diff --git a/CHANGELOG.md b/CHANGELOG.md index 38e3e2be4d..4d119a1386 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -5,6 +5,106 @@ 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). +## [0.6.36] - 2025-11-07 + +### Added + +- 🔐 OAuth group parsing now supports configurable separators via the "OAUTH_GROUPS_SEPARATOR" environment variable, enabling proper handling of semicolon-separated group claims from providers like CILogon. [#18987](https://github.com/open-webui/open-webui/pull/18987), [#18979](https://github.com/open-webui/open-webui/issues/18979) + +### Fixed + +- 🛠️ Tool calling functionality is restored by correcting asynchronous function handling in tool parameter updates. [#18981](https://github.com/open-webui/open-webui/issues/18981) +- 🖼️ The ComfyUI image edit workflow editor modal now opens correctly when clicking the Edit button. [#18978](https://github.com/open-webui/open-webui/issues/18978) +- 🔥 Firecrawl import errors are resolved by implementing lazy loading and using the correct class name. [#18973](https://github.com/open-webui/open-webui/issues/18973) +- 🔌 Socket.IO CORS warning is resolved by properly configuring CORS origins for Socket.IO connections. [Commit](https://github.com/open-webui/open-webui/commit/639d26252e528c9c37a5f553b11eb94376d8792d) + +## [0.6.35] - 2025-11-06 + +### Added + +- 🖼️ Image generation system received a comprehensive overhaul with major new capabilities including full image editing support allowing users to modify existing images using text prompts with OpenAI, Gemini, or ComfyUI engines, adding Gemini 2.5 Flash Image (Nano Banana) support, Qwen Image Edit integration, resolution of base64-encoded image display issues, streamlined AUTOMATIC1111 configuration by consolidating parameters into a flexible JSON parameters field, and enhanced UI with a code editor modal for ComfyUI workflow management. [#17434](https://github.com/open-webui/open-webui/pull/17434), [#16976](https://github.com/open-webui/open-webui/issues/16976), [Commit](https://github.com/open-webui/open-webui/commit/8e5690aab4f632a57027e2acf880b8f89a8717c0), [Commit](https://github.com/open-webui/open-webui/commit/72f8539fd2e679fec0762945f22f4b8a6920afa0), [Commit](https://github.com/open-webui/open-webui/commit/8d34fcb586eeee1fac6da2f991518b8a68b00b72), [Commit](https://github.com/open-webui/open-webui/commit/72900cd686de1fa6be84b5a8a2fc857cff7b91b8) +- 🔒 CORS origin validation was added to WebSocket connections as a defense-in-depth security measure against cross-site WebSocket hijacking attacks. [#18411](https://github.com/open-webui/open-webui/pull/18411), [#18410](https://github.com/open-webui/open-webui/issues/18410) +- 🔄 Automatic page refresh now occurs when a version update is detected via WebSocket connection, ensuring users always run the latest version without cache issues. [Commit](https://github.com/open-webui/open-webui/commit/989f192c92d2fe55daa31336e7971e21798b96ae) +- 🐍 Experimental initial preparations for Python 3.13 compatibility by updating dependencies with security enhancements and cryptographic improvements. [#18430](https://github.com/open-webui/open-webui/pull/18430), [#18424](https://github.com/open-webui/open-webui/pull/18424) +- ⚡ Image compression now preserves the original image format instead of converting to PNG, significantly reducing file sizes and improving chat loading performance. [#18506](https://github.com/open-webui/open-webui/pull/18506) +- 🎤 Mistral Voxtral model support was added for text-to-speech, including voxtral-small and voxtral-mini models with both transcription and chat completion API support. [#18934](https://github.com/open-webui/open-webui/pull/18934) +- 🔊 Text-to-speech now uses a global audio queue system to prevent overlapping playback, ensuring only one TTS instance plays at a time with proper stop/start controls and automatic cleanup when switching between messages. [#16152](https://github.com/open-webui/open-webui/pull/16152), [#18744](https://github.com/open-webui/open-webui/pull/18744), [#16150](https://github.com/open-webui/open-webui/issues/16150) +- 🔊 ELEVENLABS_API_BASE_URL environment variable now allows configuration of custom ElevenLabs API endpoints, enabling support for EU residency API requirements. [#18402](https://github.com/open-webui/open-webui/issues/18402) +- 🔐 OAUTH_ROLES_SEPARATOR environment variable now allows custom role separators for OAuth roles that contain commas, useful for roles specified in LDAP syntax. [#18572](https://github.com/open-webui/open-webui/pull/18572) +- 📄 External document loaders can now optionally forward user information headers when ENABLE_FORWARD_USER_INFO_HEADERS is enabled, enabling cost tracking, audit logs, and usage analytics for external services. [#18731](https://github.com/open-webui/open-webui/pull/18731) +- 📄 MISTRAL_OCR_API_BASE_URL environment variable now allows configuration of custom Mistral OCR API endpoints for flexible deployment options. [Commit](https://github.com/open-webui/open-webui/commit/415b93c7c35c2e2db4425e6da1b88b3750f496b0) +- ⌨️ Keyboard shortcut hints are now displayed on sidebar buttons with a refactored shortcuts modal that accurately reflects all available hotkeys across different keyboard layouts. [#18473](https://github.com/open-webui/open-webui/pull/18473) +- 🛠️ Tooltips now display tool descriptions when hovering over tool names on the model edit page, improving usability and providing immediate context. [#18707](https://github.com/open-webui/open-webui/pull/18707) +- 📝 "Create a new note" from the search modal now immediately creates a new private note and opens it in the editor instead of navigating to the generic notes page. [#18255](https://github.com/open-webui/open-webui/pull/18255) +- 🖨️ Code block output now preserves whitespace formatting with monospace font to accurately reflect terminal behavior. [#18352](https://github.com/open-webui/open-webui/pull/18352) +- ✏️ Edit button is now available in the three-dot menu of models in the workspace section for quick access to model editing, with the menu reorganized for better user experience and Edit, Clone, Copy Link, and Share options logically grouped. [#18574](https://github.com/open-webui/open-webui/pull/18574) +- 📌 Sidebar models section is now collapsible, allowing users to expand and collapse the pinned models list for better sidebar organization. [Commit](https://github.com/open-webui/open-webui/commit/82c08a3b5d189f81c96b6548cc872198771015b0) +- 🌙 Dark mode styles for select elements were added using Tailwind CSS classes, improving consistency across the interface. [#18636](https://github.com/open-webui/open-webui/pull/18636) +- 🔄 Various improvements were implemented across the frontend and backend to enhance performance, stability, and security. +- 🌐 Translations for Portuguese (Brazil), Greek, German, Traditional Chinese, Simplified Chinese, Spanish, Georgian, Danish, and Estonian were enhanced and expanded. + +### Fixed + +- 🔒 Server-Sent Event (SSE) code injection vulnerability in Direct Connections is resolved by blocking event emission from untrusted external model servers; event emitters from direct connected model servers are no longer supported, preventing arbitrary JavaScript execution in user browsers. [Commit](https://github.com/open-webui/open-webui/commit/8af6a4cf21b756a66cd58378a01c60f74c39b7ca) +- 🛡️ DOM XSS vulnerability in "Insert Prompt as Rich Text" is resolved by sanitizing HTML content with DOMPurify before rendering. [Commit](https://github.com/open-webui/open-webui/commit/eb9c4c0e358c274aea35f21c2856c0a20051e5f1) +- ⚙️ MCP server cancellation scope corruption is prevented by reversing disconnection order to follow LIFO and properly handling exceptions, resolving 100% CPU usage when resuming chats with expired tokens or using multiple streamable MCP servers. [#18537](https://github.com/open-webui/open-webui/pull/18537) +- 🔧 UI freeze when querying models with knowledge bases containing inconsistent distance metrics is resolved by properly initializing the distances array in citations. [#18585](https://github.com/open-webui/open-webui/pull/18585) +- 🤖 Duplicate model IDs from multiple OpenAI endpoints are now automatically deduplicated server-side, preventing frontend crashes for users with unified gateway proxies that aggregate multiple providers. [Commit](https://github.com/open-webui/open-webui/commit/fdf7ca11d4f3cc8fe63e81c98dc0d1e48e52ba36) +- 🔐 Login failures with passwords longer than 72 bytes are resolved by safely truncating oversized passwords for bcrypt compatibility. [#18157](https://github.com/open-webui/open-webui/issues/18157) +- 🔐 OAuth 2.1 MCP tool connections now automatically re-register clients when stored client IDs become stale, preventing unauthorized_client errors after editing tool endpoints and providing detailed error messages for callback failures. [#18415](https://github.com/open-webui/open-webui/pull/18415), [#18309](https://github.com/open-webui/open-webui/issues/18309) +- 🔓 OAuth 2.1 discovery, metadata fetching, and dynamic client registration now correctly use HTTP proxy environment variables when trust_env is enabled. [Commit](https://github.com/open-webui/open-webui/commit/bafeb76c411483bd6b135f0edbcdce048120f264) +- 🔌 MCP server connection failures now display clear error messages in the chat interface instead of silently failing. [#18892](https://github.com/open-webui/open-webui/pull/18892), [#18889](https://github.com/open-webui/open-webui/issues/18889) +- 💬 Chat titles are now properly generated even when title auto-generation is disabled in interface settings, fixing an issue where chats would remain labeled as "New chat". [#18761](https://github.com/open-webui/open-webui/pull/18761), [#18717](https://github.com/open-webui/open-webui/issues/18717), [#6478](https://github.com/open-webui/open-webui/issues/6478) +- 🔍 Chat query errors are prevented by properly validating and handling the "order_by" parameter to ensure requested columns exist. [#18400](https://github.com/open-webui/open-webui/pull/18400), [#18452](https://github.com/open-webui/open-webui/pull/18452) +- 🔧 Root-level max_tokens parameter is no longer dropped when proxying to Ollama, properly converting to num_predict to limit output token length as intended. [#18618](https://github.com/open-webui/open-webui/issues/18618) +- 🔑 Self-hosted Marker instances can now be used without requiring an API key, while keeping it optional for datalab Marker service users. [#18617](https://github.com/open-webui/open-webui/issues/18617) +- 🔧 OpenAPI specification endpoint conflict between "/api/v1/models" and "/api/v1/models/" is resolved by changing the models router endpoint to "/list", preventing duplicate operationId errors when generating TypeScript API clients. [#18758](https://github.com/open-webui/open-webui/issues/18758) +- 🏷️ Model tags are now de-duplicated