypress.Buffer.from(text + Date.now()),
+				fileName: `document-test-initial-${suffix}.txt`,
+				mimeType: 'text/plain',
+				lastModified: Date.now()
+			},
+			{
+				force: true
+			}
+		);
+		// open tag input
+		cy.get("button[aria-label='Add Tag']").click();
+		cy.get("input[placeholder='Add a tag']").type('cypress-test');
+		cy.get("button[aria-label='Save Tag']").click();
+
+		// submit to upload
+		cy.get("button[type='submit']").click();
+
+		// wait for upload to finish
+		cy.get('button').contains('#cypress-test').should('exist');
+		cy.get('div').contains(`document-test-initial-${suffix}.txt`).should('exist');
+	});
+});
+
+Cypress.Commands.add('deleteTestDocument', (suffix: any) => {
+	cy.loginAdmin();
+	cy.visit('/workspace/documents');
+	// clean up uploaded documents
+	cy.get('div')
+		.contains(`document-test-initial-${suffix}.txt`)
+		.find("button[aria-label='Delete Doc']")
+		.click();
+});
+
 before(() => {
 	cy.registerAdmin();
 });

cypress/support/index.d.ts

@@ -7,5 +7,7 @@ declare namespace Cypress {
 		register(name: string, email: string, password: string): Chainable<Element>;
 		registerAdmin(): Chainable<Element>;
 		loginAdmin(): Chainable<Element>;
+		uploadTestDocument(suffix: any): Chainable<Element>;
+		deleteTestDocument(suffix: any): Chainable<Element>;
 	}
 }

docs/CONTRIBUTING.md

@@ -22,7 +22,6 @@ Noticed something off? Have an idea? Check our [Issues tab](https://github.com/o
 > [!IMPORTANT]
 >
 > - **Template Compliance:** Please be aware that failure to follow the provided issue template, or not providing the requested information at all, will likely result in your issue being closed without further consideration. This approach is critical for maintaining the manageability and integrity of issue tracking.
->
 > - **Detail is Key:** To ensure your issue is understood and can be effectively addressed, it's imperative to include comprehensive details. Descriptions should be clear, including steps to reproduce, expected outcomes, and actual results. Lack of sufficient detail may hinder our ability to resolve your issue.
 
 ### 🧭 Scope of Support

docs/SECURITY.md

@@ -11,10 +11,26 @@ Our primary goal is to ensure the protection and confidentiality of sensitive da
 
 ## Reporting a Vulnerability
 
-If you discover a security issue within our system, please notify us immediately via a pull request or contact us on discord.
+We appreciate the community's interest in identifying potential vulnerabilities. However, effective immediately, we will **not** accept low-effort vulnerability reports. To ensure that submissions are constructive and actionable, please adhere to the following guidelines:
+
+1. **No Vague Reports**: Submissions such as "I found a vulnerability" without any details will be treated as spam and will not be accepted.
+
+2. **In-Depth Understanding Required**: Reports must reflect a clear understanding of the codebase and provide specific details about the vulnerability, including the affected components and potential impacts.
+
+3. **Proof of Concept (PoC) is Mandatory**: Each submission must include a well-documented proof of concept (PoC) that demonstrates the vulnerability. If confidentiality is a concern, reporters are encouraged to create a private fork of the repository and share access with the maintainers. Reports lacking valid evidence will be disregarded.
+
+4. **Required Patch Submission**: Along with the PoC, reporters must provide a patch or actionable steps to remediate the identified vulnerability. This helps us evaluate and implement fixes rapidly.
+
+5. **Streamlined Merging Process**: When vulnerability reports meet the above criteria, we can consider them for immediate merging, similar to regular pull requests. Well-structured and thorough submissions will expedite the process of enhancing our security.
+
+Submissions that do not meet these criteria will be closed, and repeat offenders may face a ban from future submissions. We aim to create a respectful and constructive reporting environment, where high-quality submissions foster better security for everyone.
 
 ## Product Security
 
-We regularly audit our internal processes and system's architecture for vulnerabilities using a combination of automated and manual testing techniques.
+We regularly audit our internal processes and system architecture for vulnerabilities using a combination of automated and manual testing techniques. We are also planning to implement SAST and SCA scans in our project soon.
 
-We are planning on implementing SAST and SCA scans in our project soon.
+For immediate concerns or detailed reports that meet our guidelines, please create an issue in our [issue tracker](/open-webui/open-webui/issues) or contact us on [Discord](https://discord.gg/5rJgQTnV4s).
+
+---
+
+_Last updated on **2024-08-06**._

package.json

@@ -1,6 +1,6 @@
 {
 	"name": "open-webui",
-	"version": "0.3.10",
+	"version": "0.3.13",
 	"private": true,
 	"scripts": {
 		"dev": "npm run pyodide:fetch && vite dev --host",
@@ -20,30 +20,31 @@
 		"pyodide:fetch": "node scripts/prepare-pyodide.js"
 	},
 	"devDependencies": {
-		"@sveltejs/adapter-auto": "^2.0.0",
-		"@sveltejs/adapter-static": "^2.0.3",
-		"@sveltejs/kit": "^1.30.0",
-		"@tailwindcss/typography": "^0.5.10",
+		"@sveltejs/adapter-auto": "3.2.2",
+		"@sveltejs/adapter-static": "^3.0.2",
+		"@sveltejs/kit": "^2.5.20",
+		"@sveltejs/vite-plugin-svelte": "^3.1.1",
+		"@tailwindcss/typography": "^0.5.13",
 		"@types/bun": "latest",
 		"@typescript-eslint/eslint-plugin": "^6.17.0",
 		"@typescript-eslint/parser": "^6.17.0",
 		"autoprefixer": "^10.4.16",
 		"cypress": "^13.8.1",
 		"eslint": "^8.56.0",
-		"eslint-config-prettier": "^8.5.0",
-		"eslint-plugin-cypress": "^3.0.2",
-		"eslint-plugin-svelte": "^2.30.0",
-		"i18next-parser": "^8.13.0",
+		"eslint-config-prettier": "^9.1.0",
+		"eslint-plugin-cypress": "^3.4.0",
+		"eslint-plugin-svelte": "^2.43.0",
+		"i18next-parser": "^9.0.1",
 		"postcss": "^8.4.31",
-		"prettier": "^2.8.0",
-		"prettier-plugin-svelte": "^2.10.1",
-		"svelte": "^4.0.5",
-		"svelte-check": "^3.4.3",
+		"prettier": "^3.3.3",
+		"prettier-plugin-svelte": "^3.2.6",
+		"svelte": "^4.2.18",
+		"svelte-check": "^3.8.5",
 		"svelte-confetti": "^1.3.2",
 		"tailwindcss": "^3.3.3",
 		"tslib": "^2.4.1",
-		"typescript": "^5.0.0",
-		"vite": "^4.4.2",
+		"typescript": "^5.5.4",
+		"vite": "^5.3.5",
 		"vitest": "^1.6.0"
 	},
 	"type": "module",
@@ -52,7 +53,7 @@
 		"@codemirror/lang-python": "^6.1.6",
 		"@codemirror/theme-one-dark": "^6.1.2",
 		"@pyscript/core": "^0.4.32",
-		"@sveltejs/adapter-node": "^1.3.1",
+		"@sveltejs/adapter-node": "^2.0.0",
 		"async": "^3.2.5",
 		"bits-ui": "^0.19.7",
 		"codemirror": "^6.0.1",
@@ -60,6 +61,7 @@
 		"dayjs": "^1.11.10",
 		"eventsource-parser": "^1.1.2",
 		"file-saver": "^2.0.5",
+		"fuse.js": "^7.0.0",
 		"highlight.js": "^11.9.0",
 		"i18next": "^23.10.0",
 		"i18next-browser-languagedetector": "^7.2.0",
@@ -68,6 +70,7 @@
 		"js-sha256": "^0.10.1",
 		"katex": "^0.16.9",
 		"marked": "^9.1.0",
+		"marked-katex-extension": "^5.1.1",
 		"mermaid": "^10.9.1",
 		"pyodide": "^0.26.1",
 		"socket.io-client": "^4.2.0",
@@ -76,5 +79,9 @@
 		"tippy.js": "^6.3.7",
 		"turndown": "^7.2.0",
 		"uuid": "^9.0.1"
+	},
+	"engines": {
+		"node": ">=18.13.0 <=21.x.x",
+		"npm": ">=6.0.0"
 	}
 }

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "open-webui"
-description = "Open WebUI (Formerly Ollama WebUI)"
+description = "Open WebUI"
 authors = [
     { name = "Timothy Jaeryang Baek", email = "tim@openwebui.com" }
 ]
@@ -8,67 +8,82 @@ license = { file = "LICENSE" }
 dependencies = [
     "fastapi==0.111.0",
     "uvicorn[standard]==0.22.0",
-    "pydantic==2.7.1",
+    "pydantic==2.8.2",
     "python-multipart==0.0.9",
 
     "Flask==3.0.3",
     "Flask-Cors==4.0.1",
 
-    "python-socketio==5.11.2",
+    "python-socketio==5.11.3",
     "python-jose==3.3.0",
     "passlib[bcrypt]==1.7.4",
 
-    "requests==2.32.2",
-    "aiohttp==3.9.5",
-    "peewee==3.17.5",
+    "requests==2.32.3",
+    "aiohttp==3.10.2",
+
+    "sqlalchemy==2.0.31",
+    "alembic==1.13.2",
+    "peewee==3.17.6",
     "peewee-migrate==1.12.2",
     "psycopg2-binary==2.9.9",
-    "PyMySQL==1.1.0",
+    "PyMySQL==1.1.1",
     "bcrypt==4.1.3",
 
-    "boto3==1.34.110",
+    "pymongo",
+    "redis",
+    "boto3==1.34.153",
 
     "argon2-cffi==23.1.0",
     "APScheduler==3.10.4",
-    "google-generativeai==0.5.4",
 
-    "langchain==0.2.0",
-    "langchain-community==0.2.0",
-    "langchain-chroma==0.1.1",
+    "openai",
+    "anthropic",
+    "google-generativeai==0.7.2",
+    "tiktoken",
+
+    "langchain==0.2.12",
+    "langchain-community==0.2.10",
+    "langchain-chroma==0.1.2",
 
     "fake-useragent==1.5.1",
-    "chromadb==0.5.0",
-    "sentence-transformers==2.7.0",
-    "pypdf==4.2.0",
+    "chromadb==0.5.5",
+    "sentence-transformers==3.0.1",
+    "pypdf==4.3.1",
     "docx2txt==0.8",
-    "unstructured==0.14.0",
+    "python-pptx==1.0.0",
+    "unstructured==0.15.0",
     "Markdown==3.6",
     "pypandoc==1.13",
     "pandas==2.2.2",
-    "openpyxl==3.1.2",
+    "openpyxl==3.1.5",
     "pyxlsb==1.0.10",
     "xlrd==2.0.1",
-    "validators==0.28.1",
+    "validators==0.33.0",
+    "psutil",
 
-    "opencv-python-headless==4.9.0.80",
-    "rapidocr-onnxruntime==1.3.22",
+    "opencv-python-headless==4.10.0.84",
+    "rapidocr-onnxruntime==1.3.24",
 
     "fpdf2==2.7.9",
     "rank-bm25==0.2.2",
 
     "faster-whisper==1.0.2",
 
-    "PyJWT[crypto]==2.8.0",
+    "PyJWT[crypto]==2.9.0",
     "authlib==1.3.1",
 
-    "black==24.4.2",
-    "langfuse==2.33.0",
+    "black==24.8.0",
+    "langfuse==2.43.3",
     "youtube-transcript-api==0.6.2",
     "pytube==15.0.0",
+
     "extract_msg",
     "pydub",
-    "duckduckgo-search~=6.1.5"
+    "duckduckgo-search~=6.2.1",
 
+    "docker~=7.1.0",
+    "pytest~=8.2.2",
+    "pytest-docker~=3.1.1"
 ]
 readme = "README.md"
 requires-python = ">= 3.11, < 3.12.0a1"