case-insensitively in both the model selector and workspace models page, preventing duplicate entries with different capitalization from appearing in filter dropdowns. [#18716](https://github.com/open-webui/open-webui/pull/18716), [#18711](https://github.com/open-webui/open-webui/issues/18711) +- 📄 Docling RAG parameter configuration is now correctly saved in the admin UI by fixing the typo in the "DOCLING_PARAMS" parameter name. [#18390](https://github.com/open-webui/open-webui/pull/18390) +- 📃 Tika document processing now automatically detects content types instead of relying on potentially incorrect browser-provided mime-types, improving file handling accuracy for formats like RTF. [#18765](https://github.com/open-webui/open-webui/pull/18765), [#18683](https://github.com/open-webui/open-webui/issues/18683) +- 🖼️ Image and video uploads to knowledge bases now display proper error messages instead of showing an infinite spinner when the content extraction engine does not support these file types. [#18514](https://github.com/open-webui/open-webui/issues/18514) +- 📝 Notes PDF export now properly detects and applies dark mode styling consistently across both the notes list and individual note pages, with a shared utility function to eliminate code duplication. [#18526](https://github.com/open-webui/open-webui/issues/18526) +- 💭 Details tags for reasoning content are now correctly identified and rendered even when the same tag is present in user messages. [#18840](https://github.com/open-webui/open-webui/pull/18840), [#18294](https://github.com/open-webui/open-webui/issues/18294) +- 📊 Mermaid and Vega rendering errors now display inline with the code instead of showing repetitive toast notifications, improving user experience when models generate invalid diagram syntax. [Commit](https://github.com/open-webui/open-webui/commit/fdc0f04a8b7dd0bc9f9dc0e7e30854f7a0eea3e9) +- 📈 Mermaid diagram rendering errors no longer cause UI unavailability or display error messages below the input box. [#18493](https://github.com/open-webui/open-webui/pull/18493), [#18340](https://github.com/open-webui/open-webui/issues/18340) +- 🔗 Web search SSL verification is now asynchronous, preventing the website from hanging during web search operations. [#18714](https://github.com/open-webui/open-webui/pull/18714), [#18699](https://github.com/open-webui/open-webui/issues/18699) +- 🌍 Web search results now correctly use HTTP proxy environment variables when WEB_SEARCH_TRUST_ENV is enabled. [#18667](https://github.com/open-webui/open-webui/pull/18667), [#7008](https://github.com/open-webui/open-webui/discussions/7008) +- 🔍 Google Programmable Search Engine now properly includes referer headers, enabling API keys with HTTP referrer restrictions configured in Google Cloud Console. [#18871](https://github.com/open-webui/open-webui/pull/18871), [#18870](https://github.com/open-webui/open-webui/issues/18870) +- ⚡ YouTube video transcript fetching now works correctly when using a proxy connection. [#18419](https://github.com/open-webui/open-webui/pull/18419) +- 🎙️ Speech-to-text transcription no longer deletes or replaces existing text in the prompt input field, properly preserving any previously entered content. [#18540](https://github.com/open-webui/open-webui/issues/18540) +- 🎙️ The "Instant Auto-Send After Voice Transcription" setting now functions correctly and automatically sends transcribed text when enabled. [#18466](https://github.com/open-webui/open-webui/issues/18466) +- ⚙️ Chat settings now load properly when reopening a tab or starting a new session by initializing defaults when sessionStorage is empty. [#18438](https://github.com/open-webui/open-webui/pull/18438) +- 🔎 Folder tag search in the sidebar now correctly handles folder names with multiple spaces by replacing all spaces with underscores. [Commit](https://github.com/open-webui/open-webui/commit/a8fe979af68e47e4e4bb3eb76e48d93d60cd2a45) +- 🛠️ Functions page now updates immediately after deleting a function, removing the need for a manual page reload. [#18912](https://github.com/open-webui/open-webui/pull/18912), [#18908](https://github.com/open-webui/open-webui/issues/18908) +- 🛠️ Native tool calling now properly supports sequential tool calls with shared context, allowing tools to access images and data from previous tool executions in the same conversation. [#18664](https://github.com/open-webui/open-webui/pull/18664) +- 🎯 Globally enabled actions in the model editor now correctly apply as global instead of being treated as disabled. [#18577](https://github.com/open-webui/open-webui/pull/18577) +- 📋 Clipboard images pasted via the "{{CLIPBOARD}}" prompt variable are now correctly converted to base64 format before being sent to the backend, resolving base64 encoding errors. [#18432](https://github.com/open-webui/open-webui/pull/18432), [#18425](https://github.com/open-webui/open-webui/issues/18425) +- 📋 File list is now cleared when switching to models that do not support file uploads, preventing files from being sent to incompatible models. [#18496](https://github.com/open-webui/open-webui/pull/18496) +- 📂 Move menu no longer displays when folders are empty. [#18484](https://github.com/open-webui/open-webui/pull/18484) +- 📁 Folder and channel creation now validates that names are not empty, preventing creation of folders or channels with no name and showing an error toast if attempted. [#18564](https://github.com/open-webui/open-webui/pull/18564) +- 🖊️ Rich text input no longer removes text between equals signs when pasting code with comparison operators. [#18551](https://github.com/open-webui/open-webui/issues/18551) +- ⌨️ Keyboard shortcuts now display the correct keys for international and non-QWERTY keyboard layouts by detecting the user's layout using the Keyboard API. [#18533](https://github.com/open-webui/open-webui/pull/18533) +- 🌐 "Attach Webpage" button now displays with correct disabled styling when a model does not support file uploads. [#18483](https://github.com/open-webui/open-webui/pull/18483) +- 🎚️ Divider no longer displays in the integrations menu when no integrations are enabled. [#18487](https://github.com/open-webui/open-webui/pull/18487) +- 📱 Chat controls button is now properly hidden on mobile for users without admin or explicit chat control permissions. [#18641](https://github.com/open-webui/open-webui/pull/18641) +- 📍 User menu, download submenu, and move submenu are now repositioned to prevent overlap with the Chat Controls sidebar when it is open. [Commit](https://github.com/open-webui/open-webui/commit/414ab51cb6df1ab0d6c85ac6c1f2c5c9a5f8e2aa) +- 🎯 Artifacts button no longer appears in the chat menu when there are no artifacts to display. [Commit](https://github.com/open-webui/open-webui/commit/ed6449d35f84f68dc75ee5c6b3f4748a3fda0096) +- 🎨 Artifacts view now automatically displays when opening an existing conversation containing artifacts, improving user experience. [#18215](https://github.com/open-webui/open-webui/pull/18215) +- 🖌️ Formatting toolbar is no longer hidden under images or code blocks in chat and now displays correctly above all message content. +- 🎨 Layout shift near system instructions is prevented by properly rendering the chat component when system prompts are empty. [#18594](https://github.com/open-webui/open-webui/pull/18594) +- 📐 Modal layout shift caused by scrollbar appearance is prevented by adding a stable scrollbar gutter. [#18591](https://github.com/open-webui/open-webui/pull/18591) +- ✨ Spacing between icon and label in the user menu dropdown items is now consistent. [#18595](https://github.com/open-webui/open-webui/pull/18595) +- 💬 Duplicate prompt suggestions no longer cause the webpage to freeze or throw JavaScript errors by implementing proper key management with composite keys. [#18841](https://github.com/open-webui/open-webui/pull/18841), [#18566](https://github.com/open-webui/open-webui/issues/18566) +- 🔍 Chat preview loading in the search modal now works correctly for all search results by fixing an index boundary check that previously caused out-of-bounds errors. [#18911](https://github.com/open-webui/open-webui/pull/18911) +- ♿ Screen reader support was enhanced by wrapping messages in semantic elements with descriptive aria-labels, adding "Assistant is typing" and "Response complete" announcements for improved accessibility. [#18735](https://github.com/open-webui/open-webui/pull/18735) +- 🔒 Incorrect await call in the OAuth 2.1 flow is removed, eliminating a logged exception during authentication. [#18236](https://github.com/open-webui/open-webui/pull/18236) +- 🛡️ Duplicate crossorigin attribute in the manifest file was removed. [#18413](https://github.com/open-webui/open-webui/pull/18413) + +### Changed + +- 🔄 Firecrawl integration was refactored to use the official Firecrawl SDK instead of direct HTTP requests and langchain_community FireCrawlLoader, improving reliability and performance with batch scraping support and enhanced error handling. [#18635](https://github.com/open-webui/open-webui/pull/18635) +- 📄 MinerU content extraction engine now only supports PDF files following the upstream removal of LibreOffice document conversion in version 2.0.0; users needing to process office documents should convert them to PDF format first. [#18448](https://github.com/open-webui/open-webui/issues/18448) + ## [0.6.34] - 2025-10-16 ### Added diff --git a/backend/open_webui/config.py b/backend/open_webui/config.py index c794065974..42bcaab429 100644 --- a/backend/open_webui/config.py +++ b/backend/open_webui/config.py @@ -570,6 +570,8 @@ OAUTH_BLOCKED_GROUPS = PersistentConfig( os.environ.get("OAUTH_BLOCKED_GROUPS", "[]"), ) +OAUTH_GROUPS_SEPARATOR = os.environ.get("OAUTH_GROUPS_SEPARATOR", ";") + OAUTH_ROLES_CLAIM = PersistentConfig( "OAUTH_ROLES_CLAIM", "oauth.roles_claim", @@ -1122,6 +1124,10 @@ ENABLE_LOGIN_FORM = PersistentConfig( os.environ.get("ENABLE_LOGIN_FORM", "True").lower() == "true", ) +ENABLE_PASSWORD_AUTH = ( + os.environ.get("ENABLE_PASSWORD_AUTH", "True").lower() + == "true" +) DEFAULT_LOCALE = PersistentConfig( "DEFAULT_LOCALE", @@ -2464,6 +2470,12 @@ DOCUMENT_INTELLIGENCE_KEY = PersistentConfig( os.getenv("DOCUMENT_INTELLIGENCE_KEY", ""), ) +MISTRAL_OCR_API_BASE_URL = PersistentConfig( + "MISTRAL_OCR_API_BASE_URL", + "rag.MISTRAL_OCR_API_BASE_URL", + os.getenv("MISTRAL_OCR_API_BASE_URL", "https://api.mistral.ai/v1"), +) + MISTRAL_OCR_API_KEY = PersistentConfig( "MISTRAL_OCR_API_KEY", "rag.mistral_ocr_api_key", @@ -2689,10 +2701,6 @@ Provide a clear and direct response to the user's query, including inline citati {{CONTEXT}} - - -{{QUERY}} - """ RAG_TEMPLATE = PersistentConfig( @@ -3074,16 +3082,30 @@ EXTERNAL_WEB_LOADER_API_KEY = PersistentConfig( # Images #################################### +ENABLE_IMAGE_GENERATION = PersistentConfig( + "ENABLE_IMAGE_GENERATION", + "image_generation.enable", + os.environ.get("ENABLE_IMAGE_GENERATION", "").lower() == "true", +) + IMAGE_GENERATION_ENGINE = PersistentConfig( "IMAGE_GENERATION_ENGINE", "image_generation.engine", os.getenv("IMAGE_GENERATION_ENGINE", "openai"), ) -ENABLE_IMAGE_GENERATION = PersistentConfig( - "ENABLE_IMAGE_GENERATION", - "image_generation.enable", - os.environ.get("ENABLE_IMAGE_GENERATION", "").lower() == "true", +IMAGE_GENERATION_MODEL = PersistentConfig( + "IMAGE_GENERATION_MODEL", + "image_generation.model", + os.getenv("IMAGE_GENERATION_MODEL", ""), +) + +IMAGE_SIZE = PersistentConfig( + "IMAGE_SIZE", "image_generation.size", os.getenv("IMAGE_SIZE", "512x512") +) + +IMAGE_STEPS = PersistentConfig( + "IMAGE_STEPS", "image_generation.steps", int(os.getenv("IMAGE_STEPS", 50)) ) ENABLE_IMAGE_PROMPT_GENERATION = PersistentConfig( @@ -3103,35 +3125,17 @@ AUTOMATIC1111_API_AUTH = PersistentConfig( os.getenv("AUTOMATIC1111_API_AUTH", ""), ) -AUTOMATIC1111_CFG_SCALE = PersistentConfig( - "AUTOMATIC1111_CFG_SCALE", - "image_generation.automatic1111.cfg_scale", - ( - float(os.environ.get("AUTOMATIC1111_CFG_SCALE")) - if os.environ.get("AUTOMATIC1111_CFG_SCALE") - else None - ), -) +automatic1111_params = os.getenv("AUTOMATIC1111_PARAMS", "") +try: + automatic1111_params = json.loads(automatic1111_params) +except json.JSONDecodeError: + automatic1111_params = {} -AUTOMATIC1111_SAMPLER = PersistentConfig( - "AUTOMATIC1111_SAMPLER", - "image_generation.automatic1111.sampler", - ( - os.environ.get("AUTOMATIC1111_SAMPLER") - if os.environ.get("AUTOMATIC1111_SAMPLER") - else None - ), -) - -AUTOMATIC1111_SCHEDULER = PersistentConfig( - "AUTOMATIC1111_SCHEDULER", - "image_generation.automatic1111.scheduler", - ( - os.environ.get("AUTOMATIC1111_SCHEDULER") - if os.environ.get("AUTOMATIC1111_SCHEDULER") - else None - ), +AUTOMATIC1111_PARAMS = PersistentConfig( + "AUTOMATIC1111_PARAMS", + "image_generation.automatic1111.api_auth", + automatic1111_params, ) COMFYUI_BASE_URL = PersistentConfig( @@ -3297,18 +3301,79 @@ IMAGES_GEMINI_API_KEY = PersistentConfig( os.getenv("IMAGES_GEMINI_API_KEY", GEMINI_API_KEY), ) -IMAGE_SIZE = PersistentConfig( - "IMAGE_SIZE", "image_generation.size", os.getenv("IMAGE_SIZE", "512x512") +IMAGES_GEMINI_ENDPOINT_METHOD = PersistentConfig( + "IMAGES_GEMINI_ENDPOINT_METHOD", + "image_generation.gemini.endpoint_method", + os.getenv("IMAGES_GEMINI_ENDPOINT_METHOD", ""), ) -IMAGE_STEPS = PersistentConfig( - "IMAGE_STEPS", "image_generation.steps", int(os.getenv("IMAGE_STEPS", 50)) + +IMAGE_EDIT_ENGINE = PersistentConfig( + "IMAGE_EDIT_ENGINE", + "images.edit.engine", + os.getenv("IMAGE_EDIT_ENGINE", "openai"), ) -IMAGE_GENERATION_MODEL = PersistentConfig( - "IMAGE_GENERATION_MODEL", - "image_generation.model", - os.getenv("IMAGE_GENERATION_MODEL", ""), +IMAGE_EDIT_MODEL = PersistentConfig( + "IMAGE_EDIT_MODEL", + "images.edit.model", + os.getenv("IMAGE_EDIT_MODEL", ""), +) + +IMAGE_EDIT_SIZE = PersistentConfig( + "IMAGE_EDIT_SIZE", "images.edit.size", os.getenv("IMAGE_EDIT_SIZE", "") +) + +IMAGES_EDIT_OPENAI_API_BASE_URL = PersistentConfig( + "IMAGES_EDIT_OPENAI_API_BASE_URL", + "images.edit.openai.api_base_url", + os.getenv("IMAGES_EDIT_OPENAI_API_BASE_URL", OPENAI_API_BASE_URL), +) +IMAGES_EDIT_OPENAI_API_VERSION = PersistentConfig( + "IMAGES_EDIT_OPENAI_API_VERSION", + "images.edit.openai.api_version", + os.getenv("IMAGES_EDIT_OPENAI_API_VERSION", ""), +) + +IMAGES_EDIT_OPENAI_API_KEY = PersistentConfig( + "IMAGES_EDIT_OPENAI_API_KEY", + "images.edit.openai.api_key", + os.getenv("IMAGES_EDIT_OPENAI_API_KEY", OPENAI_API_KEY), +) + +IMAGES_EDIT_GEMINI_API_BASE_URL = PersistentConfig( + "IMAGES_EDIT_GEMINI_API_BASE_URL", + "images.edit.gemini.api_base_url", + os.getenv("IMAGES_EDIT_GEMINI_API_BASE_URL", GEMINI_API_BASE_URL), +) +IMAGES_EDIT_GEMINI_API_KEY = PersistentConfig( + "IMAGES_EDIT_GEMINI_API_KEY", + "images.edit.gemini.api_key", + os.getenv("IMAGES_EDIT_GEMINI_API_KEY", GEMINI_API_KEY), +) + + +IMAGES_EDIT_COMFYUI_BASE_URL = PersistentConfig( + "IMAGES_EDIT_COMFYUI_BASE_URL", + "images.edit.comfyui.base_url", + os.getenv("IMAGES_EDIT_COMFYUI_BASE_URL", ""), +) +IMAGES_EDIT_COMFYUI_API_KEY = PersistentConfig( + "IMAGES_EDIT_COMFYUI_API_KEY", + "images.edit.comfyui.api_key", + os.getenv("IMAGES_EDIT_COMFYUI_API_KEY", ""), +) + +IMAGES_EDIT_COMFYUI_WORKFLOW = PersistentConfig( + "IMAGES_EDIT_COMFYUI_WORKFLOW", + "images.edit.comfyui.workflow", + os.getenv("IMAGES_EDIT_COMFYUI_WORKFLOW", ""), +) + +IMAGES_EDIT_COMFYUI_WORKFLOW_NODES = PersistentConfig( + "IMAGES_EDIT_COMFYUI_WORKFLOW_NODES", + "images.edit.comfyui.nodes", + [], ) #################################### @@ -3343,6 +3408,10 @@ DEEPGRAM_API_KEY = PersistentConfig( os.getenv("DEEPGRAM_API_KEY", ""), ) +# ElevenLabs configuration +ELEVENLABS_API_BASE_URL = os.getenv( + "ELEVENLABS_API_BASE_URL", "https://api.elevenlabs.io" +) AUDIO_STT_OPENAI_API_BASE_URL = PersistentConfig( "AUDIO_STT_OPENAI_API_BASE_URL", @@ -3410,6 +3479,24 @@ AUDIO_STT_AZURE_MAX_SPEAKERS = PersistentConfig( os.getenv("AUDIO_STT_AZURE_MAX_SPEAKERS", ""), ) +AUDIO_STT_MISTRAL_API_KEY = PersistentConfig( + "AUDIO_STT_MISTRAL_API_KEY", + "audio.stt.mistral.api_key", + os.getenv("AUDIO_STT_MISTRAL_API_KEY", ""), +) + +AUDIO_STT_MISTRAL_API_BASE_URL = PersistentConfig( + "AUDIO_STT_MISTRAL_API_BASE_URL", + "audio.stt.mistral.api_base_url", + os.getenv("AUDIO_STT_MISTRAL_API_BASE_URL", "https://api.mistral.ai/v1"), +) + +AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS = PersistentConfig( + "AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS", + "audio.stt.mistral.use_chat_completions", + os.getenv("AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS", "false").lower() == "true", +) + AUDIO_TTS_OPENAI_API_BASE_URL = PersistentConfig( "AUDIO_TTS_OPENAI_API_BASE_URL", "audio.tts.openai.api_base_url", diff --git a/backend/open_webui/env.py b/backend/open_webui/env.py index 8f9c1fbc44..b85316d955 100644 --- a/backend/open_webui/env.py +++ b/backend/open_webui/env.py @@ -569,6 +569,21 @@ else: CHAT_RESPONSE_MAX_TOOL_CALL_RETRIES = 30 +CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE = os.environ.get( + "CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE", "" +) + +if CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE == "": + CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE = None +else: + try: + CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE = int( + CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE + ) + except Exception: + CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE = None + + #################################### # WEBSOCKET SUPPORT #################################### diff --git a/backend/open_webui/main.py b/backend/open_webui/main.py index 1405a43061..f0aeeab02a 100644 --- a/backend/open_webui/main.py +++ b/backend/open_webui/main.py @@ -146,9 +146,7 @@ from open_webui.config import ( # Image AUTOMATIC1111_API_AUTH, AUTOMATIC1111_BASE_URL, - AUTOMATIC1111_CFG_SCALE, - AUTOMATIC1111_SAMPLER, - AUTOMATIC1111_SCHEDULER, + AUTOMATIC1111_PARAMS, COMFYUI_BASE_URL, COMFYUI_API_KEY, COMFYUI_WORKFLOW, @@ -164,6 +162,19 @@ from open_webui.config import ( IMAGES_OPENAI_API_KEY, IMAGES_GEMINI_API_BASE_URL, IMAGES_GEMINI_API_KEY, + IMAGES_GEMINI_ENDPOINT_METHOD, + IMAGE_EDIT_ENGINE, + IMAGE_EDIT_MODEL, + IMAGE_EDIT_SIZE, + IMAGES_EDIT_OPENAI_API_BASE_URL, + IMAGES_EDIT_OPENAI_API_KEY, + IMAGES_EDIT_OPENAI_API_VERSION, + IMAGES_EDIT_GEMINI_API_BASE_URL, + IMAGES_EDIT_GEMINI_API_KEY, + IMAGES_EDIT_COMFYUI_BASE_URL, + IMAGES_EDIT_COMFYUI_API_KEY, + IMAGES_EDIT_COMFYUI_WORKFLOW, + IMAGES_EDIT_COMFYUI_WORKFLOW_NODES, # Audio AUDIO_STT_ENGINE, AUDIO_STT_MODEL, @@ -175,6 +186,9 @@ from open_webui.config import ( AUDIO_STT_AZURE_LOCALES, AUDIO_STT_AZURE_BASE_URL, AUDIO_STT_AZURE_MAX_SPEAKERS, + AUDIO_STT_MISTRAL_API_KEY, + AUDIO_STT_MISTRAL_API_BASE_URL, + AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS, AUDIO_TTS_ENGINE, AUDIO_TTS_MODEL, AUDIO_TTS_VOICE, @@ -266,6 +280,7 @@ from open_webui.config import ( DOCLING_PICTURE_DESCRIPTION_API, DOCUMENT_INTELLIGENCE_ENDPOINT, DOCUMENT_INTELLIGENCE_KEY, + MISTRAL_OCR_API_BASE_URL, MISTRAL_OCR_API_KEY, RAG_TEXT_SPLITTER, TIKTOKEN_ENCODING_NAME, @@ -482,9 +497,11 @@ from open_webui.utils.auth import ( ) from open_webui.utils.plugin import install_tool_and_function_dependencies from open_webui.utils.oauth import ( + get_oauth_client_info_with_dynamic_client_registration, + encrypt_data, + decrypt_data, OAuthManager, OAuthClientManager, - decrypt_data, OAuthClientInformationFull, ) from open_webui.utils.security_headers import SecurityHeadersMiddleware @@ -856,6 +873,7 @@ app.state.config.DOCLING_PICTURE_DESCRIPTION_LOCAL = DOCLING_PICTURE_DESCRIPTION app.state.config.DOCLING_PICTURE_DESCRIPTION_API = DOCLING_PICTURE_DESCRIPTION_API app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = DOCUMENT_INTELLIGENCE_ENDPOINT app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY +app.state.config.MISTRAL_OCR_API_BASE_URL = MISTRAL_OCR_API_BASE_URL app.state.config.MISTRAL_OCR_API_KEY = MISTRAL_OCR_API_KEY app.state.config.MINERU_API_MODE = MINERU_API_MODE app.state.config.MINERU_API_URL = MINERU_API_URL @@ -1062,27 +1080,40 @@ app.state.config.IMAGE_GENERATION_ENGINE = IMAGE_GENERATION_ENGINE app.state.config.ENABLE_IMAGE_GENERATION = ENABLE_IMAGE_GENERATION app.state.config.ENABLE_IMAGE_PROMPT_GENERATION = ENABLE_IMAGE_PROMPT_GENERATION +app.state.config.IMAGE_GENERATION_MODEL = IMAGE_GENERATION_MODEL +app.state.config.IMAGE_SIZE = IMAGE_SIZE +app.state.config.IMAGE_STEPS = IMAGE_STEPS + app.state.config.IMAGES_OPENAI_API_BASE_URL = IMAGES_OPENAI_API_BASE_URL app.state.config.IMAGES_OPENAI_API_VERSION = IMAGES_OPENAI_API_VERSION app.state.config.IMAGES_OPENAI_API_KEY = IMAGES_OPENAI_API_KEY app.state.config.IMAGES_GEMINI_API_BASE_URL = IMAGES_GEMINI_API_BASE_URL app.state.config.IMAGES_GEMINI_API_KEY = IMAGES_GEMINI_API_KEY - -app.state.config.IMAGE_GENERATION_MODEL = IMAGE_GENERATION_MODEL +app.state.config.IMAGES_GEMINI_ENDPOINT_METHOD = IMAGES_GEMINI_ENDPOINT_METHOD app.state.config.AUTOMATIC1111_BASE_URL = AUTOMATIC1111_BASE_URL app.state.config.AUTOMATIC1111_API_AUTH = AUTOMATIC1111_API_AUTH -app.state.config.AUTOMATIC1111_CFG_SCALE = AUTOMATIC1111_CFG_SCALE -app.state.config.AUTOMATIC1111_SAMPLER = AUTOMATIC1111_SAMPLER -app.state.config.AUTOMATIC1111_SCHEDULER = AUTOMATIC1111_SCHEDULER +app.state.config.AUTOMATIC1111_PARAMS = AUTOMATIC1111_PARAMS + app.state.config.COMFYUI_BASE_URL = COMFYUI_BASE_URL app.state.config.COMFYUI_API_KEY = COMFYUI_API_KEY app.state.config.COMFYUI_WORKFLOW = COMFYUI_WORKFLOW app.state.config.COMFYUI_WORKFLOW_NODES = COMFYUI_WORKFLOW_NODES -app.state.config.IMAGE_SIZE = IMAGE_SIZE -app.state.config.IMAGE_STEPS = IMAGE_STEPS + +app.state.config.IMAGE_EDIT_ENGINE = IMAGE_EDIT_ENGINE +app.state.config.IMAGE_EDIT_MODEL = IMAGE_EDIT_MODEL +app.state.config.IMAGE_EDIT_SIZE = IMAGE_EDIT_SIZE +app.state.config.IMAGES_EDIT_OPENAI_API_BASE_URL = IMAGES_EDIT_OPENAI_API_BASE_URL +app.state.config.IMAGES_EDIT_OPENAI_API_KEY = IMAGES_EDIT_OPENAI_API_KEY +app.state.config.IMAGES_EDIT_OPENAI_API_VERSION = IMAGES_EDIT_OPENAI_API_VERSION +app.state.config.IMAGES_EDIT_GEMINI_API_BASE_URL = IMAGES_EDIT_GEMINI_API_BASE_URL +app.state.config.IMAGES_EDIT_GEMINI_API_KEY = IMAGES_EDIT_GEMINI_API_KEY +app.state.config.IMAGES_EDIT_COMFYUI_BASE_URL = IMAGES_EDIT_COMFYUI_BASE_URL +app.state.config.IMAGES_EDIT_COMFYUI_API_KEY = IMAGES_EDIT_COMFYUI_API_KEY +app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW = IMAGES_EDIT_COMFYUI_WORKFLOW +app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW_NODES = IMAGES_EDIT_COMFYUI_WORKFLOW_NODES ######################################## @@ -1108,6 +1139,12 @@ app.state.config.AUDIO_STT_AZURE_LOCALES = AUDIO_STT_AZURE_LOCALES app.state.config.AUDIO_STT_AZURE_BASE_URL = AUDIO_STT_AZURE_BASE_URL app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS = AUDIO_STT_AZURE_MAX_SPEAKERS +app.state.config.AUDIO_STT_MISTRAL_API_KEY = AUDIO_STT_MISTRAL_API_KEY +app.state.config.AUDIO_STT_MISTRAL_API_BASE_URL = AUDIO_STT_MISTRAL_API_BASE_URL +app.state.config.AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS = ( + AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS +) + app.state.config.TTS_ENGINE = AUDIO_TTS_ENGINE app.state.config.TTS_MODEL = AUDIO_TTS_MODEL @@ -1941,6 +1978,7 @@ if len(app.state.config.TOOL_SERVER_CONNECTIONS) > 0: if tool_server_connection.get("type", "openapi") == "mcp": server_id = tool_server_connection.get("info", {}).get("id") auth_type = tool_server_connection.get("auth_type", "none") + if server_id and auth_type == "oauth_2.1": oauth_client_info = tool_server_connection.get("info", {}).get( "oauth_client_info", "" @@ -1986,6 +2024,64 @@ except Exception as e: ) +async def register_client(self, request, client_id: str) -> bool: + server_type, server_id = client_id.split(":", 1) + + connection = None + connection_idx = None + + for idx, conn in enumerate(request.app.state.config.TOOL_SERVER_CONNECTIONS or []): + if conn.get("type", "openapi") == server_type: + info = conn.get("info", {}) + if info.get("id") == server_id: + connection = conn + connection_idx = idx + break + + if connection is None or connection_idx is None: + log.warning( + f"Unable to locate MCP tool server configuration for client {client_id} during re-registration" + ) + return False + + server_url = connection.get("url") + oauth_server_key = (connection.get("config") or {}).get("oauth_server_key") + + try: + oauth_client_info = ( + await get_oauth_client_info_with_dynamic_client_registration( + request, + client_id, + server_url, + oauth_server_key, + ) + ) + except Exception as e: + log.error(f"Dynamic client re-registration failed for {client_id}: {e}") + return False + + try: + request.app.state.config.TOOL_SERVER_CONNECTIONS[connection_idx] = { + **connection, + "info": { + **connection.get("info", {}), + "oauth_client_info": encrypt_data( + oauth_client_info.model_dump(mode="json") + ), + }, + } + except Exception as e: + log.error( + f"Failed to persist updated OAuth client info for tool server {client_id}: {e}" + ) + return False + + oauth_client_manager.remove_client(client_id) + oauth_client_manager.add_client(client_id, oauth_client_info) + log.info(f"Re-registered OAuth client {client_id} for tool server") + return True + + @app.get("/oauth/clients/{client_id}/authorize") async def oauth_client_authorize( client_id: str, @@ -1993,6 +2089,41 @@ async def oauth_client_authorize( response: Response, user=Depends(get_verified_user), ): + # ensure_valid_client_registration + client = oauth_client_manager.get_client(client_id) + client_info = oauth_client_manager.get_client_info(client_id) + if client is None or client_info is None: + raise HTTPException(status.HTTP_404_NOT_FOUND) + + if not await oauth_client_manager._preflight_authorization_url(client, client_info): + log.info( + "Detected invalid OAuth client %s; attempting re-registration", + client_id, + ) + + registered = await register_client(request, client_id) + if not registered: + raise HTTPException( + status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, + detail="Failed to re-register OAuth client", + ) + + client = oauth_client_manager.get_client(client_id) + client_info = oauth_client_manager.get_client_info(client_id) + if client is None or client_info is None: + raise HTTPException( + status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, + detail="OAuth client unavailable after re-registration", + ) + + if not await oauth_client_manager._preflight_authorization_url( + client, client_info + ): + raise HTTPException( + status_code=status.HTTP_500_INTERNAL_SERVER_ERROR, + detail="OAuth client registration is still invalid after re-registration", + ) + return await oauth_client_manager.handle_authorize(request, client_id=client_id) diff --git a/backend/open_webui/models/chats.py b/backend/open_webui/models/chats.py index 3ae7112f3e..c559932bcd 100644 --- a/backend/open_webui/models/chats.py +++ b/backend/open_webui/models/chats.py @@ -765,15 +765,20 @@ class ChatTable: ) elif dialect_name == "postgresql": - # PostgreSQL relies on proper JSON query for search + # PostgreSQL doesn't allow null bytes in text. We filter those out by checking + # the JSON representation for \u0000 before attempting text extraction postgres_content_sql = ( "EXISTS (" " SELECT 1 " " FROM json_array_elements(Chat.chat->'messages') AS message " - " WHERE LOWER(message->>'content') LIKE '%' || :content_key || '%'" + " WHERE message->'content' IS NOT NULL " + " AND (message->'content')::text NOT LIKE '%\\u0000%' " + " AND LOWER(message->>'content') LIKE '%' || :content_key || '%'" ")" ) postgres_content_clause = text(postgres_content_sql) + # Also filter out chats with null bytes in title + query = query.filter(text("Chat.title::text NOT LIKE '%\\x00%'")) query = query.filter( or_( Chat.title.ilike(bindparam("title_key")), diff --git a/backend/open_webui/models/files.py b/backend/open_webui/models/files.py index 171810fde7..e86000cfc8 100644 --- a/backend/open_webui/models/files.py +++ b/backend/open_webui/models/files.py @@ -98,6 +98,12 @@ class FileForm(BaseModel): access_control: Optional[dict] = None +class FileUpdateForm(BaseModel): + hash: Optional[str] = None + data: Optional[dict] = None + meta: Optional[dict] = None + + class FilesTable: def insert_new_file(self, user_id: str, form_data: FileForm) -> Optional[FileModel]: with get_db() as db: @@ -204,6 +210,29 @@ class FilesTable: for file in db.query(File).filter_by(user_id=user_id).all() ] + def update_file_by_id( + self, id: str, form_data: FileUpdateForm + ) -> Optional[FileModel]: + with get_db() as db: + try: + file = db.query(File).filter_by(id=id).first() + + if form_data.hash is not None: + file.hash = form_data.hash + + if form_data.data is not None: + file.data = {**(file.data if file.data else {}), **form_data.data} + + if form_data.meta is not None: + file.meta = {**(file.meta if file.meta else {}), **form_data.meta} + + file.updated_at = int(time.time()) + db.commit() + return FileModel.model_validate(file) + except Exception as e: + log.exception(f"Error updating file completely by id: {e}") + return None + def update_file_hash_by_id(self, id: str, hash: str) -> Optional[FileModel]: with get_db() as db: try: diff --git a/backend/open_webui/models/oauth_sessions.py b/backend/open_webui/models/oauth_sessions.py index 81ce220384..b0e465dbe7 100644 --- a/backend/open_webui/models/oauth_sessions.py +++ b/backend/open_webui/models/oauth_sessions.py @@ -262,5 +262,16 @@ class OAuthSessionTable: log.error(f"Error deleting OAuth sessions by user ID: {e}") return False + def delete_sessions_by_provider(self, provider: str) -> bool: + """Delete all OAuth sessions for a provider""" + try: + with get_db() as db: + db.query(OAuthSession).filter_by(provider=provider).delete() + db.commit() + return True + except Exception as e: + log.error(f"Error deleting OAuth sessions by provider {provider}: {e}") + return False + OAuthSessions = OAuthSessionTable() diff --git a/backend/open_webui/retrieval/loaders/external_document.py b/backend/open_webui/retrieval/loaders/external_document.py index 1be2ca3f24..998afd36f6 100644 --- a/backend/open_webui/retrieval/loaders/external_document.py +++ b/backend/open_webui/retrieval/loaders/external_document.py @@ -5,6 +5,7 @@ from urllib.parse import quote from langchain_core.document_loaders import BaseLoader from langchain_core.documents import Document +from open_webui.utils.headers import include_user_info_headers from open_webui.env import SRC_LOG_LEVELS log = logging.getLogger(__name__) @@ -18,6 +19,7 @@ class ExternalDocumentLoader(BaseLoader): url: str, api_key: str, mime_type=None, + user=None, **kwargs, ) -> None: self.url = url @@ -26,6 +28,8 @@ class ExternalDocumentLoader(BaseLoader): self.file_path = file_path self.mime_type = mime_type + self.user = user + def load(self) -> List[Document]: with open(self.file_path, "rb") as f: data = f.read() @@ -42,6 +46,9 @@ class ExternalDocumentLoader(BaseLoader): except: pass + if self.user is not None: + headers = include_user_info_headers(headers, self.user) + url = self.url if url.endswith("/"): url = url[:-1] diff --git a/backend/open_webui/retrieval/loaders/main.py b/backend/open_webui/retrieval/loaders/main.py index 2ef1d75e02..bbc3da9bc9 100644 --- a/backend/open_webui/retrieval/loaders/main.py +++ b/backend/open_webui/retrieval/loaders/main.py @@ -228,6 +228,7 @@ class DoclingLoader: class Loader: def __init__(self, engine: str = "", **kwargs): self.engine = engine + self.user = kwargs.get("user", None) self.kwargs = kwargs def load( @@ -264,6 +265,7 @@ class Loader: url=self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_URL"), api_key=self.kwargs.get("EXTERNAL_DOCUMENT_LOADER_API_KEY"), mime_type=file_content_type, + user=self.user, ) elif self.engine == "tika" and self.kwargs.get("TIKA_SERVER_URL"): if self._is_text_file(file_ext, file_content_type): @@ -272,7 +274,6 @@ class Loader: loader = TikaLoader( url=self.kwargs.get("TIKA_SERVER_URL"), file_path=file_path, - mime_type=file_content_type, extract_images=self.kwargs.get("PDF_EXTRACT_IMAGES"), ) elif ( @@ -369,14 +370,8 @@ class Loader: azure_credential=DefaultAzureCredential(), ) elif self.engine == "mineru" and file_ext in [ - "pdf", - "doc", - "docx", - "ppt", - "pptx", - "xls", - "xlsx", - ]: + "pdf" + ]: # MinerU currently only supports PDF loader = MinerULoader( file_path=file_path, api_mode=self.kwargs.get("MINERU_API_MODE", "local"), @@ -391,16 +386,9 @@ class Loader: in ["pdf"] # Mistral OCR currently only supports PDF and images ): loader = MistralLoader( - api_key=self.kwargs.get("MISTRAL_OCR_API_KEY"), file_path=file_path - ) - elif ( - self.engine == "external" - and