requirements-dev.lock

@@ -10,16 +10,25 @@
 #   universal: false
 
 -e file:.
-aiohttp==3.9.5
+aiohappyeyeballs==2.3.5
+    # via aiohttp
+aiohttp==3.10.2
     # via langchain
     # via langchain-community
     # via open-webui
 aiosignal==1.3.1
     # via aiohttp
+alembic==1.13.2
+    # via open-webui
 annotated-types==0.6.0
     # via pydantic
-anyio==4.3.0
+anthropic==0.32.0
+    # via open-webui
+anyio==4.4.0
+    # via anthropic
     # via httpx
+    # via langfuse
+    # via openai
     # via starlette
     # via watchfiles
 apscheduler==3.10.4
@@ -32,6 +41,7 @@ asgiref==3.8.1
     # via opentelemetry-instrumentation-asgi
 attrs==23.2.0
     # via aiohttp
+    # via pytest-docker
 authlib==1.3.1
     # via open-webui
 av==11.0.0
@@ -49,13 +59,13 @@ beautifulsoup4==4.12.3
     # via unstructured
 bidict==0.23.1
     # via python-socketio
-black==24.4.2
+black==24.8.0
     # via open-webui
 blinker==1.8.2
     # via flask
-boto3==1.34.110
+boto3==1.34.153
     # via open-webui
-botocore==1.34.110
+botocore==1.34.155
     # via boto3
     # via s3transfer
 build==1.2.1
@@ -76,9 +86,9 @@ chardet==5.2.0
 charset-normalizer==3.3.2
     # via requests
     # via unstructured-client
-chroma-hnswlib==0.7.3
+chroma-hnswlib==0.7.6
     # via chromadb
-chromadb==0.5.0
+chromadb==0.5.5
     # via langchain-chroma
     # via open-webui
 click==8.1.7
@@ -102,7 +112,6 @@ cryptography==42.0.7
 ctranslate2==4.2.1
     # via faster-whisper
 dataclasses-json==0.6.6
-    # via langchain
     # via langchain-community
     # via unstructured
     # via unstructured-client
@@ -113,11 +122,17 @@ defusedxml==0.7.1
 deprecated==1.2.14
     # via opentelemetry-api
     # via opentelemetry-exporter-otlp-proto-grpc
+distro==1.9.0
+    # via anthropic
+    # via openai
 dnspython==2.6.1
     # via email-validator
+    # via pymongo
+docker==7.1.0
+    # via open-webui
 docx2txt==0.8
     # via open-webui
-duckduckgo-search==6.1.5
+duckduckgo-search==6.2.6
     # via open-webui
 easygui==0.98.3
     # via oletools
@@ -166,7 +181,7 @@ frozenlist==1.4.1
 fsspec==2024.3.1
     # via huggingface-hub
     # via torch
-google-ai-generativelanguage==0.6.4
+google-ai-generativelanguage==0.6.6
     # via google-generativeai
 google-api-core==2.19.0
     # via google-ai-generativelanguage
@@ -183,7 +198,7 @@ google-auth==2.29.0
     # via kubernetes
 google-auth-httplib2==0.2.0
     # via google-api-python-client
-google-generativeai==0.5.4
+google-generativeai==0.7.2
     # via open-webui
 googleapis-common-protos==1.63.0
     # via google-api-core
@@ -208,8 +223,11 @@ httplib2==0.22.0
 httptools==0.6.1
     # via uvicorn
 httpx==0.27.0
+    # via anthropic
+    # via chromadb
     # via fastapi
     # via langfuse
+    # via openai
 huggingface-hub==0.23.0
     # via faster-whisper
     # via sentence-transformers
@@ -229,12 +247,16 @@ importlib-metadata==7.0.0
     # via opentelemetry-api
 importlib-resources==6.4.0
     # via chromadb
+iniconfig==2.0.0
+    # via pytest
 itsdangerous==2.2.0
     # via flask
 jinja2==3.1.4
     # via fastapi
     # via flask
     # via torch
+jiter==0.5.0
+    # via anthropic
 jmespath==1.0.1
     # via boto3
     # via botocore
@@ -249,14 +271,14 @@ jsonpointer==2.4
     # via jsonpatch
 kubernetes==29.0.0
     # via chromadb
-langchain==0.2.0
+langchain==0.2.12
     # via langchain-community
     # via open-webui
-langchain-chroma==0.1.1
+langchain-chroma==0.1.2
     # via open-webui
-langchain-community==0.2.0
+langchain-community==0.2.10
     # via open-webui
-langchain-core==0.2.1
+langchain-core==0.2.28
     # via langchain
     # via langchain-chroma
     # via langchain-community
@@ -265,22 +287,26 @@ langchain-text-splitters==0.2.0
     # via langchain
 langdetect==1.0.9
     # via unstructured
-langfuse==2.33.0
+langfuse==2.43.3
     # via open-webui
-langsmith==0.1.57
+langsmith==0.1.96
     # via langchain
     # via langchain-community
     # via langchain-core
 lark==1.1.8
     # via rtfde
 lxml==5.2.2
+    # via python-pptx
     # via unstructured
+mako==1.3.5
+    # via alembic
 markdown==3.6
     # via open-webui
 markdown-it-py==3.0.0
     # via rich
 markupsafe==2.1.5
     # via jinja2
+    # via mako
     # via werkzeug
 marshmallow==3.21.2
     # via dataclasses-json
@@ -339,11 +365,13 @@ onnxruntime==1.17.3
     # via chromadb
     # via faster-whisper
     # via rapidocr-onnxruntime
+openai==1.38.0
+    # via open-webui
 opencv-python==4.9.0.80
     # via rapidocr-onnxruntime
-opencv-python-headless==4.9.0.80
+opencv-python-headless==4.10.0.84
     # via open-webui
-openpyxl==3.1.2
+openpyxl==3.1.5
     # via open-webui
 opentelemetry-api==1.24.0
     # via chromadb
@@ -380,7 +408,6 @@ ordered-set==4.1.0
     # via deepdiff
 orjson==3.10.3
     # via chromadb
-    # via duckduckgo-search
     # via fastapi
     # via langsmith
 overrides==7.7.0
@@ -393,6 +420,7 @@ packaging==23.2
     # via langfuse
     # via marshmallow
     # via onnxruntime
+    # via pytest
     # via transformers
     # via unstructured-client
 pandas==2.2.2
@@ -403,19 +431,24 @@ pathspec==0.12.1
     # via black
 pcodedmp==1.2.6
     # via oletools
-peewee==3.17.5
+peewee==3.17.6
     # via open-webui
     # via peewee-migrate
 peewee-migrate==1.12.2
     # via open-webui
 pillow==10.3.0
     # via fpdf2
+    # via python-pptx
     # via rapidocr-onnxruntime
     # via sentence-transformers
 platformdirs==4.2.1
     # via black
+pluggy==1.5.0
+    # via pytest
 posthog==3.5.0
     # via chromadb
+primp==0.5.5
+    # via duckduckgo-search
 proto-plus==1.23.0
     # via google-ai-generativelanguage
     # via google-api-core
@@ -428,6 +461,9 @@ protobuf==4.25.3
     # via onnxruntime
     # via opentelemetry-proto
     # via proto-plus
+psutil==6.0.0
+    # via open-webui
+    # via unstructured
 psycopg2-binary==2.9.9
     # via open-webui
 pyasn1==0.6.0
@@ -440,7 +476,8 @@ pyclipper==1.3.0.post5
     # via rapidocr-onnxruntime
 pycparser==2.22
     # via cffi
-pydantic==2.7.1
+pydantic==2.8.2
+    # via anthropic
     # via chromadb
     # via fastapi
     # via google-generativeai
@@ -449,30 +486,36 @@ pydantic==2.7.1
     # via langfuse
     # via langsmith
     # via open-webui
-pydantic-core==2.18.2
+    # via openai
+pydantic-core==2.20.1
     # via pydantic
 pydub==0.25.1
     # via open-webui
 pygments==2.18.0
     # via rich
-pyjwt==2.8.0
+pyjwt==2.9.0
     # via open-webui
-pymysql==1.1.0
+pymongo==4.8.0
+    # via open-webui
+pymysql==1.1.1
     # via open-webui
 pypandoc==1.13
     # via open-webui
 pyparsing==2.4.7
     # via httplib2
     # via oletools
-pypdf==4.2.0
+pypdf==4.3.1
     # via open-webui
     # via unstructured-client
 pypika==0.48.9
     # via chromadb
 pyproject-hooks==1.1.0
     # via build
-pyreqwest-impersonate==0.4.7
-    # via duckduckgo-search
+pytest==8.2.2
+    # via open-webui
+    # via pytest-docker
+pytest-docker==3.1.1
+    # via open-webui
 python-dateutil==2.9.0.post0
     # via botocore
     # via kubernetes
@@ -492,7 +535,9 @@ python-magic==0.4.27
 python-multipart==0.0.9
     # via fastapi
     # via open-webui
-python-socketio==5.11.2
+python-pptx==1.0.0
+    # via open-webui
+python-socketio==5.11.3
     # via open-webui
 pytube==15.0.0
     # via open-webui
@@ -516,15 +561,18 @@ rank-bm25==0.2.2
     # via open-webui
 rapidfuzz==3.9.0
     # via unstructured
-rapidocr-onnxruntime==1.3.22
+rapidocr-onnxruntime==1.3.24
     # via open-webui
 red-black-tree-mod==1.20
     # via extract-msg
+redis==5.0.8
+    # via open-webui
 regex==2024.5.10
     # via nltk
+    # via tiktoken
     # via transformers
-requests==2.32.2
-    # via chromadb
+requests==2.32.3
+    # via docker
     # via google-api-core
     # via huggingface-hub
     # via kubernetes
@@ -534,6 +582,7 @@ requests==2.32.2
     # via open-webui
     # via posthog
     # via requests-oauthlib
+    # via tiktoken
     # via transformers
     # via unstructured
     # via unstructured-client
@@ -556,12 +605,12 @@ scikit-learn==1.4.2
 scipy==1.13.0
     # via scikit-learn
     # via sentence-transformers
-sentence-transformers==2.7.0
+sentence-transformers==3.0.1
     # via open-webui
 setuptools==69.5.1
     # via ctranslate2
     # via opentelemetry-instrumentation
-shapely==2.0.4
+shapely==2.0.5
     # via rapidocr-onnxruntime
 shellingham==1.5.4
     # via typer
@@ -577,13 +626,17 @@ six==1.16.0
     # via rapidocr-onnxruntime
     # via unstructured-client
 sniffio==1.3.1
+    # via anthropic
     # via anyio
     # via httpx
+    # via openai
 soupsieve==2.5
     # via beautifulsoup4
-sqlalchemy==2.0.30
+sqlalchemy==2.0.31
+    # via alembic
     # via langchain
     # via langchain-community
+    # via open-webui
 starlette==0.37.2
     # via fastapi
 sympy==1.12
@@ -598,7 +651,10 @@ tenacity==8.3.0
     # via langchain-core
 threadpoolctl==3.5.0
     # via scikit-learn
+tiktoken==0.7.0
+    # via open-webui
 tokenizers==0.15.2
+    # via anthropic
     # via chromadb
     # via faster-whisper
     # via transformers
@@ -609,21 +665,28 @@ tqdm==4.66.4
     # via google-generativeai
     # via huggingface-hub
     # via nltk
+    # via openai
     # via sentence-transformers
     # via transformers
+    # via unstructured
 transformers==4.39.3
     # via sentence-transformers
 typer==0.12.3
     # via chromadb
     # via fastapi-cli
 typing-extensions==4.11.0
+    # via alembic
+    # via anthropic
     # via chromadb
     # via fastapi
     # via google-generativeai
     # via huggingface-hub
+    # via langchain-core
+    # via openai
     # via opentelemetry-sdk
     # via pydantic
     # via pydantic-core
+    # via python-pptx
     # via sqlalchemy
     # via torch
     # via typer
@@ -640,7 +703,7 @@ tzlocal==5.2
     # via extract-msg
 ujson==5.10.0
     # via fastapi
-unstructured==0.14.0
+unstructured==0.15.0
     # via open-webui
 unstructured-client==0.22.0
     # via unstructured
@@ -648,6 +711,7 @@ uritemplate==4.1.1
     # via google-api-python-client
 urllib3==2.2.1
     # via botocore
+    # via docker
     # via kubernetes
     # via requests
     # via unstructured-client
@@ -657,7 +721,7 @@ uvicorn==0.22.0
     # via open-webui
 uvloop==0.19.0
     # via uvicorn
-validators==0.28.1
+validators==0.33.0
     # via open-webui
 watchfiles==0.21.0
     # via uvicorn
@@ -676,6 +740,8 @@ wsproto==1.2.0
     # via simple-websocket
 xlrd==2.0.1
     # via open-webui
+xlsxwriter==3.2.0
+    # via python-pptx
 yarl==1.9.4
     # via aiohttp
 youtube-transcript-api==0.6.2

requirements.lock

@@ -10,16 +10,25 @@
 #   universal: false
 
 -e file:.
-aiohttp==3.9.5
+aiohappyeyeballs==2.3.5
+    # via aiohttp
+aiohttp==3.10.2
     # via langchain
     # via langchain-community
     # via open-webui
 aiosignal==1.3.1
     # via aiohttp
+alembic==1.13.2
+    # via open-webui
 annotated-types==0.6.0
     # via pydantic
-anyio==4.3.0
+anthropic==0.32.0
+    # via open-webui
+anyio==4.4.0
+    # via anthropic
     # via httpx
+    # via langfuse
+    # via openai
     # via starlette
     # via watchfiles
 apscheduler==3.10.4
@@ -32,6 +41,7 @@ asgiref==3.8.1
     # via opentelemetry-instrumentation-asgi
 attrs==23.2.0
     # via aiohttp
+    # via pytest-docker
 authlib==1.3.1
     # via open-webui
 av==11.0.0
@@ -49,13 +59,13 @@ beautifulsoup4==4.12.3
     # via unstructured
 bidict==0.23.1
     # via python-socketio
-black==24.4.2
+black==24.8.0
     # via open-webui
 blinker==1.8.2
     # via flask
-boto3==1.34.110
+boto3==1.34.153
     # via open-webui
-botocore==1.34.110
+botocore==1.34.155
     # via boto3
     # via s3transfer
 build==1.2.1
@@ -76,9 +86,9 @@ chardet==5.2.0
 charset-normalizer==3.3.2
     # via requests
     # via unstructured-client
-chroma-hnswlib==0.7.3
+chroma-hnswlib==0.7.6
     # via chromadb
-chromadb==0.5.0
+chromadb==0.5.5
     # via langchain-chroma
     # via open-webui
 click==8.1.7
@@ -102,7 +112,6 @@ cryptography==42.0.7
 ctranslate2==4.2.1
     # via faster-whisper
 dataclasses-json==0.6.6
-    # via langchain
     # via langchain-community
     # via unstructured
     # via unstructured-client
@@ -113,11 +122,17 @@ defusedxml==0.7.1
 deprecated==1.2.14
     # via opentelemetry-api
     # via opentelemetry-exporter-otlp-proto-grpc
+distro==1.9.0
+    # via anthropic
+    # via openai
 dnspython==2.6.1
     # via email-validator
+    # via pymongo
+docker==7.1.0
+    # via open-webui
 docx2txt==0.8
     # via open-webui
-duckduckgo-search==6.1.5
+duckduckgo-search==6.2.6
     # via open-webui
 easygui==0.98.3
     # via oletools
@@ -166,7 +181,7 @@ frozenlist==1.4.1
 fsspec==2024.3.1
     # via huggingface-hub
     # via torch
-google-ai-generativelanguage==0.6.4
+google-ai-generativelanguage==0.6.6
     # via google-generativeai
 google-api-core==2.19.0
     # via google-ai-generativelanguage
@@ -183,7 +198,7 @@ google-auth==2.29.0
     # via kubernetes
 google-auth-httplib2==0.2.0
     # via google-api-python-client
-google-generativeai==0.5.4
+google-generativeai==0.7.2
     # via open-webui
 googleapis-common-protos==1.63.0
     # via google-api-core
@@ -208,8 +223,11 @@ httplib2==0.22.0
 httptools==0.6.1
     # via uvicorn
 httpx==0.27.0
+    # via anthropic
+    # via chromadb
     # via fastapi
     # via langfuse
+    # via openai
 huggingface-hub==0.23.0
     # via faster-whisper
     # via sentence-transformers
@@ -229,12 +247,16 @@ importlib-metadata==7.0.0
     # via opentelemetry-api
 importlib-resources==6.4.0
     # via chromadb
+iniconfig==2.0.0
+    # via pytest
 itsdangerous==2.2.0
     # via flask
 jinja2==3.1.4
     # via fastapi
     # via flask
     # via torch
+jiter==0.5.0
+    # via anthropic
 jmespath==1.0.1
     # via boto3
     # via botocore
@@ -249,14 +271,14 @@ jsonpointer==2.4
     # via jsonpatch
 kubernetes==29.0.0
     # via chromadb
-langchain==0.2.0
+langchain==0.2.12
     # via langchain-community
     # via open-webui
-langchain-chroma==0.1.1
+langchain-chroma==0.1.2
     # via open-webui
-langchain-community==0.2.0
+langchain-community==0.2.10
     # via open-webui
-langchain-core==0.2.1
+langchain-core==0.2.28
     # via langchain
     # via langchain-chroma
     # via langchain-community
@@ -265,22 +287,26 @@ langchain-text-splitters==0.2.0
     # via langchain
 langdetect==1.0.9
     # via unstructured
-langfuse==2.33.0
+langfuse==2.43.3
     # via open-webui
-langsmith==0.1.57
+langsmith==0.1.96
     # via langchain
     # via langchain-community
     # via langchain-core
 lark==1.1.8
     # via rtfde
 lxml==5.2.2
+    # via python-pptx
     # via unstructured
+mako==1.3.5
+    # via alembic
 markdown==3.6
     # via open-webui
 markdown-it-py==3.0.0
     # via rich
 markupsafe==2.1.5
     # via jinja2
+    # via mako
     # via werkzeug
 marshmallow==3.21.2
     # via dataclasses-json
@@ -339,11 +365,13 @@ onnxruntime==1.17.3
     # via chromadb
     # via faster-whisper
     # via rapidocr-onnxruntime
+openai==1.38.0
+    # via open-webui
 opencv-python==4.9.0.80
     # via rapidocr-onnxruntime
-opencv-python-headless==4.9.0.80
+opencv-python-headless==4.10.0.84
     # via open-webui
-openpyxl==3.1.2
+openpyxl==3.1.5
     # via open-webui
 opentelemetry-api==1.24.0
     # via chromadb
@@ -380,7 +408,6 @@ ordered-set==4.1.0
     # via deepdiff
 orjson==3.10.3
     # via chromadb
-    # via duckduckgo-search
     # via fastapi
     # via langsmith
 overrides==7.7.0
@@ -393,6 +420,7 @@ packaging==23.2
     # via langfuse
     # via marshmallow
     # via onnxruntime
+    # via pytest
     # via transformers
     # via unstructured-client
 pandas==2.2.2
@@ -403,19 +431,24 @@ pathspec==0.12.1
     # via black
 pcodedmp==1.2.6
     # via oletools
-peewee==3.17.5
+peewee==3.17.6
     # via open-webui
     # via peewee-migrate
 peewee-migrate==1.12.2
     # via open-webui
 pillow==10.3.0
     # via fpdf2
+    # via python-pptx
     # via rapidocr-onnxruntime
     # via sentence-transformers
 platformdirs==4.2.1
     # via black
+pluggy==1.5.0
+    # via pytest
 posthog==3.5.0
     # via chromadb
+primp==0.5.5
+    # via duckduckgo-search
 proto-plus==1.23.0
     # via google-ai-generativelanguage
     # via google-api-core
@@ -428,6 +461,9 @@ protobuf==4.25.3
     # via onnxruntime
     # via opentelemetry-proto
     # via proto-plus
+psutil==6.0.0
+    # via open-webui
+    # via unstructured
 psycopg2-binary==2.9.9
     # via open-webui
 pyasn1==0.6.0
@@ -440,7 +476,8 @@ pyclipper==1.3.0.post5
     # via rapidocr-onnxruntime
 pycparser==2.22
     # via cffi
-pydantic==2.7.1
+pydantic==2.8.2
+    # via anthropic
     # via chromadb
     # via fastapi
     # via google-generativeai
@@ -449,30 +486,36 @@ pydantic==2.7.1
     # via langfuse
     # via langsmith
     # via open-webui
-pydantic-core==2.18.2
+    # via openai
+pydantic-core==2.20.1
     # via pydantic
 pydub==0.25.1
     # via open-webui
 pygments==2.18.0
     # via rich
-pyjwt==2.8.0
+pyjwt==2.9.0
     # via open-webui
-pymysql==1.1.0
+pymongo==4.8.0
+    # via open-webui
+pymysql==1.1.1
     # via open-webui
 pypandoc==1.13
     # via open-webui
 pyparsing==2.4.7
     # via httplib2
     # via oletools
-pypdf==4.2.0
+pypdf==4.3.1
     # via open-webui
     # via unstructured-client
 pypika==0.48.9
     # via chromadb
 pyproject-hooks==1.1.0
     # via build
-pyreqwest-impersonate==0.4.7
-    # via duckduckgo-search
+pytest==8.2.2
+    # via open-webui
+    # via pytest-docker
+pytest-docker==3.1.1
+    # via open-webui
 python-dateutil==2.9.0.post0
     # via botocore
     # via kubernetes
@@ -492,7 +535,9 @@ python-magic==0.4.27
 python-multipart==0.0.9
     # via fastapi
     # via open-webui
-python-socketio==5.11.2
+python-pptx==1.0.0
+    # via open-webui
+python-socketio==5.11.3
     # via open-webui
 pytube==15.0.0
     # via open-webui
@@ -516,15 +561,18 @@ rank-bm25==0.2.2
     # via open-webui
 rapidfuzz==3.9.0
     # via unstructured
-rapidocr-onnxruntime==1.3.22
+rapidocr-onnxruntime==1.3.24
     # via open-webui
 red-black-tree-mod==1.20
     # via extract-msg
+redis==5.0.8
+    # via open-webui
 regex==2024.5.10
     # via nltk
+    # via tiktoken
     # via transformers
-requests==2.32.2
-    # via chromadb
+requests==2.32.3
+    # via docker
     # via google-api-core
     # via huggingface-hub
     # via kubernetes
@@ -534,6 +582,7 @@ requests==2.32.2
     # via open-webui
     # via posthog
     # via requests-oauthlib
+    # via tiktoken
     # via transformers
     # via unstructured
     # via unstructured-client
@@ -556,12 +605,12 @@ scikit-learn==1.4.2
 scipy==1.13.0
     # via scikit-learn
     # via sentence-transformers
-sentence-transformers==2.7.0
+sentence-transformers==3.0.1
     # via open-webui
 setuptools==69.5.1
     # via ctranslate2
     # via opentelemetry-instrumentation
-shapely==2.0.4
+shapely==2.0.5
     # via rapidocr-onnxruntime
 shellingham==1.5.4
     # via typer
@@ -577,13 +626,17 @@ six==1.16.0
     # via rapidocr-onnxruntime
     # via unstructured-client
 sniffio==1.3.1
+    # via anthropic
     # via anyio
     # via httpx
+    # via openai
 soupsieve==2.5
     # via beautifulsoup4
-sqlalchemy==2.0.30
+sqlalchemy==2.0.31
+    # via alembic
     # via langchain
     # via langchain-community
+    # via open-webui
 starlette==0.37.2
     # via fastapi
 sympy==1.12
@@ -598,7 +651,10 @@ tenacity==8.3.0
     # via langchain-core
 threadpoolctl==3.5.0
     # via scikit-learn
+tiktoken==0.7.0
+    # via open-webui
 tokenizers==0.15.2
+    # via anthropic
     # via chromadb
     # via faster-whisper
     # via transformers
@@ -609,21 +665,28 @@ tqdm==4.66.4
     # via google-generativeai
     # via huggingface-hub
     # via nltk
+    # via openai
     # via sentence-transformers
     # via transformers
+    # via unstructured
 transformers==4.39.3
     # via sentence-transformers
 typer==0.12.3
     # via chromadb
     # via fastapi-cli
 typing-extensions==4.11.0
+    # via alembic
+    # via anthropic
     # via chromadb
     # via fastapi
     # via google-generativeai
     # via huggingface-hub
+    # via langchain-core
+    # via openai
     # via opentelemetry-sdk
     # via pydantic
     # via pydantic-core
+    # via python-pptx
     # via sqlalchemy
     # via torch
     # via typer
@@ -640,7 +703,7 @@ tzlocal==5.2
     # via extract-msg
 ujson==5.10.0
     # via fastapi
-unstructured==0.14.0
+unstructured==0.15.0
     # via open-webui
 unstructured-client==0.22.0
     # via unstructured
@@ -648,6 +711,7 @@ uritemplate==4.1.1
     # via google-api-python-client
 urllib3==2.2.1
     # via botocore
+    # via docker
     # via kubernetes
     # via requests
     # via unstructured-client
@@ -657,7 +721,7 @@ uvicorn==0.22.0
     # via open-webui
 uvloop==0.19.0
     # via uvicorn
-validators==0.28.1
+validators==0.33.0
     # via open-webui
 watchfiles==0.21.0
     # via uvicorn
@@ -676,6 +740,8 @@ wsproto==1.2.0
     # via simple-websocket
 xlrd==2.0.1
     # via open-webui
+xlsxwriter==3.2.0
+    # via python-pptx
 yarl==1.9.4
     # via aiohttp
 youtube-transcript-api==0.6.2

src/app.css

@@ -154,3 +154,16 @@ input[type='number'] {
 .tippy-box[data-theme~='dark'] {
 	@apply rounded-lg bg-gray-950 text-xs border border-gray-900 shadow-xl;
 }
+
+.password {
+	-webkit-text-security: disc;
+}
+
+.codespan {
+	color: #eb5757;
+	border-width: 0px;
+	padding: 3px 8px;
+	font-size: 0.8em;
+	font-weight: 600;
+	@apply rounded-md dark:bg-gray-800 bg-gray-100 mx-0.5;
+}

src/app.html

@@ -1,4 +1,4 @@
-<!DOCTYPE html>
+<!doctype html>
 <html lang="en">
 	<head>
 		<meta charset="utf-8" />

src/lib/apis/audio/index.ts

@@ -131,3 +131,59 @@ export const synthesizeOpenAISpeech = async (
 
 	return res;
 };
+
+export const getModels = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${AUDIO_API_BASE_URL}/models`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err.detail;
+			console.log(err);
+
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};
+
+export const getVoices = async (token: string = '') => {
+	let error = null;
+
+	const res = await fetch(`${AUDIO_API_BASE_URL}/voices`, {
+		method: 'GET',
+		headers: {
+			'Content-Type': 'application/json',
+			Authorization: `Bearer ${token}`
+		}
+	})
+		.then(async (res) => {
+			if (!res.ok) throw await res.json();
+			return res.json();
+		})
+		.catch((err) => {
+			error = err.detail;
+			console.log(err);
+
+			return null;
+		});
+
+	if (error) {
+		throw error;
+	}
+
+	return res;
+};

src/lib/apis/chats/index.ts

@@ -32,10 +32,15 @@ export const createNewChat = async (token: string, chat: object) => {
 	return res;
 };
 
-export const getChatList = async (token: string = '') => {
+export const getChatList = async (token: string = '', page: number | null = null) => {
 	let error = null;
+	const searchParams = new URLSearchParams();
 
-	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/`, {
+	if (page !== null) {
+		searchParams.append('page', `${page}`);
+	}
+
+	const res = await fetch(`${WEBUI_API_BASE_URL}/chats/?${searchParams.toString()}`, {
 		method: 'GET',
 		headers: {
 			Accept: 'application/json',

src/lib/apis/index.ts

@@ -69,6 +69,7 @@ type ChatCompletedForm = {
 	model: string;
 	messages: string[];
 	chat_id: string;
+	session_id: string;
 };
 
 export const chatCompleted = async (token: string, body: ChatCompletedForm) => {

src/lib/apis/ollama/index.ts

@@ -1,5 +1,4 @@
 import { OLLAMA_API_BASE_URL } from '$lib/constants';
-import { titleGenerationTemplate } from '$lib/utils';
 
 export const getOllamaConfig = async (token: string = '') => {
 	let error = null;
@@ -203,55 +202,6 @@ export const getOllamaModels = async (token: string = '') => {
 		});
 };
 
-// TODO: migrate to backend
-export const generateTitle = async (
-	token: string = '',
-	template: string,
-	model: string,
-	prompt: string
-) => {
-	let error = null;
-
-	template = titleGenerationTemplate(template, prompt);
-
-	console.log(template);
-
-	const res = await fetch(`${OLLAMA_API_BASE_URL}/api/generate`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			model: model,
-			prompt: template,
-			stream: false,
-			options: {
-				// Restrict the number of tokens generated to 50
-				num_predict: 50
-			}
-		})
-	})
-		.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?.response.replace(/["']/g, '') ?? 'New Chat';
-};
-
 export const generatePrompt = async (token: string = '', model: string, conversation: string) => {
 	let error = null;
 

src/lib/apis/openai/index.ts

@@ -1,6 +1,4 @@
 import { OPENAI_API_BASE_URL } from '$lib/constants';
-import { titleGenerationTemplate } from '$lib/utils';
-import { type Model, models, settings } from '$lib/stores';
 
 export const getOpenAIConfig = async (token: string = '') => {
 	let error = null;
@@ -260,7 +258,7 @@ export const getOpenAIModelsDirect = async (
 		throw error;
 	}
 
-	const models = Array.isArray(res) ? res : res?.data ?? null;
+	const models = Array.isArray(res) ? res : (res?.data ?? null);
 
 	return models
 		.map((model) => ({ id: model.id, name: model.name ?? model.id, external: true }))
@@ -330,126 +328,3 @@ export const synthesizeOpenAISpeech = async (
 
 	return res;
 };
-
-export const generateTitle = async (
-	token: string = '',
-	template: string,
-	model: string,
-	prompt: string,
-	chat_id?: string,
-	url: string = OPENAI_API_BASE_URL
-) => {
-	let error = null;
-
-	template = titleGenerationTemplate(template, prompt);
-
-	console.log(template);
-
-	const res = await fetch(`${url}/chat/completions`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			model: model,
-			messages: [
-				{
-					role: 'user',
-					content: template
-				}
-			],
-			stream: false,
-			// Restricting the max tokens to 50 to avoid long titles
-			max_tokens: 50,
-			...(chat_id && { chat_id: chat_id }),
-			title: true
-		})
-	})
-		.then(async (res) => {
-			if (!res.ok) throw await res.json();
-			return res.json();
-		})
-		.catch((err) => {
-			console.log(err);
-			if ('detail' in err) {
-				error = err.detail;
-			}
-			return null;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res?.choices[0]?.message?.content.replace(/["']/g, '') ?? 'New Chat';
-};
-
-export const generateSearchQuery = async (
-	token: string = '',
-	model: string,
-	previousMessages: string[],
-	prompt: string,
-	url: string = OPENAI_API_BASE_URL
-): Promise<string | undefined> => {
-	let error = null;
-
-	// TODO: Allow users to specify the prompt
-	// Get the current date in the format "January 20, 2024"
-	const currentDate = new Intl.DateTimeFormat('en-US', {
-		year: 'numeric',
-		month: 'long',
-		day: '2-digit'
-	}).format(new Date());
-
-	const res = await fetch(`${url}/chat/completions`, {
-		method: 'POST',
-		headers: {
-			Accept: 'application/json',
-			'Content-Type': 'application/json',
-			Authorization: `Bearer ${token}`
-		},
-		body: JSON.stringify({
-			model: model,
-			// Few shot prompting
-			messages: [
-				{
-					role: 'assistant',
-					content: `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 ${currentDate}.`
-				},
-				{
-					role: 'user',
-					content: prompt
-				}
-				// {
-				// 	role: 'user',
-				// 	content:
-				// 		(previousMessages.length > 0
-				// 			? `Previous Questions:\n${previousMessages.join('\n')}\n\n`
-				// 			: '') + `Current Question: ${prompt}`
-				// }
-			],
-			stream: false,
-			// Restricting the max tokens to 30 to avoid long search queries
-			max_tokens: 30
-		})
-	})
-		.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 undefined;
-		});
-
-	if (error) {
-		throw error;
-	}
-
-	return res?.choices[0]?.message?.content.replace(/["']/g, '') ?? undefined;
-};

src/lib/components/ChangelogModal.svelte

@@ -75,12 +75,12 @@
 										class="font-semibold uppercase text-xs {section === 'added'
 											? 'text-white bg-blue-600'
 											: section === 'fixed'
-											? 'text-white bg-green-600'
-											: section === 'changed'
-											? 'text-white bg-yellow-600'
-											: section === 'removed'
-											? 'text-white bg-red-600'
-											: ''}  w-fit px-3 rounded-full my-2.5"
+												? 'text-white bg-green-600'
+												: section === 'changed'
+													? 'text-white bg-yellow-600'
+													: section === 'removed'
+														? 'text-white bg-red-600'
+														: ''}  w-fit px-3 rounded-full my-2.5"
 									>
 										{section}
 									</div>

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

@@ -1,13 +1,19 @@
 <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';
-	import SensitiveInput from '$lib/components/common/SensitiveInput.svelte';
+	import { createEventDispatcher, onMount, getContext } from 'svelte';
 	const dispatch = createEventDispatcher();
 
+	import { getBackendConfig } from '$lib/apis';
+	import {
+		getAudioConfig,
+		updateAudioConfig,
+		getModels as _getModels,
+		getVoices as _getVoices
+	} from '$lib/apis/audio';
+	import { user, settings, config } from '$lib/stores';
+
+	import SensitiveInput from '$lib/components/common/SensitiveInput.svelte';
+
 	const i18n = getContext('i18n');
 
 	export let saveHandler: Function;
@@ -16,6 +22,7 @@
 
 	let TTS_OPENAI_API_BASE_URL = '';
 	let TTS_OPENAI_API_KEY = '';
+	let TTS_API_KEY = '';
 	let TTS_ENGINE = '';
 	let TTS_MODEL = '';
 	let TTS_VOICE = '';
@@ -29,30 +36,41 @@
 	let models = [];
 	let nonLocalVoices = false;
 
-	const getOpenAIVoices = () => {
-		voices = [
-			{ name: 'alloy' },
-			{ name: 'echo' },
-			{ name: 'fable' },
-			{ name: 'onyx' },
-			{ name: 'nova' },
-			{ name: 'shimmer' }
-		];
-	};
+	const getModels = async () => {
+		if (TTS_ENGINE === '') {
+			models = [];
+		} else {
+			const res = await _getModels(localStorage.token).catch((e) => {
+				toast.error(e);
+			});
 