self.kwargs.get("MISTRAL_OCR_API_KEY") != "" - and file_ext - in ["pdf"] # Mistral OCR currently only supports PDF and images - ): - loader = MistralLoader( - api_key=self.kwargs.get("MISTRAL_OCR_API_KEY"), file_path=file_path + base_url=self.kwargs.get("MISTRAL_OCR_API_BASE_URL"), + api_key=self.kwargs.get("MISTRAL_OCR_API_KEY"), + file_path=file_path, ) else: if file_ext == "pdf": diff --git a/backend/open_webui/retrieval/loaders/mineru.py b/backend/open_webui/retrieval/loaders/mineru.py index 437f44ae6b..360af804c7 100644 --- a/backend/open_webui/retrieval/loaders/mineru.py +++ b/backend/open_webui/retrieval/loaders/mineru.py @@ -33,13 +33,14 @@ class MinerULoader: self.api_key = api_key # Parse params dict with defaults - params = params or {} + self.params = params or {} self.enable_ocr = params.get("enable_ocr", False) self.enable_formula = params.get("enable_formula", True) self.enable_table = params.get("enable_table", True) self.language = params.get("language", "en") self.model_version = params.get("model_version", "pipeline") - self.page_ranges = params.get("page_ranges", "") + + self.page_ranges = self.params.pop("page_ranges", "") # Validate API mode if self.api_mode not in ["local", "cloud"]: @@ -76,27 +77,10 @@ class MinerULoader: # Build form data for Local API form_data = { + **self.params, "return_md": "true", - "formula_enable": str(self.enable_formula).lower(), - "table_enable": str(self.enable_table).lower(), } - # Parse method based on OCR setting - if self.enable_ocr: - form_data["parse_method"] = "ocr" - else: - form_data["parse_method"] = "auto" - - # Language configuration (Local API uses lang_list array) - if self.language: - form_data["lang_list"] = self.language - - # Backend/model version (Local API uses "backend" parameter) - if self.model_version == "vlm": - form_data["backend"] = "vlm-vllm-engine" - else: - form_data["backend"] = "pipeline" - # Page ranges (Local API uses start_page_id and end_page_id) if self.page_ranges: # For simplicity, if page_ranges is specified, log a warning @@ -236,10 +220,7 @@ class MinerULoader: # Build request body request_body = { - "enable_formula": self.enable_formula, - "enable_table": self.enable_table, - "language": self.language, - "model_version": self.model_version, + **self.params, "files": [ { "name": filename, diff --git a/backend/open_webui/retrieval/loaders/mistral.py b/backend/open_webui/retrieval/loaders/mistral.py index b7f2622f5e..6a2d235559 100644 --- a/backend/open_webui/retrieval/loaders/mistral.py +++ b/backend/open_webui/retrieval/loaders/mistral.py @@ -30,10 +30,9 @@ class MistralLoader: - Enhanced error handling with retryable error classification """ - BASE_API_URL = "https://api.mistral.ai/v1" - def __init__( self, + base_url: str, api_key: str, file_path: str, timeout: int = 300, # 5 minutes default @@ -55,6 +54,9 @@ class MistralLoader: if not os.path.exists(file_path): raise FileNotFoundError(f"File not found at {file_path}") + self.base_url = ( + base_url.rstrip("/") if base_url else "https://api.mistral.ai/v1" + ) self.api_key = api_key self.file_path = file_path self.timeout = timeout @@ -240,7 +242,7 @@ class MistralLoader: in a context manager to minimize memory usage duration. """ log.info("Uploading file to Mistral API") - url = f"{self.BASE_API_URL}/files" + url = f"{self.base_url}/files" def upload_request(): # MEMORY OPTIMIZATION: Use context manager to minimize file handle lifetime @@ -275,7 +277,7 @@ class MistralLoader: async def _upload_file_async(self, session: aiohttp.ClientSession) -> str: """Async file upload with streaming for better memory efficiency.""" - url = f"{self.BASE_API_URL}/files" + url = f"{self.base_url}/files" async def upload_request(): # Create multipart writer for streaming upload @@ -321,7 +323,7 @@ class MistralLoader: def _get_signed_url(self, file_id: str) -> str: """Retrieves a temporary signed URL for the uploaded file (sync version).""" log.info(f"Getting signed URL for file ID: {file_id}") - url = f"{self.BASE_API_URL}/files/{file_id}/url" + url = f"{self.base_url}/files/{file_id}/url" params = {"expiry": 1} signed_url_headers = {**self.headers, "Accept": "application/json"} @@ -346,7 +348,7 @@ class MistralLoader: self, session: aiohttp.ClientSession, file_id: str ) -> str: """Async signed URL retrieval.""" - url = f"{self.BASE_API_URL}/files/{file_id}/url" + url = f"{self.base_url}/files/{file_id}/url" params = {"expiry": 1} headers = {**self.headers, "Accept": "application/json"} @@ -373,7 +375,7 @@ class MistralLoader: def _process_ocr(self, signed_url: str) -> Dict[str, Any]: """Sends the signed URL to the OCR endpoint for processing (sync version).""" log.info("Processing OCR via Mistral API") - url = f"{self.BASE_API_URL}/ocr" + url = f"{self.base_url}/ocr" ocr_headers = { **self.headers, "Content-Type": "application/json", @@ -407,7 +409,7 @@ class MistralLoader: self, session: aiohttp.ClientSession, signed_url: str ) -> Dict[str, Any]: """Async OCR processing with timing metrics.""" - url = f"{self.BASE_API_URL}/ocr" + url = f"{self.base_url}/ocr" headers = { **self.headers, @@ -446,7 +448,7 @@ class MistralLoader: def _delete_file(self, file_id: str) -> None: """Deletes the file from Mistral storage (sync version).""" log.info(f"Deleting uploaded file ID: {file_id}") - url = f"{self.BASE_API_URL}/files/{file_id}" + url = f"{self.base_url}/files/{file_id}" try: response = requests.delete( @@ -467,7 +469,7 @@ class MistralLoader: async def delete_request(): self._debug_log(f"Deleting file ID: {file_id}") async with session.delete( - url=f"{self.BASE_API_URL}/files/{file_id}", + url=f"{self.base_url}/files/{file_id}", headers=self.headers, timeout=aiohttp.ClientTimeout( total=self.cleanup_timeout diff --git a/backend/open_webui/retrieval/utils.py b/backend/open_webui/retrieval/utils.py index 08dcde34da..f20884a4d2 100644 --- a/backend/open_webui/retrieval/utils.py +++ b/backend/open_webui/retrieval/utils.py @@ -71,6 +71,7 @@ def get_loader(request, url: str): url, verify_ssl=request.app.state.config.ENABLE_WEB_LOADER_SSL_VERIFICATION, requests_per_second=request.app.state.config.WEB_LOADER_CONCURRENT_REQUESTS, + trust_env=request.app.state.config.WEB_SEARCH_TRUST_ENV, ) @@ -159,10 +160,18 @@ def query_doc_with_hybrid_search( hybrid_bm25_weight: float, ) -> dict: try: + # First check if collection_result has the required attributes if ( not collection_result or not hasattr(collection_result, "documents") - or not collection_result.documents + or not hasattr(collection_result, "metadatas") + ): + log.warning(f"query_doc_with_hybrid_search:no_docs {collection_name}") + return {"documents": [], "metadatas": [], "distances": []} + + # Now safely check the documents content after confirming attributes exist + if ( + not collection_result.documents or len(collection_result.documents) == 0 or not collection_result.documents[0] ): @@ -507,11 +516,13 @@ def get_reranking_function(reranking_engine, reranking_model, reranking_function if reranking_function is None: return None if reranking_engine == "external": - return lambda sentences, user=None: reranking_function.predict( - sentences, user=user + return lambda query, documents, user=None: reranking_function.predict( + [(query, doc.page_content) for doc in documents], user=user ) else: - return lambda sentences, user=None: reranking_function.predict(sentences) + return lambda query, documents, user=None: reranking_function.predict( + [(query, doc.page_content) for doc in documents] + ) def get_sources_from_items( @@ -1055,9 +1066,7 @@ class RerankCompressor(BaseDocumentCompressor): scores = None if reranking: - scores = self.reranking_function( - [(query, doc.page_content) for doc in documents] - ) + scores = self.reranking_function(query, documents) else: from sentence_transformers import util diff --git a/backend/open_webui/retrieval/web/external.py b/backend/open_webui/retrieval/web/external.py index a5c8003e47..13f6a5aa68 100644 --- a/backend/open_webui/retrieval/web/external.py +++ b/backend/open_webui/retrieval/web/external.py @@ -2,27 +2,42 @@ import logging from typing import Optional, List import requests -from open_webui.retrieval.web.main import SearchResult, get_filtered_results + +from fastapi import Request + from open_webui.env import SRC_LOG_LEVELS +from open_webui.retrieval.web.main import SearchResult, get_filtered_results +from open_webui.utils.headers import include_user_info_headers + + log = logging.getLogger(__name__) log.setLevel(SRC_LOG_LEVELS["RAG"]) def search_external( + request: Request, external_url: str, external_api_key: str, query: str, count: int, filter_list: Optional[List[str]] = None, + user=None, ) -> List[SearchResult]: try: + headers = { + "User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) RAG Bot", + "Authorization": f"Bearer {external_api_key}", + } + headers = include_user_info_headers(headers, user) + + chat_id = getattr(request.state, "chat_id", None) + if chat_id: + headers["X-OpenWebUI-Chat-Id"] = str(chat_id) + response = requests.post( external_url, - headers={ - "User-Agent": "Open WebUI (https://github.com/open-webui/open-webui) RAG Bot", - "Authorization": f"Bearer {external_api_key}", - }, + headers=headers, json={ "query": query, "count": count, diff --git a/backend/open_webui/retrieval/web/firecrawl.py b/backend/open_webui/retrieval/web/firecrawl.py index acad014d70..2d9b104bca 100644 --- a/backend/open_webui/retrieval/web/firecrawl.py +++ b/backend/open_webui/retrieval/web/firecrawl.py @@ -4,7 +4,6 @@ from typing import Optional, List from open_webui.retrieval.web.main import SearchResult, get_filtered_results from open_webui.env import SRC_LOG_LEVELS -from firecrawl import Firecrawl log = logging.getLogger(__name__) log.setLevel(SRC_LOG_LEVELS["RAG"]) @@ -18,7 +17,9 @@ def search_firecrawl( filter_list: Optional[List[str]] = None, ) -> List[SearchResult]: try: - firecrawl = Firecrawl(api_key=firecrawl_api_key, api_url=firecrawl_url) + from firecrawl import FirecrawlApp + + firecrawl = FirecrawlApp(api_key=firecrawl_api_key, api_url=firecrawl_url) response = firecrawl.search( query=query, limit=count, ignore_invalid_urls=True, timeout=count * 3 ) diff --git a/backend/open_webui/retrieval/web/google_pse.py b/backend/open_webui/retrieval/web/google_pse.py index 2d2b863b42..69de24711a 100644 --- a/backend/open_webui/retrieval/web/google_pse.py +++ b/backend/open_webui/retrieval/web/google_pse.py @@ -15,6 +15,7 @@ def search_google_pse( query: str, count: int, filter_list: Optional[list[str]] = None, + referer: Optional[str] = None, ) -> list[SearchResult]: """Search using Google's Programmable Search Engine API and return the results as a list of SearchResult objects. Handles pagination for counts greater than 10. @@ -30,7 +31,11 @@ def search_google_pse( list[SearchResult]: A list of SearchResult objects. """ url = "https://www.googleapis.com/customsearch/v1" + headers = {"Content-Type": "application/json"} + if referer: + headers["Referer"] = referer + all_results = [] start_index = 1 # Google PSE start parameter is 1-based diff --git a/backend/open_webui/retrieval/web/utils.py b/backend/open_webui/retrieval/web/utils.py index f5c89b4b58..91699a157b 100644 --- a/backend/open_webui/retrieval/web/utils.py +++ b/backend/open_webui/retrieval/web/utils.py @@ -16,6 +16,8 @@ from typing import ( Union, Literal, ) + +from fastapi.concurrency import run_in_threadpool import aiohttp import certifi import validators @@ -39,7 +41,6 @@ from open_webui.config import ( ) from open_webui.env import SRC_LOG_LEVELS -from firecrawl import Firecrawl log = logging.getLogger(__name__) log.setLevel(SRC_LOG_LEVELS["RAG"]) @@ -142,13 +143,13 @@ class RateLimitMixin: class URLProcessingMixin: - def _verify_ssl_cert(self, url: str) -> bool: + async def _verify_ssl_cert(self, url: str) -> bool: """Verify SSL certificate for a URL.""" - return verify_ssl_cert(url) + return await run_in_threadpool(verify_ssl_cert, url) async def _safe_process_url(self, url: str) -> bool: """Perform safety checks before processing a URL.""" - if self.verify_ssl and not self._verify_ssl_cert(url): + if self.verify_ssl and not await self._verify_ssl_cert(url): raise ValueError(f"SSL certificate verification failed for {url}") await self._wait_for_rate_limit() return True @@ -225,7 +226,9 @@ class SafeFireCrawlLoader(BaseLoader, RateLimitMixin, URLProcessingMixin): self.params, ) try: - firecrawl = Firecrawl(api_key=self.api_key, api_url=self.api_url) + from firecrawl import FirecrawlApp + + firecrawl = FirecrawlApp(api_key=self.api_key, api_url=self.api_url) result = firecrawl.batch_scrape( self.web_paths, formats=["markdown"], @@ -264,7 +267,9 @@ class SafeFireCrawlLoader(BaseLoader, RateLimitMixin, URLProcessingMixin): self.params, ) try: - firecrawl = Firecrawl(api_key=self.api_key, api_url=self.api_url) + from firecrawl import FirecrawlApp + + firecrawl = FirecrawlApp(api_key=self.api_key, api_url=self.api_url) result = firecrawl.batch_scrape( self.web_paths, formats=["markdown"], diff --git a/backend/open_webui/routers/audio.py b/backend/open_webui/routers/audio.py index cb7a57b5b7..45b4f1e692 100644 --- a/backend/open_webui/routers/audio.py +++ b/backend/open_webui/routers/audio.py @@ -4,6 +4,7 @@ import logging import os import uuid import html +import base64 from functools import lru_cache from pydub import AudioSegment from pydub.silence import split_on_silence @@ -39,13 +40,14 @@ from open_webui.config import ( WHISPER_MODEL_DIR, CACHE_DIR, WHISPER_LANGUAGE, + ELEVENLABS_API_BASE_URL, ) from open_webui.constants import ERROR_MESSAGES from open_webui.env import ( + ENV, AIOHTTP_CLIENT_SESSION_SSL, AIOHTTP_CLIENT_TIMEOUT, - ENV, SRC_LOG_LEVELS, DEVICE_TYPE, ENABLE_FORWARD_USER_INFO_HEADERS, @@ -178,6 +180,9 @@ class STTConfigForm(BaseModel): AZURE_LOCALES: str AZURE_BASE_URL: str AZURE_MAX_SPEAKERS: str + MISTRAL_API_KEY: str + MISTRAL_API_BASE_URL: str + MISTRAL_USE_CHAT_COMPLETIONS: bool class AudioConfigUpdateForm(BaseModel): @@ -214,6 +219,9 @@ async def get_audio_config(request: Request, user=Depends(get_admin_user)): "AZURE_LOCALES": request.app.state.config.AUDIO_STT_AZURE_LOCALES, "AZURE_BASE_URL": request.app.state.config.AUDIO_STT_AZURE_BASE_URL, "AZURE_MAX_SPEAKERS": request.app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS, + "MISTRAL_API_KEY": request.app.state.config.AUDIO_STT_MISTRAL_API_KEY, + "MISTRAL_API_BASE_URL": request.app.state.config.AUDIO_STT_MISTRAL_API_BASE_URL, + "MISTRAL_USE_CHAT_COMPLETIONS": request.app.state.config.AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS, }, } @@ -255,6 +263,13 @@ async def update_audio_config( request.app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS = ( form_data.stt.AZURE_MAX_SPEAKERS ) + request.app.state.config.AUDIO_STT_MISTRAL_API_KEY = form_data.stt.MISTRAL_API_KEY + request.app.state.config.AUDIO_STT_MISTRAL_API_BASE_URL = ( + form_data.stt.MISTRAL_API_BASE_URL + ) + request.app.state.config.AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS = ( + form_data.stt.MISTRAL_USE_CHAT_COMPLETIONS + ) if request.app.state.config.STT_ENGINE == "": request.app.state.faster_whisper_model = set_faster_whisper_model( @@ -290,6 +305,9 @@ async def update_audio_config( "AZURE_LOCALES": request.app.state.config.AUDIO_STT_AZURE_LOCALES, "AZURE_BASE_URL": request.app.state.config.AUDIO_STT_AZURE_BASE_URL, "AZURE_MAX_SPEAKERS": request.app.state.config.AUDIO_STT_AZURE_MAX_SPEAKERS, + "MISTRAL_API_KEY": request.app.state.config.AUDIO_STT_MISTRAL_API_KEY, + "MISTRAL_API_BASE_URL": request.app.state.config.AUDIO_STT_MISTRAL_API_BASE_URL, + "MISTRAL_USE_CHAT_COMPLETIONS": request.app.state.config.AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS, }, } @@ -413,7 +431,7 @@ async def speech(request: Request, user=Depends(get_verified_user)): timeout=timeout, trust_env=True ) as session: async with session.post( - f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}", + f"{ELEVENLABS_API_BASE_URL}/v1/text-to-speech/{voice_id}", json={ "text": payload["input"], "model_id": request.app.state.config.TTS_MODEL, @@ -828,6 +846,186 @@ def transcription_handler(request, file_path, metadata): detail=detail if detail else "Open WebUI: Server Connection Error", ) + elif request.app.state.config.STT_ENGINE == "mistral": + # Check file exists + if not os.path.exists(file_path): + raise HTTPException(status_code=400, detail="Audio file not found") + + # Check file size + file_size = os.path.getsize(file_path) + if file_size > MAX_FILE_SIZE: + raise HTTPException( + status_code=400, + detail=f"File size exceeds limit of {MAX_FILE_SIZE_MB}MB", + ) + + api_key = request.app.state.config.AUDIO_STT_MISTRAL_API_KEY + api_base_url = ( + request.app.state.config.AUDIO_STT_MISTRAL_API_BASE_URL + or "https://api.mistral.ai/v1" + ) + use_chat_completions = ( + request.app.state.config.AUDIO_STT_MISTRAL_USE_CHAT_COMPLETIONS + ) + + if not api_key: + raise HTTPException( + status_code=400, + detail="Mistral API key is required for Mistral STT", + ) + + r = None + try: + # Use voxtral-mini-latest as the default model for transcription + model = request.app.state.config.STT_MODEL or "voxtral-mini-latest" + + log.info( + f"Mistral STT - model: {model}, " + f"method: {'chat_completions' if use_chat_completions else 'transcriptions'}" + ) + + if use_chat_completions: + # Use chat completions API with audio input + # This method requires mp3 or wav format + audio_file_to_use = file_path + + if is_audio_conversion_required(file_path): + log.debug("Converting audio to mp3 for chat completions API") + converted_path = convert_audio_to_mp3(file_path) + if converted_path: + audio_file_to_use = converted_path + else: + log.error("Audio conversion failed") + raise HTTPException( + status_code=500, + detail="Audio conversion failed. Chat completions API requires mp3 or wav format.", + ) + + # Read and encode audio file as base64 + with open(audio_file_to_use, "rb") as audio_file: + audio_base64 = base64.b64encode(audio_file.read()).decode("utf-8") + + # Prepare chat completions request + url = f"{api_base_url}/chat/completions" + + # Add language instruction if specified + language = metadata.get("language", None) if metadata else None + if language: + text_instruction = f"Transcribe this audio exactly as spoken in {language}. Do not translate it." + else: + text_instruction = "Transcribe this audio exactly as spoken in its original language. Do not translate it to another language." + + payload = { + "model": model, + "messages": [ + { + "role": "user", + "content": [ + { + "type": "input_audio", + "input_audio": audio_base64, + }, + {"type": "text", "text": text_instruction}, + ], + } + ], + } + + r = requests.post( + url=url, + json=payload, + headers={ + "Authorization": f"Bearer {api_key}", + "Content-Type": "application/json", + }, + ) + + r.raise_for_status() + response = r.json() + + # Extract transcript from chat completion response + transcript = ( + response.get("choices", [{}])[0] + .get("message", {}) + .get("content", "") + .strip() + ) + if not transcript: + raise ValueError("Empty transcript in response") + + data = {"text": transcript} + + else: + # Use dedicated transcriptions API + url = f"{api_base_url}/audio/transcriptions" + + # Determine the MIME type + mime_type, _ = mimetypes.guess_type(file_path) + if not mime_type: + mime_type = "audio/webm" + + # Use context manager to ensure file is properly closed + with open(file_path, "rb") as audio_file: + files = {"file": (filename, audio_file, mime_type)} + data_form = {"model": model} + + # Add language if specified in metadata + language = metadata.get("language", None) if metadata else None + if language: + data_form["language"] = language + + r = requests.post( + url=url, + files=files, + data=data_form, + headers={ + "Authorization": f"Bearer {api_key}", + }, + ) + + r.raise_for_status() + response = r.json() + + # Extract transcript from response + transcript = response.get("text", "").strip() + if not transcript: + raise ValueError("Empty transcript in response") + + data = {"text": transcript} + + # Save transcript to json file (consistent with other providers) + transcript_file = f"{file_dir}/{id}.json" + with open(transcript_file, "w") as f: + json.dump(data, f) + + log.debug(data) + return data + + except ValueError as e: + log.exception("Error parsing Mistral response") + raise HTTPException( + status_code=500, + detail=f"Failed to parse Mistral response: {str(e)}", + ) + except requests.exceptions.RequestException as e: + log.exception(e) + detail = None + + try: + if r is not None and r.status_code != 200: + res = r.json() + if "error" in res: + detail = f"External: {res['error'].get('message', '')}" + else: + detail = f"External: {r.text}" + except Exception: + detail = f"External: {e}" + + raise HTTPException( + status_code=getattr(r, "status_code", 500) if r else 500, + detail=detail if detail else "Open WebUI: Server Connection Error", + ) + def transcribe(request: Request, file_path: str, metadata: Optional[dict] = None): log.info(f"transcribe: {file_path} {metadata}") @@ -1037,7 +1235,7 @@ def get_available_models(request: Request) -> list[dict]: elif request.app.state.config.TTS_ENGINE == "elevenlabs": try: response = requests.get( - "https://api.elevenlabs.io/v1/models", + f"{ELEVENLABS_API_BASE_URL}/v1/models", headers={ "xi-api-key": request.app.state.config.TTS_API_KEY, "Content-Type": "application/json", @@ -1141,7 +1339,7 @@ def get_elevenlabs_voices(api_key: str) -> dict: try: # TODO: Add retries response = requests.get( - "https://api.elevenlabs.io/v1/voices", + f"{ELEVENLABS_API_BASE_URL}/v1/voices", headers={ "xi-api-key": api_key, "Content-Type": "application/json", diff --git a/backend/open_webui/routers/auths.py b/backend/open_webui/routers/auths.py index