-	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);
+			if (res) {
+				console.log(res);
+				models = res.models;
 			}
-		}, 100);
+		}
+	};
+
+	const getVoices = async () => {
+		if (TTS_ENGINE === '') {
+			const getVoicesLoop = setInterval(async () => {
+				voices = await speechSynthesis.getVoices();
+
+				// do your loop
+				if (voices.length > 0) {
+					clearInterval(getVoicesLoop);
+				}
+			}, 100);
+		} else {
+			const res = await _getVoices(localStorage.token).catch((e) => {
+				toast.error(e);
+			});
+
+			if (res) {
+				console.log(res);
+				voices = res.voices;
+			}
+		}
 	};
 
 	const updateConfigHandler = async () => {
@@ -60,6 +78,7 @@
 			tts: {
 				OPENAI_API_BASE_URL: TTS_OPENAI_API_BASE_URL,
 				OPENAI_API_KEY: TTS_OPENAI_API_KEY,
+				API_KEY: TTS_API_KEY,
 				ENGINE: TTS_ENGINE,
 				MODEL: TTS_MODEL,
 				VOICE: TTS_VOICE
@@ -86,6 +105,7 @@
 			console.log(res);
 			TTS_OPENAI_API_BASE_URL = res.tts.OPENAI_API_BASE_URL;
 			TTS_OPENAI_API_KEY = res.tts.OPENAI_API_KEY;
+			TTS_API_KEY = res.tts.API_KEY;
 
 			TTS_ENGINE = res.tts.ENGINE;
 			TTS_MODEL = res.tts.MODEL;
@@ -98,12 +118,8 @@
 			STT_MODEL = res.stt.MODEL;
 		}
 
-		if (TTS_ENGINE === 'openai') {
-			getOpenAIVoices();
-			getOpenAIModels();
-		} else {
-			getWebAPIVoices();
-		}
+		await getVoices();
+		await getModels();
 	});
 </script>
 
@@ -138,7 +154,7 @@
 					<div>
 						<div class="mt-1 flex gap-2 mb-1">
 							<input
-								class="flex-1 w-full rounded-l-lg py-2 pl-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+								class="flex-1 w-full rounded-lg py-2 pl-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
 								placeholder={$i18n.t('API Base URL')}
 								bind:value={STT_OPENAI_API_BASE_URL}
 								required
@@ -182,19 +198,23 @@
 							class=" dark:bg-gray-900 w-fit pr-8 rounded px-2 p-1 text-xs bg-transparent outline-none text-right"
 							bind:value={TTS_ENGINE}
 							placeholder="Select a mode"
-							on:change={(e) => {
+							on:change={async (e) => {
+								await updateConfigHandler();
+								await getVoices();
+								await getModels();
+
 								if (e.target.value === 'openai') {
-									getOpenAIVoices();
 									TTS_VOICE = 'alloy';
 									TTS_MODEL = 'tts-1';
 								} else {
-									getWebAPIVoices();
 									TTS_VOICE = '';
+									TTS_MODEL = '';
 								}
 							}}
 						>
 							<option value="">{$i18n.t('Web API')}</option>
 							<option value="openai">{$i18n.t('OpenAI')}</option>
+							<option value="elevenlabs">{$i18n.t('ElevenLabs')}</option>
 						</select>
 					</div>
 				</div>
@@ -203,7 +223,7 @@
 					<div>
 						<div class="mt-1 flex gap-2 mb-1">
 							<input
-								class="flex-1 w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+								class="flex-1 w-full rounded-lg py-2 pl-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
 								placeholder={$i18n.t('API Base URL')}
 								bind:value={TTS_OPENAI_API_BASE_URL}
 								required
@@ -212,6 +232,17 @@
 							<SensitiveInput placeholder={$i18n.t('API Key')} bind:value={TTS_OPENAI_API_KEY} />
 						</div>
 					</div>
+				{:else if TTS_ENGINE === 'elevenlabs'}
+					<div>
+						<div class="mt-1 flex gap-2 mb-1">
+							<input
+								class="flex-1 w-full rounded-lg py-2 pl-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+								placeholder={$i18n.t('API Key')}
+								bind:value={TTS_API_KEY}
+								required
+							/>
+						</div>
+					</div>
 				{/if}
 
 				<hr class=" dark:border-gray-850 my-2" />
@@ -252,7 +283,7 @@
 
 									<datalist id="voice-list">
 										{#each voices as voice}
-											<option value={voice.name} />
+											<option value={voice.id}>{voice.name}</option>
 										{/each}
 									</datalist>
 								</div>
@@ -263,15 +294,56 @@
 							<div class="flex w-full">
 								<div class="flex-1">
 									<input
-										list="model-list"
+										list="tts-model-list"
 										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
 										bind:value={TTS_MODEL}
 										placeholder="Select a model"
 									/>
 
-									<datalist id="model-list">
+									<datalist id="tts-model-list">
 										{#each models as model}
-											<option value={model.name} />
+											<option value={model.id} />
+										{/each}
+									</datalist>
+								</div>
+							</div>
+						</div>
+					</div>
+				{:else if TTS_ENGINE === 'elevenlabs'}
+					<div class=" flex gap-2">
+						<div class="w-full">
+							<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Voice')}</div>
+							<div class="flex w-full">
+								<div class="flex-1">
+									<input
+										list="voice-list"
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+										bind:value={TTS_VOICE}
+										placeholder="Select a voice"
+									/>
+
+									<datalist id="voice-list">
+										{#each voices as voice}
+											<option value={voice.id}>{voice.name}</option>
+										{/each}
+									</datalist>
+								</div>
+							</div>
+						</div>
+						<div class="w-full">
+							<div class=" mb-1.5 text-sm font-medium">{$i18n.t('TTS Model')}</div>
+							<div class="flex w-full">
+								<div class="flex-1">
+									<input
+										list="tts-model-list"
+										class="w-full rounded-lg py-2 px-4 text-sm bg-gray-50 dark:text-gray-300 dark:bg-gray-850 outline-none"
+										bind:value={TTS_MODEL}
+										placeholder="Select a model"
+									/>
+
+									<datalist id="tts-model-list">
+										{#each models as model}
+											<option value={model.id} />
 										{/each}
 									</datalist>
 								</div>

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

@@ -112,7 +112,7 @@
 							url: OpenAIUrl,
 							batch_size: OpenAIBatchSize
 						}
-				  }
+					}
 				: {})
 		}).catch(async (error) => {
 			toast.error(error);
@@ -269,7 +269,7 @@
 		saveHandler();
 	}}
 >
-	<div class=" space-y-2.5 overflow-y-scroll scrollbar-hidden h-full">
+	<div class=" space-y-2.5 overflow-y-scroll scrollbar-hidden h-full pr-1.5">
 		<div class="flex flex-col gap-0.5">
 			<div class=" mb-0.5 text-sm font-medium">{$i18n.t('General Settings')}</div>
 
@@ -615,7 +615,7 @@
 		<div class=" ">
 			<div class=" text-sm font-medium">{$i18n.t('Query Params')}</div>
 
-			<div class=" flex">
+			<div class=" flex gap-1">
 				<div class="  flex w-full justify-between">
 					<div class="self-center text-xs font-medium min-w-fit">{$i18n.t('Top K')}</div>
 
@@ -632,7 +632,7 @@
 				</div>
 
 				{#if querySettings.hybrid === true}
-					<div class="flex w-full">
+					<div class="  flex w-full justify-between">
 						<div class=" self-center text-xs font-medium min-w-fit">
 							{$i18n.t('Minimum Score')}
 						</div>

src/lib/components/chat/Chat.svelte

@@ -25,7 +25,8 @@
 		user,
 		socket,
 		showCallOverlay,
-		tools
+		tools,
+		currentChatPage
 	} from '$lib/stores';
 	import {
 		convertMessagesToHistory,
@@ -80,6 +81,7 @@
 	let eventConfirmationMessage = '';
 	let eventConfirmationInput = false;
 	let eventConfirmationInputPlaceholder = '';
+	let eventConfirmationInputValue = '';
 	let eventCallback = null;
 
 	let showModelSelector = true;
@@ -108,7 +110,6 @@
 	};
 
 	let params = {};
-	let valves = {};
 
 	$: if (history.currentId !== null) {
 		let _messages = [];
@@ -182,6 +183,7 @@
 				eventConfirmationTitle = data.title;
 				eventConfirmationMessage = data.message;
 				eventConfirmationInputPlaceholder = data.placeholder;
+				eventConfirmationInputValue = data?.value ?? '';
 			} else {
 				console.log('Unknown message type', data);
 			}
@@ -281,6 +283,10 @@
 
 		if ($page.url.searchParams.get('q')) {
 			prompt = $page.url.searchParams.get('q') ?? '';
+			selectedToolIds = ($page.url.searchParams.get('tool_ids') ?? '')
+				.split(',')
+				.map((id) => id.trim())
+				.filter((id) => id);
 
 			if (prompt) {
 				await tick();
@@ -416,7 +422,9 @@
 					params: params,
 					files: chatFiles
 				});
-				await chats.set(await getChatList(localStorage.token));
+
+				currentChatPage.set(1);
+				await chats.set(await getChatList(localStorage.token, $currentChatPage));
 			}
 		}
 	};
@@ -462,7 +470,9 @@
 					params: params,
 					files: chatFiles
 				});
-				await chats.set(await getChatList(localStorage.token));
+
+				currentChatPage.set(1);
+				await chats.set(await getChatList(localStorage.token, $currentChatPage));
 			}
 		}
 	};
@@ -569,8 +579,8 @@
 		let selectedModelIds = modelId
 			? [modelId]
 			: atSelectedModel !== undefined
-			? [atSelectedModel.id]
-			: selectedModels;
+				? [atSelectedModel.id]
+				: selectedModels;
 
 		// Create response messages for each selected model
 		const responseMessageIds = {};
@@ -622,7 +632,9 @@
 					tags: [],
 					timestamp: Date.now()
 				});
-				await chats.set(await getChatList(localStorage.token));
+
+				currentChatPage.set(1);
+				await chats.set(await getChatList(localStorage.token, $currentChatPage));
 				await chatId.set(chat.id);
 			} else {
 				await chatId.set('local');
@@ -698,7 +710,9 @@
 			})
 		);
 
-		await chats.set(await getChatList(localStorage.token));
+		currentChatPage.set(1);
+		await chats.set(await getChatList(localStorage.token, $currentChatPage));
+
 		return _responses;
 	};
 
@@ -706,6 +720,7 @@
 		let _response = null;
 
 		const responseMessage = history.messages[responseMessageId];
+		const userMessage = history.messages[responseMessage.parentId];
 
 		// Wait until history/message have been updated
 		await tick();
@@ -724,11 +739,11 @@
 								? await getAndUpdateUserLocation(localStorage.token)
 								: undefined
 						)}${
-							responseMessage?.userContext ?? null
+							(responseMessage?.userContext ?? null)
 								? `\n\nUser Context:\n${responseMessage?.userContext ?? ''}`
 								: ''
 						}`
-				  }
+					}
 				: undefined,
 			...messages
 		]
@@ -772,11 +787,12 @@
 		if (model?.info?.meta?.knowledge ?? false) {
 			files.push(...model.info.meta.knowledge);
 		}
-		if (responseMessage?.files) {
-			files.push(
-				...responseMessage?.files.filter((item) => ['web_search_results'].includes(item.type))
-			);
-		}
+		files.push(
+			...(userMessage?.files ?? []).filter((item) =>
+				['doc', 'file', 'collection'].includes(item.type)
+			),
+			...(responseMessage?.files ?? []).filter((item) => ['web_search_results'].includes(item.type))
+		);
 
 		eventTarget.dispatchEvent(
 			new CustomEvent('chat:start', {
@@ -795,10 +811,10 @@
 			options: {
 				...(params ?? $settings.params ?? {}),
 				stop:
-					params?.stop ?? $settings?.params?.stop ?? undefined
-						? (params?.stop ?? $settings.params.stop).map((str) =>
-								decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
-						  )
+					(params?.stop ?? $settings?.params?.stop ?? undefined)
+						? (params?.stop.split(',').map((token) => token.trim()) ?? $settings.params.stop).map(
+								(str) => decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
+							)
 						: undefined,
 				num_predict: params?.max_tokens ?? $settings?.params?.max_tokens ?? undefined,
 				repeat_penalty:
@@ -808,7 +824,6 @@
 			keep_alive: $settings.keepAlive ?? undefined,
 			tool_ids: selectedToolIds.length > 0 ? selectedToolIds : undefined,
 			files: files.length > 0 ? files : undefined,
-			...(Object.keys(valves).length ? { valves } : {}),
 			session_id: $socket?.id,
 			chat_id: $chatId,
 			id: responseMessageId
@@ -862,6 +877,10 @@
 								} else {
 									responseMessage.content += data.message.content;
 
+									if (navigator.vibrate && ($settings?.hapticFeedback ?? false)) {
+										navigator.vibrate(5);
+									}
+
 									const sentences = extractSentencesForAudio(responseMessage.content);
 									sentences.pop();
 
@@ -943,7 +962,9 @@
 						params: params,
 						files: chatFiles
 					});
-					await chats.set(await getChatList(localStorage.token));
+
+					currentChatPage.set(1);
+					await chats.set(await getChatList(localStorage.token, $currentChatPage));
 				}
 			}
 		} else {
@@ -1006,17 +1027,20 @@
 
 	const sendPromptOpenAI = async (model, userPrompt, responseMessageId, _chatId) => {
 		let _response = null;
+
 		const responseMessage = history.messages[responseMessageId];
+		const userMessage = history.messages[responseMessage.parentId];
 
 		let files = JSON.parse(JSON.stringify(chatFiles));
 		if (model?.info?.meta?.knowledge ?? false) {
 			files.push(...model.info.meta.knowledge);
 		}
-		if (responseMessage?.files) {
-			files.push(
-				...responseMessage?.files.filter((item) => ['web_search_results'].includes(item.type))
-			);
-		}
+		files.push(
+			...(userMessage?.files ?? []).filter((item) =>
+				['doc', 'file', 'collection'].includes(item.type)
+			),
+			...(responseMessage?.files ?? []).filter((item) => ['web_search_results'].includes(item.type))
+		);
 
 		scrollToBottom();
 
@@ -1036,10 +1060,10 @@
 					stream: true,
 					model: model.id,
 					stream_options:
-						model.info?.meta?.capabilities?.usage ?? false
+						(model.info?.meta?.capabilities?.usage ?? false)
 							? {
 									include_usage: true
-							  }
+								}
 							: undefined,
 					messages: [
 						params?.system || $settings.system || (responseMessage?.userContext ?? null)
@@ -1052,11 +1076,11 @@
 											? await getAndUpdateUserLocation(localStorage.token)
 											: undefined
 									)}${
-										responseMessage?.userContext ?? null
+										(responseMessage?.userContext ?? null)
 											? `\n\nUser Context:\n${responseMessage?.userContext ?? ''}`
 											: ''
 									}`
-							  }
+								}
 							: undefined,
 						...messages
 					]
@@ -1072,7 +1096,7 @@
 												text:
 													arr.length - 1 !== idx
 														? message.content
-														: message?.raContent ?? message.content
+														: (message?.raContent ?? message.content)
 											},
 											...message.files
 												.filter((file) => file.type === 'image')
@@ -1083,20 +1107,20 @@
 													}
 												}))
 										]
-								  }
+									}
 								: {
 										content:
 											arr.length - 1 !== idx
 												? message.content
-												: message?.raContent ?? message.content
-								  })
+												: (message?.raContent ?? message.content)
+									})
 						})),
 					seed: params?.seed ?? $settings?.params?.seed ?? undefined,
 					stop:
-						params?.stop ?? $settings?.params?.stop ?? undefined
-							? (params?.stop ?? $settings.params.stop).map((str) =>
-									decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
-							  )
+						(params?.stop ?? $settings?.params?.stop ?? undefined)
+							? (params?.stop.split(',').map((token) => token.trim()) ?? $settings.params.stop).map(
+									(str) => decodeURIComponent(JSON.parse('"' + str.replace(/\"/g, '\\"') + '"'))
+								)
 							: undefined,
 					temperature: params?.temperature ?? $settings?.params?.temperature ?? undefined,
 					top_p: params?.top_p ?? $settings?.params?.top_p ?? undefined,
@@ -1105,7 +1129,6 @@
 					max_tokens: params?.max_tokens ?? $settings?.params?.max_tokens ?? undefined,
 					tool_ids: selectedToolIds.length > 0 ? selectedToolIds : undefined,
 					files: files.length > 0 ? files : undefined,
-					...(Object.keys(valves).length ? { valves } : {}),
 					session_id: $socket?.id,
 					chat_id: $chatId,
 					id: responseMessageId
@@ -1120,7 +1143,6 @@
 
 			if (res && res.ok && res.body) {
 				const textStream = await createOpenAITextStream(res.body, $settings.splitLargeChunks);
-				let lastUsage = null;
 
 				for await (const update of textStream) {
 					const { value, done, citations, error, usage } = update;
@@ -1146,7 +1168,7 @@
 					}
 
 					if (usage) {
-						lastUsage = usage;
+						responseMessage.info = { ...usage, openai: true };
 					}
 
 					if (citations) {
@@ -1159,6 +1181,10 @@
 					} else {
 						responseMessage.content += value;
 
+						if (navigator.vibrate && ($settings?.hapticFeedback ?? false)) {
+							navigator.vibrate(5);
+						}
+
 						const sentences = extractSentencesForAudio(responseMessage.content);
 						sentences.pop();
 
@@ -1200,10 +1226,6 @@
 					document.getElementById(`speak-button-${responseMessage.id}`)?.click();
 				}
 
-				if (lastUsage) {
-					responseMessage.info = { ...lastUsage, openai: true };
-				}
-
 				if ($chatId == _chatId) {
 					if ($settings.saveChatHistory ?? true) {
 						chat = await updateChatById(localStorage.token, _chatId, {
@@ -1213,7 +1235,9 @@
 							params: params,
 							files: chatFiles
 						});
-						await chats.set(await getChatList(localStorage.token));
+
+						currentChatPage.set(1);
+						await chats.set(await getChatList(localStorage.token, $currentChatPage));
 					}
 				}
 			} else {
@@ -1378,7 +1402,9 @@
 
 		if ($settings.saveChatHistory ?? true) {
 			chat = await updateChatById(localStorage.token, _chatId, { title: _title });
-			await chats.set(await getChatList(localStorage.token));
+
+			currentChatPage.set(1);
+			await chats.set(await getChatList(localStorage.token, $currentChatPage));
 		}
 	};
 
@@ -1484,6 +1510,7 @@
 	message={eventConfirmationMessage}
 	input={eventConfirmationInput}
 	inputPlaceholder={eventConfirmationInputPlaceholder}
+	inputValue={eventConfirmationInputValue}
 	on:confirm={(e) => {
 		if (e.detail) {
 			eventCallback(e.detail);
@@ -1631,7 +1658,6 @@
 			bind:show={showControls}
 			bind:chatFiles
 			bind:params
-			bind:valves
 		/>
 	</div>
 {/if}

src/lib/components/chat/ChatControls.svelte

@@ -9,9 +9,7 @@
 	export let models = [];
 
 	export let chatId = null;
-
 	export let chatFiles = [];
-	export let valves = {};
 	export let params = {};
 
 	let largeScreen = false;
@@ -50,7 +48,6 @@
 						}}
 						{models}
 						bind:chatFiles
-						bind:valves
 						bind:params
 					/>
 				</div>
@@ -66,7 +63,6 @@
 				}}
 				{models}
 				bind:chatFiles
-				bind:valves
 				bind:params
 			/>
 		</div>

src/lib/components/chat/Controls/Controls.svelte

@@ -5,13 +5,15 @@
 
 	import XMark from '$lib/components/icons/XMark.svelte';
 	import AdvancedParams from '../Settings/Advanced/AdvancedParams.svelte';
-	import Valves from '$lib/components/common/Valves.svelte';
+	import Valves from '$lib/components/chat/Controls/Valves.svelte';
 	import FileItem from '$lib/components/common/FileItem.svelte';
+	import Collapsible from '$lib/components/common/Collapsible.svelte';
+
+	import { user } from '$lib/stores';
 
 	export let models = [];
 
 	export let chatFiles = [];
-	export let valves = {};
 	export let params = {};
 </script>
 
@@ -28,64 +30,59 @@
 		</button>
 	</div>
 
-	<div class=" dark:text-gray-200 text-sm font-primary">
+	<div class=" dark:text-gray-200 text-sm font-primary py-0.5">
 		{#if chatFiles.length > 0}
-			<div>
-				<div class="mb-1.5 font-medium">{$i18n.t('Files')}</div>
-
-				<div>
-					{#each chatFiles as file}
+			<Collapsible title={$i18n.t('Files')} open={true}>
+				<div class="flex flex-col gap-1 mt-1.5" slot="content">
+					{#each chatFiles as file, fileIdx}
 						<FileItem
 							className="w-full"
 							url={`${file?.url}`}
 							name={file.name}
 							type={file.type}
+							size={file?.size}
 							dismissible={true}
 							on:dismiss={() => {
 								// Remove the file from the chatFiles array
-								chatFiles = chatFiles.filter((f) => f.id !== file.id);
+
+								chatFiles.splice(fileIdx, 1);
+								chatFiles = chatFiles;
 							}}
 						/>
 					{/each}
 				</div>
-			</div>
+			</Collapsible>
 
 			<hr class="my-2 border-gray-100 dark:border-gray-800" />
 		{/if}
 
-		{#if models.length === 1 && models[0]?.pipe?.valves_spec}
-			<div>
-				<div class=" font-medium">{$i18n.t('Valves')}</div>
-
-				<div>
-					<Valves valvesSpec={models[0]?.pipe?.valves_spec} bind:valves />
-				</div>
+		<Collapsible title={$i18n.t('Valves')}>
+			<div class="text-sm mt-1.5" slot="content">
+				<Valves />
 			</div>
-
-			<hr class="my-2 border-gray-100 dark:border-gray-800" />
-		{/if}
-
-		<div>
-			<div class="mb-1.5 font-medium">{$i18n.t('System Prompt')}</div>
-
-			<div>
-				<textarea
-					bind:value={params.system}
-					class="w-full rounded-lg px-4 py-3 text-sm dark:text-gray-300 dark:bg-gray-850 border border-gray-100 dark:border-gray-800 outline-none resize-none"
-					rows="3"
-					placeholder={$i18n.t('Enter system prompt')}
-				/>
-			</div>
-		</div>
+		</Collapsible>
 
 		<hr class="my-2 border-gray-100 dark:border-gray-800" />
 
-		<div>
-			<div class="mb-1.5 font-medium">{$i18n.t('Advanced Params')}</div>
-
-			<div>
-				<AdvancedParams bind:params />
+		<Collapsible title={$i18n.t('System Prompt')} open={true}>
+			<div class=" mt-1.5" slot="content">
+				<textarea
+					bind:value={params.system}
+					class="w-full rounded-lg px-3.5 py-2.5 text-sm dark:text-gray-300 dark:bg-gray-850 border border-gray-100 dark:border-gray-800 outline-none resize-none"
+					rows="4"
+					placeholder={$i18n.t('Enter system prompt')}
+				/>
 			</div>
-		</div>
+		</Collapsible>
+
+		<hr class="my-2 border-gray-100 dark:border-gray-800" />
+
+		<Collapsible title={$i18n.t('Advanced Params')} open={true}>
+			<div class="text-sm mt-1.5" slot="content">
+				<div>
+					<AdvancedParams admin={$user?.role === 'admin'} bind:params />
+				</div>
+			</div>
+		</Collapsible>
 	</div>
 </div>

src/lib/components/chat/Controls/Valves.svelte

@@ -15,18 +15,14 @@
 		updateUserValvesById as updateFunctionUserValvesById
 	} from '$lib/apis/functions';
 
-	import ManageModal from './Personalization/ManageModal.svelte';
 	import Tooltip from '$lib/components/common/Tooltip.svelte';
 	import Spinner from '$lib/components/common/Spinner.svelte';
-	import Switch from '$lib/components/common/Switch.svelte';
 	import Valves from '$lib/components/common/Valves.svelte';
 
 	const dispatch = createEventDispatcher();
 
 	const i18n = getContext('i18n');
 
-	export let saveSettings: Function;
-
 	let tab = 'tools';
 	let selectedId = '';
 
@@ -35,6 +31,19 @@
 	let valvesSpec = null;
 	let valves = {};
 
+	let debounceTimer;
+
+	const debounceSubmitHandler = async () => {
+		if (debounceTimer) {
+			clearTimeout(debounceTimer);
+		}
+
+		// Set a new timer
+		debounceTimer = setTimeout(() => {
+			submitHandler();
+		}, 500); // 0.5 second debounce
+	};
+
 	const getUserValves = async () => {
 		loading = true;
 		if (tab === 'tools') {
@@ -112,53 +121,45 @@
 		dispatch('save');
 	}}
 >
-	<div class="flex flex-col pr-1.5 overflow-y-scroll max-h-[25rem]">
-		<div>
-			<div class="flex items-center justify-between mb-2">
-				<Tooltip content="">
-					<div class="text-sm font-medium">
-						{$i18n.t('Manage Valves')}
-					</div>
-				</Tooltip>
-
-				<div class=" self-end">
-					<select
-						class=" dark:bg-gray-900 w-fit pr-8 rounded text-xs bg-transparent outline-none text-right"
-						bind:value={tab}
-						placeholder="Select"
-					>
-						<option value="tools">{$i18n.t('Tools')}</option>
-						<option value="functions">{$i18n.t('Functions')}</option>
-					</select>
-				</div>
-			</div>
-		</div>
-
+	<div class="flex flex-col">
 		<div class="space-y-1">
 			<div class="flex gap-2">
 				<div class="flex-1">
 					<select
-						class="w-full rounded-lg py-2 px-4 text-sm dark:text-gray-300 dark:bg-gray-850 outline-none"
+						class="  w-full rounded text-xs py-2 px-1 bg-transparent outline-none"
+						bind:value={tab}
+						placeholder="Select"
+					>
+						<option value="tools" class="bg-gray-100 dark:bg-gray-800">{$i18n.t('Tools')}</option>
+						<option value="functions" class="bg-gray-100 dark:bg-gray-800"
+							>{$i18n.t('Functions')}</option
+						>
+					</select>
+				</div>
+
+				<div class="flex-1">
+					<select
+						class="w-full rounded py-2 px-1 text-xs bg-transparent outline-none"
 						bind:value={selectedId}
 						on:change={async () => {
 							await tick();
 						}}
 					>
 						{#if tab === 'tools'}
-							<option value="" selected disabled class="bg-gray-100 dark:bg-gray-700"
+							<option value="" selected disabled class="bg-gray-100 dark:bg-gray-800"
 								>{$i18n.t('Select a tool')}</option
 							>
 
 							{#each $tools as tool, toolIdx}
-								<option value={tool.id} class="bg-gray-100 dark:bg-gray-700">{tool.name}</option>
+								<option value={tool.id} class="bg-gray-100 dark:bg-gray-800">{tool.name}</option>
 							{/each}
 						{:else if tab === 'functions'}
-							<option value="" selected disabled class="bg-gray-100 dark:bg-gray-700"
+							<option value="" selected disabled class="bg-gray-100 dark:bg-gray-800"
 								>{$i18n.t('Select a function')}</option
 							>
 
 							{#each $functions as func, funcIdx}
-								<option value={func.id} class="bg-gray-100 dark:bg-700">{func.name}</option>
+								<option value={func.id} class="bg-gray-100 dark:bg-gray-800">{func.name}</option>
 							{/each}
 						{/if}
 					</select>
@@ -167,24 +168,21 @@
 		</div>
 
 		{#if selectedId}
-			<hr class="dark:border-gray-800 my-3 w-full" />
+			<hr class="dark:border-gray-800 my-1 w-full" />
 
-			<div>
+			<div class="my-2 text-xs">
 				{#if !loading}
-					<Valves {valvesSpec} bind:valves />
+					<Valves
+						{valvesSpec}
+						bind:valves
+						on:change={() => {
+							debounceSubmitHandler();
+						}}
+					/>
 				{:else}
 					<Spinner className="size-5" />
 				{/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/chat/MessageInput.svelte

@@ -98,6 +98,7 @@
 
 	const uploadFileHandler = async (file) => {
 		console.log(file);
+
 		// Check if the file is an audio file and transcribe/convert it to text file
 		if (['audio/mpeg', 'audio/wav'].includes(file['type'])) {
 			const res = await transcribeAudio(localStorage.token, file).catch((error) => {
@@ -112,40 +113,49 @@
 			}
 		}
 
-		// Upload the file to the server
-		const uploadedFile = await uploadFile(localStorage.token, file).catch((error) => {
-			toast.error(error);
-			return null;
-		});
+		const fileItem = {
+			type: 'file',
+			file: '',
+			id: null,
+			url: '',
+			name: file.name,
+			collection_name: '',
+			status: '',
+			size: file.size,
+			error: ''
+		};
+		files = [...files, fileItem];
 
-		if (uploadedFile) {
-			const fileItem = {
-				type: 'file',
-				file: uploadedFile,
-				id: uploadedFile.id,
-				url: `${WEBUI_API_BASE_URL}/files/${uploadedFile.id}`,
-				name: file.name,
-				collection_name: '',
-				status: 'uploaded',
-				error: ''
-			};
-			files = [...files, fileItem];
+		try {
+			const uploadedFile = await uploadFile(localStorage.token, file);
 
-			// TODO: Check if tools & functions have files support to skip this step to delegate file processing
-			// Default Upload to VectorDB
-			if (
-				SUPPORTED_FILE_TYPE.includes(file['type']) ||
-				SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
-			) {
-				processFileItem(fileItem);
+			if (uploadedFile) {
+				fileItem.status = 'uploaded';
+				fileItem.file = uploadedFile;
+				fileItem.id = uploadedFile.id;
+				fileItem.url = `${WEBUI_API_BASE_URL}/files/${uploadedFile.id}`;
+
+				// TODO: Check if tools & functions have files support to skip this step to delegate file processing
+				// Default Upload to VectorDB
+				if (
+					SUPPORTED_FILE_TYPE.includes(file['type']) ||
+					SUPPORTED_FILE_EXTENSIONS.includes(file.name.split('.').at(-1))
+				) {
+					processFileItem(fileItem);
+				} else {
+					toast.error(
+						$i18n.t(`Unknown file type '{{file_type}}'. Proceeding with the file upload anyway.`, {
+							file_type: file['type']
+						})
+					);
+					processFileItem(fileItem);
+				}
 			} else {
-				toast.error(
-					$i18n.t(`Unknown file type '{{file_type}}'. Proceeding with the file upload anyway.`, {
-						file_type: file['type']
-					})
-				);
-				processFileItem(fileItem);
+				files = files.filter((item) => item.status !== null);
 			}
+		} catch (e) {
+			toast.error(e);
+			files = files.filter((item) => item.status !== null);
 		}
 	};
 
@@ -162,7 +172,6 @@
 			// Remove the failed doc from the files array
 			// files = files.filter((f) => f.id !== fileItem.id);
 			toast.error(e);
-
 			fileItem.status = 'processed';
 			files = files;
 		}
@@ -375,7 +384,7 @@
 
 				{#if atSelectedModel !== undefined}
 					<div
-						class="px-3 py-2.5 text-left w-full flex justify-between items-center absolute bottom-0 left-0 right-0 bg-gradient-to-t from-50% from-white dark:from-gray-900"
+						class="px-3 py-2.5 text-left w-full flex justify-between items-center absolute bottom-0 left-0 right-0 bg-gradient-to-t from-50% from-white dark:from-gray-900 z-50"
 					>
 						<div class="flex items-center gap-2 text-sm dark:text-gray-500">
 							<img
@@ -545,6 +554,7 @@
 											<FileItem
 												name={file.name}
 												type={file.type}
+												size={file?.size}
 												status={file.status}
 												dismissible={true}
 												on:dismiss={() => {

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

@@ -609,10 +609,10 @@
 								style="font-size:{rmsLevel * 100 > 4
 									? '4.5'
 									: rmsLevel * 100 > 2
-									? '4.25'
-									: rmsLevel * 100 > 1
-									? '3.75'
-									: '3.5'}rem;width: 100%; text-align:center;"
+										? '4.25'
+										: rmsLevel * 100 > 1
+											? '3.75'
+											: '3.5'}rem;width: 100%; text-align:center;"
 							>
 								{emoji}
 							</div>
@@ -658,10 +658,10 @@
 								class=" {rmsLevel * 100 > 4
 									? ' size-[4.5rem]'
 									: rmsLevel * 100 > 2
-									? ' size-16'
-									: rmsLevel * 100 > 1
-									? 'size-14'
-									: 'size-12'}  transition-all rounded-full {(model?.info?.meta
+										? ' size-16'
+										: rmsLevel * 100 > 1
+											? 'size-14'
+											: 'size-12'}  transition-all rounded-full {(model?.info?.meta
 									?.profile_image_url ?? '/static/favicon.png') !== '/static/favicon.png'
 									? ' bg-cover bg-center bg-no-repeat'
 									: 'bg-black dark:bg-white'}  bg-black dark:bg-white"
@@ -691,10 +691,10 @@
 									style="font-size:{rmsLevel * 100 > 4
 										? '13'
 										: rmsLevel * 100 > 2
-										? '12'
-										: rmsLevel * 100 > 1
-										? '11.5'
-										: '11'}rem;width:100%;text-align:center;"
+											? '12'
+											: rmsLevel * 100 > 1
+												? '11.5'
+												: '11'}rem;width:100%;text-align:center;"
 								>
 									{emoji}
 								</div>
@@ -740,10 +740,10 @@
 									class=" {rmsLevel * 100 > 4
 										? ' size-52'
 										: rmsLevel * 100 > 2
-										? 'size-48'
-										: rmsLevel * 100 > 1
-										? 'size-[11.5rem]'
-										: 'size-44'}  transition-all rounded-full {(model?.info?.meta
+											? 'size-48'
+											: rmsLevel * 100 > 1
+												? 'size-[11.5rem]'
+												: 'size-44'}  transition-all rounded-full {(model?.info?.meta
 										?.profile_image_url ?? '/static/favicon.png') !== '/static/favicon.png'
 										? ' bg-cover bg-center bg-no-repeat'
 										: 'bg-black dark:bg-white'} "

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

@@ -27,7 +27,7 @@
 						title: $i18n.t('All Documents'),
 						collection_names: $documents.map((doc) => doc.collection_name)
 					}
-			  ]
+				]
 			: []),
 		...$documents
 			.reduce((a, e, i, arr) => {

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

@@ -147,8 +147,8 @@
 					<div class="m-1 overflow-y-auto p-1 rounded-r-lg space-y-0.5 scrollbar-hidden">
 						{#each filteredModels as model, modelIdx}
 							<button
-								class=" px-3 py-1.5 rounded-xl w-full text-left {modelIdx === selectedIdx
-									? '  bg-gray-50 dark:bg-gray-850  selected-command-option-button'
+								class="px-3 py-1.5 rounded-xl w-full text-left {modelIdx === selectedIdx
+									? 'bg-gray-50 dark:bg-gray-850 selected-command-option-button'
 									: ''}"
 								type="button"
 								on:click={() => {
@@ -159,13 +159,18 @@
 								}}
 								on:focus={() => {}}
 							>
-								<div class=" font-medium text-black dark:text-gray-100 line-clamp-1">
+								<div class="flex font-medium text-black dark:text-gray-100 line-clamp-1">
+									<img
+										src={model?.info?.meta?.profile_image_url ?? '/static/favicon.png'}
+										alt={model?.name ?? model.id}
+										class="rounded-full size-6 items-center mr-2"
+									/>
 									{model.name}
 								</div>
 
 								<!-- <div class=" text-xs text-gray-600 line-clamp-1">
 								{doc.title}
-							</div> -->
+								</div> -->
 							</button>
 						{/each}
 					</div>

src/lib/components/chat/Messages.svelte

@@ -1,6 +1,6 @@
 <script lang="ts">
 	import { v4 as uuidv4 } from 'uuid';
-	import { chats, config, settings, user as _user, mobile } from '$lib/stores';
+	import { chats, config, settings, user as _user, mobile, currentChatPage } from '$lib/stores';
 	import { tick, getContext, onMount } from 'svelte';
 
 	import { toast } from 'svelte-sonner';
@@ -90,7 +90,8 @@
 			history: history
 		});
 
-		await chats.set(await getChatList(localStorage.token));
+		currentChatPage.set(1);
+		await chats.set(await getChatList(localStorage.token, $currentChatPage));
 	};
 
 	const confirmEditResponseMessage = async (messageId, content) => {
@@ -146,12 +147,14 @@
 
 		await tick();
 
-		const element = document.getElementById('messages-container');
-		autoScroll = element.scrollHeight - element.scrollTop <= element.clientHeight + 50;
+		if ($settings?.scrollOnBranchChange ?? true) {
+			const element = document.getElementById('messages-container');
+			autoScroll = element.scrollHeight - element.scrollTop <= element.clientHeight + 50;
 
-		setTimeout(() => {
-			scrollToBottom();
-		}, 100);
+			setTimeout(() => {
+				scrollToBottom();
+			}, 100);
+		}
 	};
 
 	const showNextMessage = async (message) => {
@@ -195,12 +198,14 @@
 
 		await tick();
 
-		const element = document.getElementById('messages-container');
-		autoScroll = element.scrollHeight - element.scrollTop <= element.clientHeight + 50;
+		if ($settings?.scrollOnBranchChange ?? true) {
+			const element = document.getElementById('messages-container');
+			autoScroll = element.scrollHeight - element.scrollTop <= element.clientHeight + 50;
 
-		setTimeout(() => {
-			scrollToBottom();
-		}, 100);
+			setTimeout(() => {
+				scrollToBottom();
+			}, 100);
+		}
 	};
 
 	const deleteMessageHandler = async (messageId) => {
@@ -300,7 +305,7 @@
 				{#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 {$settings?.widescreenMode ?? null
+							class="flex flex-col justify-between px-5 mb-3 {($settings?.widescreenMode ?? null)
 								? 'max-w-full'
 								: 'max-w-5xl'} mx-auto rounded-lg group"
 						>
@@ -312,10 +317,10 @@
 									{message}
 									isFirstMessage={messageIdx === 0}
 									siblings={message.parentId !== null
-										? history.messages[message.parentId]?.childrenIds ?? []
-										: Object.values(history.messages)
+										? (history.messages[message.parentId]?.childrenIds ?? [])
+										: (Object.values(history.messages)
 												.filter((message) => message.parentId === null)
-												.map((message) => message.id) ?? []}
+												.map((message) => message.id) ?? [])}
 									{confirmEditMessage}
 									{showPreviousMessage}
 									{showNextMessage}

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

@@ -60,8 +60,8 @@
 									href={document?.metadata?.file_id
 										? `/api/v1/files/${document?.metadata?.file_id}/content`
 										: document.source.name.includes('http')
-										? document.source.name
-										: `#`}
+											? document.source.name
+											: `#`}
 									target="_blank"
 								>
 									{document?.metadata?.name ?? document.source.name}

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

@@ -1,17 +1,25 @@
 <script lang="ts">
-	import Spinner from '$lib/components/common/Spinner.svelte';
-	import { copyToClipboard } from '$lib/utils';
 	import hljs from 'highlight.js';
-	import 'highlight.js/styles/github-dark.min.css';
 	import { loadPyodide } from 'pyodide';
-	import { onMount, tick } from 'svelte';
+	import mermaid from 'mermaid';
+
+	import { getContext, getAllContexts, onMount } from 'svelte';
+	import { copyToClipboard } from '$lib/utils';
+
+	import 'highlight.js/styles/github-dark.min.css';
+
 	import PyodideWorker from '$lib/workers/pyodide.worker?worker';
 
+	const i18n = getContext('i18n');
+
 	export let id = '';
 
+	export let token;
 	export let lang = '';
 	export let code = '';
 
+	let mermaidHtml = null;
+
 	let highlightedCode = null;
 	let executing = false;
 
@@ -204,70 +212,102 @@ __builtins__.input = input`);
 	};
 
 	let debounceTimeout;
+
 	$: if (code) {
-		// Function to perform the code highlighting
-		const highlightCode = () => {
-			highlightedCode = hljs.highlightAuto(code, hljs.getLanguage(lang)?.aliases).value || code;
-		};
+		if (lang === 'mermaid' && (token?.raw ?? '').endsWith('```')) {
+			(async () => {
+				try {
+					const { svg } = await mermaid.render(`mermaid-${id}`, code);
+					mermaidHtml = svg;
+				} catch (error) {
+					console.error('Error:', error);
+				}
+			})();
+		} else {
+			// Function to perform the code highlighting
+			const highlightCode = () => {
+				highlightedCode = hljs.highlightAuto(code, hljs.getLanguage(lang)?.aliases).value || code;
+			};
 
-		// Clear the previous timeout if it exists
-		clearTimeout(debounceTimeout);
-
-		// Set a new timeout to debounce the code highlighting
-		debounceTimeout = setTimeout(highlightCode, 10);
+			// Clear the previous timeout if it exists
+			clearTimeout(debounceTimeout);
+			// Set a new timeout to debounce the code highlighting
+			debounceTimeout = setTimeout(highlightCode, 10);
+		}
 	}
+
+	onMount(async () => {
+		await mermaid.initialize({ startOnLoad: true });
+
+		if (lang === 'mermaid' && (token?.raw ?? '').endsWith('```')) {
+			try {
+				const { svg } = await mermaid.render(`mermaid-${id}`, code);
+				mermaidHtml = svg;
+			} catch (error) {
+				console.error('Error:', error);
+			}
+		}
+	});
 </script>
 
-<div class="mb-4" dir="ltr">
-	<div
-		class="flex justify-between bg-[#202123] text-white text-xs px-4 pt-1 pb-0.5 rounded-t-lg overflow-x-auto"
-	>
-		<div class="p-1">{@html lang}</div>
+<div class="my-2" dir="ltr">
+	{#if lang === 'mermaid'}
+		{#if mermaidHtml}
+			{@html mermaidHtml}
+		{:else}
+			<pre class=" mermaid-{id}">{code}</pre>
+		{/if}
+	{:else}
+		<div
+			class="flex justify-between bg-[#202123] text-white text-xs px-4 pt-1 pb-0.5 rounded-t-lg overflow-x-auto"
+		>
+			<div class="p-1">{@html lang}</div>
 
-		<div class="flex items-center">
-			{#if lang.toLowerCase() === 'python' || lang.toLowerCase() === 'py' || (lang === '' && checkPythonCode(code))}
-				{#if executing}
-					<div class="copy-code-button bg-none border-none p-1 cursor-not-allowed">Running</div>
-				{:else}
-					<button
-						class="copy-code-button bg-none border-none p-1"
-						on:click={() => {
-							executePython(code);
-						}}>Run</button
-					>
+			<div class="flex items-center">
+				{#if lang.toLowerCase() === 'python' || lang.toLowerCase() === 'py' || (lang === '' && checkPythonCode(code))}
+					{#if executing}
+						<div class="copy-code-button bg-none border-none p-1 cursor-not-allowed">Running</div>
+					{:else}
+						<button
+							class="copy-code-button bg-none border-none p-1"
+							on:click={() => {
+								executePython(code);
+							}}>{$i18n.t('Run')}</button
+						>
+					{/if}
 				{/if}
-			{/if}
-			<button class="copy-code-button bg-none border-none p-1" on:click={copyCode}
-				>{copied ? 'Copied' : 'Copy Code'}</button
-			>
+				<button class="copy-code-button bg-none border-none p-1" on:click={copyCode}
+					>{copied ? $i18n.t('Copied') : $i18n.t('Copy Code')}</button
+				>
+			</div>
 		</div>
-	</div>
 
-	<pre
-		class=" hljs p-4 px-5 overflow-x-auto"
-		style="border-top-left-radius: 0px; border-top-right-radius: 0px; {(executing ||
-			stdout ||
-			stderr ||
-			result) &&
-			'border-bottom-left-radius: 0px; border-bottom-right-radius: 0px;'}"><code
-			class="language-{lang} rounded-t-none whitespace-pre"
-			>{#if highlightedCode}{@html highlightedCode}{:else}{code}{/if}</code
-		></pre>
+		<pre
+			class=" hljs p-4 px-5 overflow-x-auto"
+			style="border-top-left-radius: 0px; border-top-right-radius: 0px; {(executing ||
+				stdout ||
+				stderr ||
+				result) &&
+				'border-bottom-left-radius: 0px; border-bottom-right-radius: 0px;'}"><code
+				class="language-{lang} rounded-t-none whitespace-pre"
+				>{#if highlightedCode}{@html highlightedCode}{:else}{code}{/if}</code
+			></pre>
 
-	<div
-		id="plt-canvas-{id}"
-		class="bg-[#202123] text-white max-w-full overflow-x-auto scrollbar-hidden"
-	/>
+		<div
+			id="plt-canvas-{id}"
+			class="bg-[#202123] text-white max-w-full overflow-x-auto scrollbar-hidden"
+		/>
 
-	{#if executing}
-		<div class="bg-[#202123] text-white px-4 py-4 rounded-b-lg">
-			<div class=" text-gray-500 text-xs mb-1">STDOUT/STDERR</div>
-			<div class="text-sm">Running...</div>
-		</div>
-	{:else if stdout || stderr || result}
-		<div class="bg-[#202123] text-white px-4 py-4 rounded-b-lg">
-			<div class=" text-gray-500 text-xs mb-1">STDOUT/STDERR</div>
-			<div class="text-sm">{stdout || stderr || result}</div>
-		</div>
+		{#if executing}
+			<div class="bg-[#202123] text-white px-4 py-4 rounded-b-lg">
+				<div class=" text-gray-500 text-xs mb-1">STDOUT/STDERR</div>
+				<div class="text-sm">Running...</div>
+			</div>
+		{:else if stdout || stderr || result}
+			<div class="bg-[#202123] text-white px-4 py-4 rounded-b-lg">
+				<div class=" text-gray-500 text-xs mb-1">STDOUT/STDERR</div>
+				<div class="text-sm">{stdout || stderr || result}</div>
+			</div>
+		{/if}
 	{/if}
 </div>

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

@@ -118,47 +118,47 @@
 								currentMessageId = message.id;
 								let messageId = message.id;
 								console.log(messageId);
-
 								//
 								let messageChildrenIds = history.messages[messageId].childrenIds;
 								while (messageChildrenIds.length !== 0) {
 									messageId = messageChildrenIds.at(-1);
 									messageChildrenIds = history.messages[messageId].childrenIds;
 								}
-
 								history.currentId = messageId;
 								dispatch('change');
 							}
 						}}
 					>
-						<ResponseMessage
-							message={groupedMessages[model].messages[groupedMessagesIdx[model]]}
-							siblings={groupedMessages[model].messages.map((m) => m.id)}
-							isLastMessage={true}
-							{updateChatMessages}
-							{confirmEditResponseMessage}
-							showPreviousMessage={() => showPreviousMessage(model)}
-							showNextMessage={() => showNextMessage(model)}
-							{readOnly}
-							{rateMessage}
-							{copyToClipboard}
-							{continueGeneration}
-							regenerateResponse={async (message) => {
-								regenerateResponse(message);
-								await tick();
-								groupedMessagesIdx[model] = groupedMessages[model].messages.length - 1;
-							}}
-							on:save={async (e) => {
-								console.log('save', e);
+						{#key history.currentId}
+							<ResponseMessage
+								message={groupedMessages[model].messages[groupedMessagesIdx[model]]}
+								siblings={groupedMessages[model].messages.map((m) => m.id)}
+								isLastMessage={true}
+								{updateChatMessages}
+								{confirmEditResponseMessage}
+								showPreviousMessage={() => showPreviousMessage(model)}
+								showNextMessage={() => showNextMessage(model)}
+								{readOnly}
+								{rateMessage}
+								{copyToClipboard}
+								{continueGeneration}
+								regenerateResponse={async (message) => {
+									regenerateResponse(message);
+									await tick();
+									groupedMessagesIdx[model] = groupedMessages[model].messages.length - 1;
+								}}
+								on:save={async (e) => {
+									console.log('save', e);
 
-								const message = e.detail;
-								history.messages[message.id] = message;
-								await updateChatById(localStorage.token, chatId, {
-									messages: messages,
-									history: history
-								});
-							}}
-						/>
+									const message = e.detail;
+									history.messages[message.id] = message;
+									await updateChatById(localStorage.token, chatId, {
+										messages: messages,
+										history: history
+									});
+								}}
+							/>
+						{/key}
 					</div>
 				{/if}
 			{/each}

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

@@ -0,0 +1,30 @@
+<script lang="ts">
+	import Image from '$lib/components/common/Image.svelte';
+	import CodeBlock from './CodeBlock.svelte';
+
+	/* The html content of the tag */
+	export let html; //: string;
+	let parsedHTML = [html];
+
+	export let images;
+	export let codes;
+
+	//  all images are in {{IMAGE_0}}, {{IMAGE_1}}....  format
+	// all codes are in {{CODE_0}}, {{CODE_1}}....  format
+
+	const rules = [];
+	rules.forEach((rule) => {
+		parsedHTML = parsedHTML.map((substr) => substr.split(rule.regex)).flat();
+	});
+</script>
+
+{#each parsedHTML as part}
+	{@const match = rules.find((rule) => rule.regex.test(part))}
+	{#if match}
+		<svelte:component this={match.component} {...match.props}>
+			{@html part}
+		</svelte:component>
+	{:else}
+		{@html part}
+	{/if}
+{/each}

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

@@ -0,0 +1,9 @@
+<script lang="ts">
+	import katex from 'katex';
+	import 'katex/contrib/mhchem';
+
+	export let content: string;
+	export let displayMode: boolean = false;
+</script>
+
+{@html katex.renderToString(content, { displayMode, throwOnError: false })}

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

@@ -0,0 +1,45 @@
+<script lang="ts">
+	import type { Token } from 'marked';
+	import { revertSanitizedResponseContent, unescapeHtml } from '$lib/utils';
+	import { onMount } from 'svelte';
+	import Image from '$lib/components/common/Image.svelte';
+
+	import KatexRenderer from './KatexRenderer.svelte';
+
+	export let id: string;
+	export let tokens: Token[];
+</script>
+
+{#each tokens as token}
+	{#if token.type === 'escape'}
+		{unescapeHtml(token.text)}
+	{:else if token.type === 'html'}
+		{@html token.text}
+	{:else if token.type === 'link'}
+		<a href={token.href} target="_blank" rel="nofollow" title={token.title}>{token.text}</a>
+	{:else if token.type === 'image'}
+		<Image src={token.href} alt={token.text} />
+	{:else if token.type === 'strong'}
+		<strong>
+			<svelte:self id={`${id}-strong`} tokens={token.tokens} />
+		</strong>
+	{:else if token.type === 'em'}
+		<em>
+			<svelte:self id={`${id}-em`} tokens={token.tokens} />
+		</em>
+	{:else if token.type === 'codespan'}
+		<code class="codespan">{revertSanitizedResponseContent(token.raw)}</code>
+	{:else if token.type === 'br'}
+		<br />
+	{:else if token.type === 'del'}
+		<del>
+			<svelte:self id={`${id}-del`} tokens={token.tokens} />
+		</del>
+	{:else if token.type === 'inlineKatex'}
+		{#if token.text}
+			<KatexRenderer content={revertSanitizedResponseContent(token.text)} displayMode={false} />
+		{/if}
+	{:else if token.type === 'text'}
+		{token.raw}
+	{/if}
+{/each}

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

@@ -0,0 +1,132 @@
+<script lang="ts">
+	import { onMount } from 'svelte';
+	import type { Token } from 'marked';
+	import { revertSanitizedResponseContent, unescapeHtml } from '$lib/utils';
+
+	import CodeBlock from '$lib/components/chat/Messages/CodeBlock.svelte';
+	import MarkdownInlineTokens from '$lib/components/chat/Messages/MarkdownInlineTokens.svelte';
+	import KatexRenderer from './KatexRenderer.svelte';
+
+	export let id: string;
+	export let tokens: Token[];
+	export let top = true;
+
+	const headerComponent = (depth: number) => {
+		return 'h' + depth;
+	};
+</script>
+
+<!-- {JSON.stringify(tokens)} -->
+{#each tokens as token, tokenIdx}
+	{#if token.type === 'hr'}
+		<hr />
+	{:else if token.type === 'heading'}
+		<svelte:element this={headerComponent(token.depth)}>
+			<MarkdownInlineTokens id={`${id}-${tokenIdx}-h`} tokens={token.tokens} />
+		</svelte:element>
+	{:else if token.type === 'code'}
+		<CodeBlock
+			id={`${id}-${tokenIdx}`}
+			{token}
+			lang={token?.lang ?? ''}
+			code={revertSanitizedResponseContent(token?.text ?? '')}
+		/>
+	{:else if token.type === 'table'}
+		<table>
+			<thead>
+				<tr>
+					{#each token.header as header, headerIdx}
+						<th style={token.align[headerIdx] ? '' : `text-align: ${token.align[headerIdx]}`}>
+							<MarkdownInlineTokens
+								id={`${id}-${tokenIdx}-header-${headerIdx}`}
+								tokens={header.tokens}
+							/>
+						</th>
+					{/each}
+				</tr>
+			</thead>
+			<tbody>
+				{#each token.rows as row, rowIdx}
+					<tr>
+						{#each row ?? [] as cell, cellIdx}
+							<td style={token.align[cellIdx] ? '' : `text-align: ${token.align[cellIdx]}`}>
+								<MarkdownInlineTokens
+									id={`${id}-${tokenIdx}-row-${rowIdx}-${cellIdx}`}
+									tokens={cell.tokens}
+								/>
+							</td>
+						{/each}
+					</tr>
+				{/each}
+			</tbody>
+		</table>
+	{:else if token.type === 'blockquote'}
+		<blockquote>
+			<svelte:self id={`${id}-${tokenIdx}`} tokens={token.tokens} />
+		</blockquote>
+	{:else if token.type === 'list'}
+		{#if token.ordered}
+			<ol start={token.start || 1}>
+				{#each token.items as item, itemIdx}
+					<li>
+						<svelte:self
+							id={`${id}-${tokenIdx}-${itemIdx}`}
+							tokens={item.tokens}
+							top={token.loose}
+						/>
+					</li>
+				{/each}
+			</ol>
+		{:else}
+			<ul>
+				{#each token.items as item, itemIdx}
+					<li>
+						<svelte:self
+							id={`${id}-${tokenIdx}-${itemIdx}`}
+							tokens={item.tokens}
+							top={token.loose}
+						/>
+					</li>
+				{/each}
+			</ul>
+		{/if}
+	{:else if token.type === 'html'}
+		{@html token.text}
+	{:else if token.type === 'paragraph'}
+		<p>
+			<MarkdownInlineTokens id={`${id}-${tokenIdx}-p`} tokens={token.tokens ?? []} />
+		</p>
+	{:else if token.type === 'text'}
+		{#if top}
+			<p>
+				{#if token.tokens}
+					<MarkdownInlineTokens id={`${id}-${tokenIdx}-t`} tokens={token.tokens} />
+				{:else}
+					{unescapeHtml(token.text)}
+				{/if}
+			</p>
+		{:else if token.tokens}
+			<MarkdownInlineTokens id={`${id}-${tokenIdx}-p`} tokens={token.tokens ?? []} />
+		{:else}
+			{unescapeHtml(token.text)}
+		{/if}
+	{:else if token.type === 'inlineKatex'}
+		{#if token.text}
+			<KatexRenderer
+				content={revertSanitizedResponseContent(token.text)}
+				displayMode={token?.displayMode ?? false}
+			/>
+		{/if}
+	{:else if token.type === 'blockKatex'}
+		{#if token.text}
+			<KatexRenderer
+				content={revertSanitizedResponseContent(token.text)}
+				displayMode={token?.displayMode ?? false}
+			/>
+		{/if}
+	{:else if token.type === 'space'}
+		{''}
+	{:else}
+		{console.log('Unknown token', token)}
+	{/if}
+{/each}

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

@@ -20,7 +20,10 @@
 			<ChevronDown strokeWidth="3.5" className="size-3.5 " />
 		{/if}
 	</div>
-	<div class="text-sm border border-gray-300/30 dark:border-gray-700/50 rounded-xl" slot="content">
+	<div
+		class="text-sm border border-gray-300/30 dark:border-gray-700/50 rounded-xl mb-1.5"
+		slot="content"
+	>
 		{#if status?.query}
 			<a
 				href="https://www.google.com/search?q={status.query}"

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

@@ -62,8 +62,8 @@
 	{#if !($settings?.chatBubble ?? true)}
 		<ProfileImage
 			src={message.user
-				? $models.find((m) => m.id === message.user)?.info?.meta?.profile_image_url ?? '/user.png'
-				: user?.profile_image_url ?? '/user.png'}
+				? ($models.find((m) => m.id === message.user)?.info?.meta?.profile_image_url ?? '/user.png')
+				: (user?.profile_image_url ?? '/user.png')}
 		/>
 	{/if}
 	<div class="w-full overflow-hidden pl-1">
@@ -96,11 +96,17 @@
 			{#if message.files}
 				<div class="mt-2.5 mb-1 w-full flex flex-col justify-end overflow-x-auto gap-1 flex-wrap">
 					{#each message.files as file}
-						<div class={$settings?.chatBubble ?? true ? 'self-end' : ''}>
+						<div class={($settings?.chatBubble ?? true) ? 'self-end' : ''}>
 							{#if file.type === 'image'}
 								<img src={file.url} alt="input" class=" max-h-96 rounded-lg" draggable="false" />
 							{:else}
-								<FileItem url={file.url} name={file.name} type={file.type} />
+								<FileItem
+									url={file.url}
+									name={file.name}
+									type={file.type}
+									size={file?.size}
+									colorClassName="bg-white dark:bg-gray-850 "
+								/>
 							{/if}
 						</div>
 					{/each}
@@ -156,12 +162,12 @@
 				</div>
 			{:else}
 				<div class="w-full">
-					<div class="flex {$settings?.chatBubble ?? true ? 'justify-end' : ''} mb-2">
+					<div class="flex {($settings?.chatBubble ?? true) ? 'justify-end' : ''} mb-2">
 						<div
-							class="rounded-3xl {$settings?.chatBubble ?? true
+							class="rounded-3xl {($settings?.chatBubble ?? true)
 								? `max-w-[90%] px-5 py-2  bg-gray-50 dark:bg-gray-850 ${
 										message.files ? 'rounded-tr-lg' : ''
-								  }`
+									}`
 								: ''}  "
 						>
 							<pre id="user-message">{message.content}</pre>
@@ -169,7 +175,7 @@
 					</div>
 
 					<div
-						class=" flex {$settings?.chatBubble ?? true
+						class=" flex {($settings?.chatBubble ?? true)
 							? 'justify-end'
 							: ''}  text-gray-600 dark:text-gray-500"
 					>

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

@@ -1,6 +1,7 @@
 <script lang="ts">
 	import { DropdownMenu } from 'bits-ui';
 	import { marked } from 'marked';
+	import Fuse from 'fuse.js';
 
 	import { flyAndScale } from '$lib/utils/transitions';
 	import { createEventDispatcher, onMount, getContext, tick } from 'svelte';
@@ -33,7 +34,7 @@
 		[key: string]: any;
 	} = [];
 
-	export let className = 'w-[30rem]';
+	export let className = 'w-[32rem]';
 
 	let show = false;
 
@@ -43,17 +44,31 @@
 	let searchValue = '';
 	let ollamaVersion = null;
 
-	$: filteredItems = items.filter(
-		(item) =>
-			(searchValue
-				? item.value.toLowerCase().includes(searchValue.toLowerCase()) ||
-				  item.label.toLowerCase().includes(searchValue.toLowerCase()) ||
-				  (item.model?.info?.meta?.tags ?? []).some((tag) =>
-						tag.name.toLowerCase().includes(searchValue.toLowerCase())
-				  )
-				: true) && !(item.model?.info?.meta?.hidden ?? false)
+	let selectedModelIdx = 0;
+
+	const fuse = new Fuse(
+		items
+			.filter((item) => !item.model?.info?.meta?.hidden)
+			.map((item) => {
+				const _item = {
+					...item,
+					modelName: item.model?.name,
+					tags: item.model?.info?.meta?.tags?.map((tag) => tag.name).join(' '),
+					desc: item.model?.info?.meta?.description
+				};
+				return _item;
+			}),
+		{
+			keys: ['value', 'label', 'tags', 'desc', 'modelName']
+		}
 	);
 
+	$: filteredItems = searchValue
+		? fuse.search(searchValue).map((e) => {
+				return e.item;
+			})
+		: items.filter((item) => !item.model?.info?.meta?.hidden);
+
 	const pullModelHandler = async () => {
 		const sanitizedModelTag = searchValue.trim().replace(/^ollama\s+(run|pull)\s+/, '');
 
@@ -202,6 +217,7 @@
 	bind:open={show}
 	onOpenChange={async () => {
 		searchValue = '';
+		selectedModelIdx = 0;
 		window.setTimeout(() => document.getElementById('model-search-input')?.focus(), 0);
 	}}
 	closeFocus={false}
@@ -238,19 +254,41 @@
 						class="w-full text-sm bg-transparent outline-none"
 						placeholder={searchPlaceholder}
 						autocomplete="off"
+						on:keydown={(e) => {
+							if (e.code === 'Enter' && filteredItems.length > 0) {
+								value = filteredItems[selectedModelIdx].value;
+								show = false;
+								return; // dont need to scroll on selection
+							} else if (e.code === 'ArrowDown') {
+								selectedModelIdx = Math.min(selectedModelIdx + 1, filteredItems.length - 1);
+							} else if (e.code === 'ArrowUp') {
+								selectedModelIdx = Math.max(selectedModelIdx - 1, 0);
+							} else {
+								// if the user types something, reset to the top selection.
+								selectedModelIdx = 0;
+							}
+
+							const item = document.querySelector(`[data-arrow-selected="true"]`);
+							item?.scrollIntoView({ block: 'center', inline: 'nearest', behavior: 'instant' });
+						}}
 					/>
 				</div>
 
 				<hr class="border-gray-100 dark:border-gray-800" />
 			{/if}
 
-			<div class="px-3 my-2 max-h-64 overflow-y-auto scrollbar-hidden">
-				{#each filteredItems as item}
+			<div class="px-3 my-2 max-h-64 overflow-y-auto scrollbar-hidden group">
+				{#each filteredItems as item, index}
 					<button
 						aria-label="model-item"
-						class="flex w-full text-left font-medium line-clamp-1 select-none items-center rounded-button py-2 pl-3 pr-1.5 text-sm text-gray-700 dark:text-gray-100 outline-none transition-all duration-75 hover:bg-gray-100 dark:hover:bg-gray-800 rounded-lg cursor-pointer data-[highlighted]:bg-muted"
+						class="flex w-full text-left font-medium line-clamp-1 select-none items-center rounded-button py-2 pl-3 pr-1.5 text-sm text-gray-700 dark:text-gray-100 outline-none transition-all duration-75 hover:bg-gray-100 dark:hover:bg-gray-800 rounded-lg cursor-pointer data-[highlighted]:bg-muted {index ===
+						selectedModelIdx
+							? 'bg-gray-100 dark:bg-gray-800 group-hover:bg-transparent'
+							: ''}"
+						data-arrow-selected={index === selectedModelIdx}
 						on:click={() => {
 							value = item.value;
+							selectedModelIdx = index;
 
 							show = false;
 						}}
@@ -270,7 +308,14 @@
 							<div class="flex items-center gap-2">
 								<div class="flex items-center min-w-fit">
 									<div class="line-clamp-1">
-										{item.label}
+										<div class="flex items-center min-w-fit">
+											<img
+												src={item.model?.info?.meta?.profile_image_url ?? '/static/favicon.png'}
+												alt="Model"
+												class="rounded-full size-5 flex items-center mr-2"
+											/>
+											{item.label}
+										</div>
 									</div>
 									{#if item.model.owned_by === 'ollama' && (item.model.ollama?.details?.parameter_size ?? '') !== ''}
 										<div class="flex ml-1 items-center translate-y-[0.5px]">
@@ -295,23 +340,11 @@
 									{/if}
 								</div>
 
-								{#if !$mobile && (item?.model?.info?.meta?.tags ?? []).length > 0}
-									<div class="flex gap-0.5 self-center items-center h-full translate-y-[0.5px]">
-										{#each item.model?.info?.meta.tags as tag}
-											<div
-												class=" text-xs font-bold px-1 rounded uppercase line-clamp-1 bg-gray-500/20 text-gray-700 dark:text-gray-200"
-											>
-												{tag.name}
-											</div>
-										{/each}
-									</div>
-								{/if}
-
 								<!-- {JSON.stringify(item.info)} -->
 
 								{#if item.model.owned_by === 'openai'}
 									<Tooltip content={`${'External'}`}>
-										<div class="">
+										<div class="translate-y-[1px]">
 											<svg
 												xmlns="http://www.w3.org/2000/svg"
 												viewBox="0 0 16 16"
@@ -342,7 +375,7 @@
 											)
 										)}`}
 									>
-										<div class="">
+										<div class=" translate-y-[1px]">
 											<svg
 												xmlns="http://www.w3.org/2000/svg"
 												fill="none"
@@ -360,6 +393,20 @@
 										</div>
 									</Tooltip>
 								{/if}
+
+								{#if !$mobile && (item?.model?.info?.meta?.tags ?? []).length > 0}
+									<div class="flex gap-0.5 self-center items-center h-full translate-y-[0.5px]">
+										{#each item.model?.info?.meta.tags as tag}
+											<Tooltip content={tag.name}>
+												<div
+													class=" text-xs font-bold px-1 rounded uppercase line-clamp-1 bg-gray-500/20 text-gray-700 dark:text-gray-200"
+												>
+													{tag.name}
+												</div>
+											</Tooltip>
+										{/each}
+									</div>
+								{/if}
 							</div>
 						</div>
 

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

@@ -65,8 +65,8 @@
 							{updateAvailable === null
 								? $i18n.t('Checking for updates...')
 								: updateAvailable
-								? `(v${version.latest} ${$i18n.t('available!')})`
-								: $i18n.t('(latest)')}
+									? `(v${version.latest} ${$i18n.t('available!')})`
+									: $i18n.t('(latest)')}
 						</a>
 					</div>
 

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

@@ -20,6 +20,7 @@
 		mirostat_tau: null,
 		top_k: null,
 		top_p: null,
+		min_p: null,
 		tfs_z: null,
 		num_ctx: null,
 		num_batch: null,
@@ -28,6 +29,7 @@
 		use_mmap: null,
 		use_mlock: null,
 		num_thread: null,
+		num_gpu: null,
 		template: null
 	};
 
@@ -385,6 +387,52 @@
 		{/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">{$i18n.t('Min P')}</div>
+
+			<button
+				class="p-1 px-3 text-xs flex rounded transition flex-shrink-0 outline-none"
+				type="button"
+				on:click={() => {
+					params.min_p = (params?.min_p ?? null) === null ? 0.0 : null;
+				}}
+			>
+				{#if (params?.min_p ?? null) === null}
+					<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+				{:else}
+					<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
+				{/if}
+			</button>
+		</div>
+
+		{#if (params?.min_p ?? null) !== null}
+			<div class="flex mt-0.5 space-x-2">
+				<div class=" flex-1">
+					<input
+						id="steps-range"
+						type="range"
+						min="0"
+						max="1"
+						step="0.05"
+						bind:value={params.min_p}
+						class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
+					/>
+				</div>
+				<div>
+					<input
+						bind:value={params.min_p}
+						type="number"
+						class=" bg-transparent text-center w-14"
+						min="0"
+						max="1"
+						step="any"
+					/>
+				</div>
+			</div>
+		{/if}
+	</div>
+
 	<div class=" py-0.5 w-full justify-between">
 		<div class="flex w-full justify-between">
 			<div class=" self-center text-xs font-medium">{$i18n.t('Frequency Penalty')}</div>
@@ -817,6 +865,52 @@
 			{/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">{$i18n.t('num_gpu (Ollama)')}</div>
+
+				<button
+					class="p-1 px-3 text-xs flex rounded transition flex-shrink-0 outline-none"
+					type="button"
+					on:click={() => {
+						params.num_gpu = (params?.num_gpu ?? null) === null ? 0 : null;
+					}}
+				>
+					{#if (params?.num_gpu ?? null) === null}
+						<span class="ml-2 self-center">{$i18n.t('Default')}</span>
+					{:else}
+						<span class="ml-2 self-center">{$i18n.t('Custom')}</span>
+					{/if}
+				</button>
+			</div>
+
+			{#if (params?.num_gpu ?? null) !== null}
+				<div class="flex mt-0.5 space-x-2">
+					<div class=" flex-1">
+						<input
+							id="steps-range"
+							type="range"
+							min="0"
+							max="256"
+							step="1"
+							bind:value={params.num_gpu}
+							class="w-full h-2 rounded-lg appearance-none cursor-pointer dark:bg-gray-700"
+						/>
+					</div>
+					<div class="">
+						<input
+							bind:value={params.num_gpu}
+							type="number"
+							class=" bg-transparent text-center w-14"
+							min="0"
+							max="256"
+							step="1"
+						/>
+					</div>
+				</div>
+			{/if}
+		</div>
+
 		<!-- <div class=" py-0.5 w-full justify-between">
 			<div class="flex w-full justify-between">
 				<div class=" self-center text-xs font-medium">{$i18n.t('Template')}</div>

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

@@ -1,7 +1,10 @@
 <script lang="ts">
-	import { user, settings, config } from '$lib/stores';
-	import { createEventDispatcher, onMount, getContext } from 'svelte';
 	import { toast } from 'svelte-sonner';
+	import { createEventDispatcher, onMount, getContext } from 'svelte';
+
+	import { user, settings, config } from '$lib/stores';
+	import { getVoices as _getVoices } from '$lib/apis/audio';
+
 	import Switch from '$lib/components/common/Switch.svelte';
 	const dispatch = createEventDispatcher();
 
@@ -20,26 +23,26 @@
 	let voices = [];
 	let voice = '';
 
-	const getOpenAIVoices = () => {
-		voices = [
-			{ name: 'alloy' },
-			{ name: 'echo' },
-			{ name: 'fable' },
-			{ name: 'onyx' },
-			{ name: 'nova' },
-			{ name: 'shimmer' }
-		];
-	};
+	const getVoices = async () => {
+		if ($config.audio.tts.engine === '') {
+			const getVoicesLoop = setInterval(async () => {
+				voices = await speechSynthesis.getVoices();
 
-	const getWebAPIVoices = () => {
-		const getVoicesLoop = setInterval(async () => {
-			voices = await speechSynthesis.getVoices();
+				// do your loop
+				if (voices.length > 0) {
+					clearInterval(getVoicesLoop);
+				}
+			}, 100);
+		} else {
+			const res = await _getVoices(localStorage.token).catch((e) => {
+				toast.error(e);
+			});
 
-			// do your loop
-			if (voices.length > 0) {
-				clearInterval(getVoicesLoop);
+			if (res) {
+				console.log(res);
+				voices = res.voices;
 			}
-		}, 100);
+		}
 	};
 
 	const toggleResponseAutoPlayback = async () => {
@@ -58,14 +61,16 @@
 		responseAutoPlayback = $settings.responseAutoPlayback ?? false;
 
 		STTEngine = $settings?.audio?.stt?.engine ?? '';
-		voice = $settings?.audio?.tts?.voice ?? $config.audio.tts.voice ?? '';
+
+		if ($settings?.audio?.tts?.defaultVoice === $config.audio.tts.voice) {
+			voice = $settings?.audio?.tts?.voice ?? $config.audio.tts.voice ?? '';
+		} else {
+			voice = $config.audio.tts.voice ?? '';
+		}
+
 		nonLocalVoices = $settings.audio?.tts?.nonLocalVoices ?? false;
 
-		if ($config.audio.tts.engine === 'openai') {
-			getOpenAIVoices();
-		} else {
-			getWebAPIVoices();
-		}
+		await getVoices();
 	});
 </script>
 
@@ -79,6 +84,7 @@
 				},
 				tts: {
 					voice: voice !== '' ? voice : undefined,
+					defaultVoice: $config?.audio?.tts?.voice ?? '',
 					nonLocalVoices: $config.audio.tts.engine === '' ? nonLocalVoices : undefined
 				}
 			}
@@ -181,7 +187,7 @@
 					</div>
 				</div>
 			</div>
-		{:else if $config.audio.tts.engine === 'openai'}
+		{:else 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">
@@ -195,7 +201,7 @@
 
 						<datalist id="voice-list">
 							{#each voices as voice}
-								<option value={voice.name} />
+								<option value={voice.id}>{voice.name}</option>
 							{/each}
 						</datalist>
 					</div>

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

@@ -2,7 +2,7 @@
 	import fileSaver from 'file-saver';
 	const { saveAs } = fileSaver;
 
-	import { chats, user, settings } from '$lib/stores';
+	import { chats, user, settings, scrollPaginationEnabled, currentChatPage } from '$lib/stores';
 
 	import {
 		archiveAllChats,
@@ -62,7 +62,9 @@
 			}
 		}
 
-		await chats.set(await getChatList(localStorage.token));
+		currentChatPage.set(1);
+		await chats.set(await getChatList(localStorage.token, $currentChatPage));
+		scrollPaginationEnabled.set(true);
 	};
 
 	const exportChats = async () => {
@@ -77,7 +79,10 @@
 		await archiveAllChats(localStorage.token).catch((error) => {
 			toast.error(error);
 		});
-		await chats.set(await getChatList(localStorage.token));
+
+		currentChatPage.set(1);
+		await chats.set(await getChatList(localStorage.token, $currentChatPage));
+		scrollPaginationEnabled.set(true);
 	};
 
 	const deleteAllChatsHandler = async () => {
@@ -85,7 +90,10 @@
 		await deleteAllChats(localStorage.token).catch((error) => {
 			toast.error(error);
 		});
-		await chats.set(await getChatList(localStorage.token));
+
+		currentChatPage.set(1);
+		await chats.set(await getChatList(localStorage.token, $currentChatPage));
+		scrollPaginationEnabled.set(true);
 	};
 
 	const toggleSaveChatHistory = async () => {

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

@@ -22,6 +22,7 @@
 	let responseAutoCopy = false;
 	let widescreenMode = false;
 	let splitLargeChunks = false;
+	let scrollOnBranchChange = true;
 	let userLocation = false;
 
 	// Interface
@@ -33,12 +34,18 @@
 
 	let showEmojiInCall = false;
 	let voiceInterruption = false;
+	let hapticFeedback = false;
 
 	const toggleSplitLargeChunks = async () => {
 		splitLargeChunks = !splitLargeChunks;
 		saveSettings({ splitLargeChunks: splitLargeChunks });
 	};
 
+	const togglesScrollOnBranchChange = async () => {
+		scrollOnBranchChange = !scrollOnBranchChange;
+		saveSettings({ scrollOnBranchChange: scrollOnBranchChange });
+	};
+
 	const togglewidescreenMode = async () => {
 		widescreenMode = !widescreenMode;
 		saveSettings({ widescreenMode: widescreenMode });
@@ -64,6 +71,11 @@
 		saveSettings({ voiceInterruption: voiceInterruption });
 	};
 
+	const toggleHapticFeedback = async () => {
+		hapticFeedback = !hapticFeedback;
+		saveSettings({ hapticFeedback: hapticFeedback });
+	};
+
 	const toggleUserLocation = async () => {
 		userLocation = !userLocation;
 
@@ -141,9 +153,12 @@
 		chatBubble = $settings.chatBubble ?? true;
 		widescreenMode = $settings.widescreenMode ?? false;
 		splitLargeChunks = $settings.splitLargeChunks ?? false;
+		scrollOnBranchChange = $settings.scrollOnBranchChange ?? true;
 		chatDirection = $settings.chatDirection ?? 'LTR';
 		userLocation = $settings.userLocation ?? false;
 
+		hapticFeedback = $settings.hapticFeedback ?? false;
+
 		defaultModelId = $settings?.models?.at(0) ?? '';
 		if ($config?.default_models) {
 			defaultModelId = $config.default_models.split(',')[0];
@@ -318,6 +333,28 @@
 				</div>
 			</div>
 
+			<div>
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs">
+						{$i18n.t('Scroll to bottom when switching between branches')}
+					</div>
+
+					<button
+						class="p-1 px-3 text-xs flex rounded transition"
+						on:click={() => {
+							togglesScrollOnBranchChange();
+						}}
+						type="button"
+					>
+						{#if scrollOnBranchChange === true}
+							<span class="ml-2 self-center">{$i18n.t('On')}</span>
+						{:else}
+							<span class="ml-2 self-center">{$i18n.t('Off')}</span>
+						{/if}
+					</button>
+				</div>
+			</div>
+
 			<div>
 				<div class=" py-0.5 flex w-full justify-between">
 					<div class=" self-center text-xs">
@@ -409,6 +446,26 @@
 				</div>
 			</div>
 
+			<div>
+				<div class=" py-0.5 flex w-full justify-between">
+					<div class=" self-center text-xs">{$i18n.t('Haptic Feedback')}</div>
+
+					<button
+						class="p-1 px-3 text-xs flex rounded transition"
+						on:click={() => {
+							toggleHapticFeedback();
+						}}
+						type="button"
+					>
+						{#if hapticFeedback === true}
+							<span class="ml-2 self-center">{$i18n.t('On')}</span>
+						{:else}
+							<span class="ml-2 self-center">{$i18n.t('Off')}</span>
+						{/if}
+					</button>
+				</div>
+			</div>
+
 			<div class=" my-1.5 text-sm font-medium">{$i18n.t('Voice')}</div>
 
 			<div>