f261673f38..8a777c2afb 100644 --- a/backend/open_webui/routers/auths.py +++ b/backend/open_webui/routers/auths.py @@ -35,7 +35,7 @@ from open_webui.env import ( ) from fastapi import APIRouter, Depends, HTTPException, Request, status from fastapi.responses import RedirectResponse, Response, JSONResponse -from open_webui.config import OPENID_PROVIDER_URL, ENABLE_OAUTH_SIGNUP, ENABLE_LDAP +from open_webui.config import OPENID_PROVIDER_URL, ENABLE_OAUTH_SIGNUP, ENABLE_LDAP, ENABLE_PASSWORD_AUTH from pydantic import BaseModel from open_webui.utils.misc import parse_duration, validate_email_format @@ -185,7 +185,17 @@ async def update_password( ############################ @router.post("/ldap", response_model=SessionUserResponse) async def ldap_auth(request: Request, response: Response, form_data: LdapForm): - ENABLE_LDAP = request.app.state.config.ENABLE_LDAP + # Security checks FIRST - before loading any config + if not request.app.state.config.ENABLE_LDAP: + raise HTTPException(400, detail="LDAP authentication is not enabled") + + if (not ENABLE_PASSWORD_AUTH): + raise HTTPException( + status_code=status.HTTP_403_FORBIDDEN, + detail=ERROR_MESSAGES.ACTION_PROHIBITED, + ) + + # NOW load LDAP config variables LDAP_SERVER_LABEL = request.app.state.config.LDAP_SERVER_LABEL LDAP_SERVER_HOST = request.app.state.config.LDAP_SERVER_HOST LDAP_SERVER_PORT = request.app.state.config.LDAP_SERVER_PORT @@ -206,9 +216,6 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm): else "ALL" ) - if not ENABLE_LDAP: - raise HTTPException(400, detail="LDAP authentication is not enabled") - try: tls = Tls( validate=LDAP_VALIDATE_CERT, @@ -463,6 +470,12 @@ async def ldap_auth(request: Request, response: Response, form_data: LdapForm): @router.post("/signin", response_model=SessionUserResponse) async def signin(request: Request, response: Response, form_data: SigninForm): + if (not ENABLE_PASSWORD_AUTH): + raise HTTPException( + status_code=status.HTTP_403_FORBIDDEN, + detail=ERROR_MESSAGES.ACTION_PROHIBITED, + ) + if WEBUI_AUTH_TRUSTED_EMAIL_HEADER: if WEBUI_AUTH_TRUSTED_EMAIL_HEADER not in request.headers: raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_TRUSTED_HEADER) diff --git a/backend/open_webui/routers/configs.py b/backend/open_webui/routers/configs.py index e7fa13d1ff..5fd744c793 100644 --- a/backend/open_webui/routers/configs.py +++ b/backend/open_webui/routers/configs.py @@ -1,4 +1,5 @@ import logging +import copy from fastapi import APIRouter, Depends, Request, HTTPException from pydantic import BaseModel, ConfigDict import aiohttp @@ -15,6 +16,7 @@ from open_webui.utils.tools import ( set_tool_servers, ) from open_webui.utils.mcp.client import MCPClient +from open_webui.models.oauth_sessions import OAuthSessions from open_webui.env import SRC_LOG_LEVELS @@ -165,6 +167,21 @@ async def set_tool_servers_config( form_data: ToolServersConfigForm, user=Depends(get_admin_user), ): + for connection in request.app.state.config.TOOL_SERVER_CONNECTIONS: + server_type = connection.get("type", "openapi") + auth_type = connection.get("auth_type", "none") + + if auth_type == "oauth_2.1": + # Remove existing OAuth clients for tool servers + server_id = connection.get("info", {}).get("id") + client_key = f"{server_type}:{server_id}" + + try: + request.app.state.oauth_client_manager.remove_client(client_key) + except: + pass + + # Set new tool server connections request.app.state.config.TOOL_SERVER_CONNECTIONS = [ connection.model_dump() for connection in form_data.TOOL_SERVER_CONNECTIONS ] @@ -176,6 +193,7 @@ async def set_tool_servers_config( if server_type == "mcp": server_id = connection.get("info", {}).get("id") auth_type = connection.get("auth_type", "none") + if auth_type == "oauth_2.1" and server_id: try: oauth_client_info = connection.get("info", {}).get( @@ -211,7 +229,7 @@ async def verify_tool_servers_config( log.debug( f"Trying to fetch OAuth 2.1 discovery document from {discovery_url}" ) - async with aiohttp.ClientSession() as session: + async with aiohttp.ClientSession(trust_env=True) as session: async with session.get( discovery_url ) as oauth_server_metadata_response: diff --git a/backend/open_webui/routers/files.py b/backend/open_webui/routers/files.py index 84d8f841cf..2a5c3e5bb1 100644 --- a/backend/open_webui/routers/files.py +++ b/backend/open_webui/routers/files.py @@ -115,6 +115,10 @@ def process_uploaded_file(request, file, file_path, file_item, file_metadata, us request.app.state.config.CONTENT_EXTRACTION_ENGINE == "external" ): process_file(request, ProcessFileForm(file_id=file_item.id), user=user) + else: + raise Exception( + f"File type {file.content_type} is not supported for processing" + ) else: log.info( f"File type {file.content_type} is not provided, but trying to process anyway" diff --git a/backend/open_webui/routers/images.py b/backend/open_webui/routers/images.py index 059b3a23d7..0a1de28cc7 100644 --- a/backend/open_webui/routers/images.py +++ b/backend/open_webui/routers/images.py @@ -1,5 +1,6 @@ import asyncio import base64 +import uuid import io import json import logging @@ -10,23 +11,22 @@ from typing import Optional from urllib.parse import quote import requests -from fastapi import ( - APIRouter, - Depends, - HTTPException, - Request, - UploadFile, -) +from fastapi import APIRouter, Depends, HTTPException, Request, UploadFile +from fastapi.responses import FileResponse from open_webui.config import CACHE_DIR from open_webui.constants import ERROR_MESSAGES from open_webui.env import ENABLE_FORWARD_USER_INFO_HEADERS, SRC_LOG_LEVELS -from open_webui.routers.files import upload_file_handler +from open_webui.routers.files import upload_file_handler, get_file_content_by_id from open_webui.utils.auth import get_admin_user, get_verified_user +from open_webui.utils.headers import include_user_info_headers from open_webui.utils.images.comfyui import ( - ComfyUIGenerateImageForm, + ComfyUICreateImageForm, + ComfyUIEditImageForm, ComfyUIWorkflow, - comfyui_generate_image, + comfyui_upload_image, + comfyui_create_image, + comfyui_edit_image, ) from pydantic import BaseModel @@ -36,210 +36,9 @@ log.setLevel(SRC_LOG_LEVELS["IMAGES"]) IMAGE_CACHE_DIR = CACHE_DIR / "image" / "generations" IMAGE_CACHE_DIR.mkdir(parents=True, exist_ok=True) - router = APIRouter() -@router.get("/config") -async def get_config(request: Request, user=Depends(get_admin_user)): - return { - "enabled": request.app.state.config.ENABLE_IMAGE_GENERATION, - "engine": request.app.state.config.IMAGE_GENERATION_ENGINE, - "prompt_generation": request.app.state.config.ENABLE_IMAGE_PROMPT_GENERATION, - "openai": { - "OPENAI_API_BASE_URL": request.app.state.config.IMAGES_OPENAI_API_BASE_URL, - "OPENAI_API_VERSION": request.app.state.config.IMAGES_OPENAI_API_VERSION, - "OPENAI_API_KEY": request.app.state.config.IMAGES_OPENAI_API_KEY, - }, - "automatic1111": { - "AUTOMATIC1111_BASE_URL": request.app.state.config.AUTOMATIC1111_BASE_URL, - "AUTOMATIC1111_API_AUTH": request.app.state.config.AUTOMATIC1111_API_AUTH, - "AUTOMATIC1111_CFG_SCALE": request.app.state.config.AUTOMATIC1111_CFG_SCALE, - "AUTOMATIC1111_SAMPLER": request.app.state.config.AUTOMATIC1111_SAMPLER, - "AUTOMATIC1111_SCHEDULER": request.app.state.config.AUTOMATIC1111_SCHEDULER, - }, - "comfyui": { - "COMFYUI_BASE_URL": request.app.state.config.COMFYUI_BASE_URL, - "COMFYUI_API_KEY": request.app.state.config.COMFYUI_API_KEY, - "COMFYUI_WORKFLOW": request.app.state.config.COMFYUI_WORKFLOW, - "COMFYUI_WORKFLOW_NODES": request.app.state.config.COMFYUI_WORKFLOW_NODES, - }, - "gemini": { - "GEMINI_API_BASE_URL": request.app.state.config.IMAGES_GEMINI_API_BASE_URL, - "GEMINI_API_KEY": request.app.state.config.IMAGES_GEMINI_API_KEY, - }, - } - - -class OpenAIConfigForm(BaseModel): - OPENAI_API_BASE_URL: str - OPENAI_API_VERSION: str - OPENAI_API_KEY: str - - -class Automatic1111ConfigForm(BaseModel): - AUTOMATIC1111_BASE_URL: str - AUTOMATIC1111_API_AUTH: str - AUTOMATIC1111_CFG_SCALE: Optional[str | float | int] - AUTOMATIC1111_SAMPLER: Optional[str] - AUTOMATIC1111_SCHEDULER: Optional[str] - - -class ComfyUIConfigForm(BaseModel): - COMFYUI_BASE_URL: str - COMFYUI_API_KEY: str - COMFYUI_WORKFLOW: str - COMFYUI_WORKFLOW_NODES: list[dict] - - -class GeminiConfigForm(BaseModel): - GEMINI_API_BASE_URL: str - GEMINI_API_KEY: str - - -class ConfigForm(BaseModel): - enabled: bool - engine: str - prompt_generation: bool - openai: OpenAIConfigForm - automatic1111: Automatic1111ConfigForm - comfyui: ComfyUIConfigForm - gemini: GeminiConfigForm - - -@router.post("/config/update") -async def update_config( - request: Request, form_data: ConfigForm, user=Depends(get_admin_user) -): - request.app.state.config.IMAGE_GENERATION_ENGINE = form_data.engine - request.app.state.config.ENABLE_IMAGE_GENERATION = form_data.enabled - - request.app.state.config.ENABLE_IMAGE_PROMPT_GENERATION = ( - form_data.prompt_generation - ) - - request.app.state.config.IMAGES_OPENAI_API_BASE_URL = ( - form_data.openai.OPENAI_API_BASE_URL - ) - request.app.state.config.IMAGES_OPENAI_API_VERSION = ( - form_data.openai.OPENAI_API_VERSION - ) - request.app.state.config.IMAGES_OPENAI_API_KEY = form_data.openai.OPENAI_API_KEY - - request.app.state.config.IMAGES_GEMINI_API_BASE_URL = ( - form_data.gemini.GEMINI_API_BASE_URL - ) - request.app.state.config.IMAGES_GEMINI_API_KEY = form_data.gemini.GEMINI_API_KEY - - request.app.state.config.AUTOMATIC1111_BASE_URL = ( - form_data.automatic1111.AUTOMATIC1111_BASE_URL - ) - request.app.state.config.AUTOMATIC1111_API_AUTH = ( - form_data.automatic1111.AUTOMATIC1111_API_AUTH - ) - - request.app.state.config.AUTOMATIC1111_CFG_SCALE = ( - float(form_data.automatic1111.AUTOMATIC1111_CFG_SCALE) - if form_data.automatic1111.AUTOMATIC1111_CFG_SCALE - else None - ) - request.app.state.config.AUTOMATIC1111_SAMPLER = ( - form_data.automatic1111.AUTOMATIC1111_SAMPLER - if form_data.automatic1111.AUTOMATIC1111_SAMPLER - else None - ) - request.app.state.config.AUTOMATIC1111_SCHEDULER = ( - form_data.automatic1111.AUTOMATIC1111_SCHEDULER - if form_data.automatic1111.AUTOMATIC1111_SCHEDULER - else None - ) - - request.app.state.config.COMFYUI_BASE_URL = ( - form_data.comfyui.COMFYUI_BASE_URL.strip("/") - ) - request.app.state.config.COMFYUI_API_KEY = form_data.comfyui.COMFYUI_API_KEY - - request.app.state.config.COMFYUI_WORKFLOW = form_data.comfyui.COMFYUI_WORKFLOW - request.app.state.config.COMFYUI_WORKFLOW_NODES = ( - form_data.comfyui.COMFYUI_WORKFLOW_NODES - ) - - return { - "enabled": request.app.state.config.ENABLE_IMAGE_GENERATION, - "engine": request.app.state.config.IMAGE_GENERATION_ENGINE, - "prompt_generation": request.app.state.config.ENABLE_IMAGE_PROMPT_GENERATION, - "openai": { - "OPENAI_API_BASE_URL": request.app.state.config.IMAGES_OPENAI_API_BASE_URL, - "OPENAI_API_VERSION": request.app.state.config.IMAGES_OPENAI_API_VERSION, - "OPENAI_API_KEY": request.app.state.config.IMAGES_OPENAI_API_KEY, - }, - "automatic1111": { - "AUTOMATIC1111_BASE_URL": request.app.state.config.AUTOMATIC1111_BASE_URL, - "AUTOMATIC1111_API_AUTH": request.app.state.config.AUTOMATIC1111_API_AUTH, - "AUTOMATIC1111_CFG_SCALE": request.app.state.config.AUTOMATIC1111_CFG_SCALE, - "AUTOMATIC1111_SAMPLER": request.app.state.config.AUTOMATIC1111_SAMPLER, - "AUTOMATIC1111_SCHEDULER": request.app.state.config.AUTOMATIC1111_SCHEDULER, - }, - "comfyui": { - "COMFYUI_BASE_URL": request.app.state.config.COMFYUI_BASE_URL, - "COMFYUI_API_KEY": request.app.state.config.COMFYUI_API_KEY, - "COMFYUI_WORKFLOW": request.app.state.config.COMFYUI_WORKFLOW, - "COMFYUI_WORKFLOW_NODES": request.app.state.config.COMFYUI_WORKFLOW_NODES, - }, - "gemini": { - "GEMINI_API_BASE_URL": request.app.state.config.IMAGES_GEMINI_API_BASE_URL, - "GEMINI_API_KEY": request.app.state.config.IMAGES_GEMINI_API_KEY, - }, - } - - -def get_automatic1111_api_auth(request: Request): - if request.app.state.config.AUTOMATIC1111_API_AUTH is None: - return "" - else: - auth1111_byte_string = request.app.state.config.AUTOMATIC1111_API_AUTH.encode( - "utf-8" - ) - auth1111_base64_encoded_bytes = base64.b64encode(auth1111_byte_string) - auth1111_base64_encoded_string = auth1111_base64_encoded_bytes.decode("utf-8") - return f"Basic {auth1111_base64_encoded_string}" - - -@router.get("/config/url/verify") -async def verify_url(request: Request, user=Depends(get_admin_user)): - if request.app.state.config.IMAGE_GENERATION_ENGINE == "automatic1111": - try: - r = requests.get( - url=f"{request.app.state.config.AUTOMATIC1111_BASE_URL}/sdapi/v1/options", - headers={"authorization": get_automatic1111_api_auth(request)}, - ) - r.raise_for_status() - return True - except Exception: - request.app.state.config.ENABLE_IMAGE_GENERATION = False - raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL) - elif request.app.state.config.IMAGE_GENERATION_ENGINE == "comfyui": - - headers = None - if request.app.state.config.COMFYUI_API_KEY: - headers = { - "Authorization": f"Bearer {request.app.state.config.COMFYUI_API_KEY}" - } - - try: - r = requests.get( - url=f"{request.app.state.config.COMFYUI_BASE_URL}/object_info", - headers=headers, - ) - r.raise_for_status() - return True - except Exception: - request.app.state.config.ENABLE_IMAGE_GENERATION = False - raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL) - else: - return True - - def set_image_model(request: Request, model: str): log.info(f"Setting image model to {model}") request.app.state.config.IMAGE_GENERATION_MODEL = model @@ -295,28 +94,101 @@ def get_image_model(request): raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e)) -class ImageConfigForm(BaseModel): - MODEL: str - IMAGE_SIZE: str - IMAGE_STEPS: int +class ImagesConfig(BaseModel): + ENABLE_IMAGE_GENERATION: bool + ENABLE_IMAGE_PROMPT_GENERATION: bool + + IMAGE_GENERATION_ENGINE: str + IMAGE_GENERATION_MODEL: str + IMAGE_SIZE: Optional[str] + IMAGE_STEPS: Optional[int] + + IMAGES_OPENAI_API_BASE_URL: str + IMAGES_OPENAI_API_KEY: str + IMAGES_OPENAI_API_VERSION: str + + AUTOMATIC1111_BASE_URL: str + AUTOMATIC1111_API_AUTH: str + AUTOMATIC1111_PARAMS: Optional[dict | str] + + COMFYUI_BASE_URL: str + COMFYUI_API_KEY: str + COMFYUI_WORKFLOW: str + COMFYUI_WORKFLOW_NODES: list[dict] + + IMAGES_GEMINI_API_BASE_URL: str + IMAGES_GEMINI_API_KEY: str + IMAGES_GEMINI_ENDPOINT_METHOD: str + + IMAGE_EDIT_ENGINE: str + IMAGE_EDIT_MODEL: str + IMAGE_EDIT_SIZE: Optional[str] + + IMAGES_EDIT_OPENAI_API_BASE_URL: str + IMAGES_EDIT_OPENAI_API_KEY: str + IMAGES_EDIT_OPENAI_API_VERSION: str + IMAGES_EDIT_GEMINI_API_BASE_URL: str + IMAGES_EDIT_GEMINI_API_KEY: str + IMAGES_EDIT_COMFYUI_BASE_URL: str + IMAGES_EDIT_COMFYUI_API_KEY: str + IMAGES_EDIT_COMFYUI_WORKFLOW: str + IMAGES_EDIT_COMFYUI_WORKFLOW_NODES: list[dict] -@router.get("/image/config") -async def get_image_config(request: Request, user=Depends(get_admin_user)): +@router.get("/config", response_model=ImagesConfig) +async def get_config(request: Request, user=Depends(get_admin_user)): return { - "MODEL": request.app.state.config.IMAGE_GENERATION_MODEL, + "ENABLE_IMAGE_GENERATION": request.app.state.config.ENABLE_IMAGE_GENERATION, + "ENABLE_IMAGE_PROMPT_GENERATION": request.app.state.config.ENABLE_IMAGE_PROMPT_GENERATION, + "IMAGE_GENERATION_ENGINE": request.app.state.config.IMAGE_GENERATION_ENGINE, + "IMAGE_GENERATION_MODEL": request.app.state.config.IMAGE_GENERATION_MODEL, "IMAGE_SIZE": request.app.state.config.IMAGE_SIZE, "IMAGE_STEPS": request.app.state.config.IMAGE_STEPS, + "IMAGES_OPENAI_API_BASE_URL": request.app.state.config.IMAGES_OPENAI_API_BASE_URL, + "IMAGES_OPENAI_API_KEY": request.app.state.config.IMAGES_OPENAI_API_KEY, + "IMAGES_OPENAI_API_VERSION": request.app.state.config.IMAGES_OPENAI_API_VERSION, + "AUTOMATIC1111_BASE_URL": request.app.state.config.AUTOMATIC1111_BASE_URL, + "AUTOMATIC1111_API_AUTH": request.app.state.config.AUTOMATIC1111_API_AUTH, + "AUTOMATIC1111_PARAMS": request.app.state.config.AUTOMATIC1111_PARAMS, + "COMFYUI_BASE_URL": request.app.state.config.COMFYUI_BASE_URL, + "COMFYUI_API_KEY": request.app.state.config.COMFYUI_API_KEY, + "COMFYUI_WORKFLOW": request.app.state.config.COMFYUI_WORKFLOW, + "COMFYUI_WORKFLOW_NODES": request.app.state.config.COMFYUI_WORKFLOW_NODES, + "IMAGES_GEMINI_API_BASE_URL": request.app.state.config.IMAGES_GEMINI_API_BASE_URL, + "IMAGES_GEMINI_API_KEY": request.app.state.config.IMAGES_GEMINI_API_KEY, + "IMAGES_GEMINI_ENDPOINT_METHOD": request.app.state.config.IMAGES_GEMINI_ENDPOINT_METHOD, + "IMAGE_EDIT_ENGINE": request.app.state.config.IMAGE_EDIT_ENGINE, + "IMAGE_EDIT_MODEL": request.app.state.config.IMAGE_EDIT_MODEL, + "IMAGE_EDIT_SIZE": request.app.state.config.IMAGE_EDIT_SIZE, + "IMAGES_EDIT_OPENAI_API_BASE_URL": request.app.state.config.IMAGES_EDIT_OPENAI_API_BASE_URL, + "IMAGES_EDIT_OPENAI_API_KEY": request.app.state.config.IMAGES_EDIT_OPENAI_API_KEY, + "IMAGES_EDIT_OPENAI_API_VERSION": request.app.state.config.IMAGES_EDIT_OPENAI_API_VERSION, + "IMAGES_EDIT_GEMINI_API_BASE_URL": request.app.state.config.IMAGES_EDIT_GEMINI_API_BASE_URL, + "IMAGES_EDIT_GEMINI_API_KEY": request.app.state.config.IMAGES_EDIT_GEMINI_API_KEY, + "IMAGES_EDIT_COMFYUI_BASE_URL": request.app.state.config.IMAGES_EDIT_COMFYUI_BASE_URL, + "IMAGES_EDIT_COMFYUI_API_KEY": request.app.state.config.IMAGES_EDIT_COMFYUI_API_KEY, + "IMAGES_EDIT_COMFYUI_WORKFLOW": request.app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW, + "IMAGES_EDIT_COMFYUI_WORKFLOW_NODES": request.app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW_NODES, } -@router.post("/image/config/update") -async def update_image_config( - request: Request, form_data: ImageConfigForm, user=Depends(get_admin_user) +@router.post("/config/update") +async def update_config( + request: Request, form_data: ImagesConfig, user=Depends(get_admin_user) ): - set_image_model(request, form_data.MODEL) + request.app.state.config.ENABLE_IMAGE_GENERATION = form_data.ENABLE_IMAGE_GENERATION - if form_data.IMAGE_SIZE == "auto" and form_data.MODEL != "gpt-image-1": + # Create Image + request.app.state.config.ENABLE_IMAGE_PROMPT_GENERATION = ( + form_data.ENABLE_IMAGE_PROMPT_GENERATION + ) + + request.app.state.config.IMAGE_GENERATION_ENGINE = form_data.IMAGE_GENERATION_ENGINE + set_image_model(request, form_data.IMAGE_GENERATION_MODEL) + if ( + form_data.IMAGE_SIZE == "auto" + and form_data.IMAGE_GENERATION_MODEL != "gpt-image-1" + ): raise HTTPException( status_code=400, detail=ERROR_MESSAGES.INCORRECT_FORMAT( @@ -325,7 +197,11 @@ async def update_image_config( ) pattern = r"^\d+x\d+$" - if form_data.IMAGE_SIZE == "auto" or re.match(pattern, form_data.IMAGE_SIZE): + if ( + form_data.IMAGE_SIZE == "auto" + or form_data.IMAGE_SIZE == "" + or re.match(pattern, form_data.IMAGE_SIZE) + ): request.app.state.config.IMAGE_SIZE = form_data.IMAGE_SIZE else: raise HTTPException( @@ -341,13 +217,146 @@ async def update_image_config( detail=ERROR_MESSAGES.INCORRECT_FORMAT(" (e.g., 50)."), ) + request.app.state.config.IMAGES_OPENAI_API_BASE_URL = ( + form_data.IMAGES_OPENAI_API_BASE_URL + ) + request.app.state.config.IMAGES_OPENAI_API_KEY = form_data.IMAGES_OPENAI_API_KEY + request.app.state.config.IMAGES_OPENAI_API_VERSION = ( + form_data.IMAGES_OPENAI_API_VERSION + ) + + request.app.state.config.AUTOMATIC1111_BASE_URL = form_data.AUTOMATIC1111_BASE_URL + request.app.state.config.AUTOMATIC1111_API_AUTH = form_data.AUTOMATIC1111_API_AUTH + request.app.state.config.AUTOMATIC1111_PARAMS = form_data.AUTOMATIC1111_PARAMS + + request.app.state.config.COMFYUI_BASE_URL = form_data.COMFYUI_BASE_URL.strip("/") + request.app.state.config.COMFYUI_API_KEY = form_data.COMFYUI_API_KEY + request.app.state.config.COMFYUI_WORKFLOW = form_data.COMFYUI_WORKFLOW + request.app.state.config.COMFYUI_WORKFLOW_NODES = form_data.COMFYUI_WORKFLOW_NODES + + request.app.state.config.IMAGES_GEMINI_API_BASE_URL = ( + form_data.IMAGES_GEMINI_API_BASE_URL + ) + request.app.state.config.IMAGES_GEMINI_API_KEY = form_data.IMAGES_GEMINI_API_KEY + request.app.state.config.IMAGES_GEMINI_ENDPOINT_METHOD = ( + form_data.IMAGES_GEMINI_ENDPOINT_METHOD + ) + + # Edit Image + request.app.state.config.IMAGE_EDIT_ENGINE = form_data.IMAGE_EDIT_ENGINE + request.app.state.config.IMAGE_EDIT_MODEL = form_data.IMAGE_EDIT_MODEL + request.app.state.config.IMAGE_EDIT_SIZE = form_data.IMAGE_EDIT_SIZE + + request.app.state.config.IMAGES_EDIT_OPENAI_API_BASE_URL = ( + form_data.IMAGES_EDIT_OPENAI_API_BASE_URL + ) + request.app.state.config.IMAGES_EDIT_OPENAI_API_KEY = ( + form_data.IMAGES_EDIT_OPENAI_API_KEY + ) + request.app.state.config.IMAGES_EDIT_OPENAI_API_VERSION = ( + form_data.IMAGES_EDIT_OPENAI_API_VERSION + ) + + request.app.state.config.IMAGES_EDIT_GEMINI_API_BASE_URL = ( + form_data.IMAGES_EDIT_GEMINI_API_BASE_URL + ) + request.app.state.config.IMAGES_EDIT_GEMINI_API_KEY = ( + form_data.IMAGES_EDIT_GEMINI_API_KEY + ) + + request.app.state.config.IMAGES_EDIT_COMFYUI_BASE_URL = ( + form_data.IMAGES_EDIT_COMFYUI_BASE_URL.strip("/") + ) + request.app.state.config.IMAGES_EDIT_COMFYUI_API_KEY = ( + form_data.IMAGES_EDIT_COMFYUI_API_KEY + ) + request.app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW = ( + form_data.IMAGES_EDIT_COMFYUI_WORKFLOW + ) + request.app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW_NODES = ( + form_data.IMAGES_EDIT_COMFYUI_WORKFLOW_NODES + ) + return { - "MODEL": request.app.state.config.IMAGE_GENERATION_MODEL, + "ENABLE_IMAGE_GENERATION": request.app.state.config.ENABLE_IMAGE_GENERATION, + "ENABLE_IMAGE_PROMPT_GENERATION": request.app.state.config.ENABLE_IMAGE_PROMPT_GENERATION, + "IMAGE_GENERATION_ENGINE": request.app.state.config.IMAGE_GENERATION_ENGINE, + "IMAGE_GENERATION_MODEL": request.app.state.config.IMAGE_GENERATION_MODEL, "IMAGE_SIZE": request.app.state.config.IMAGE_SIZE, "IMAGE_STEPS": request.app.state.config.IMAGE_STEPS, + "IMAGES_OPENAI_API_BASE_URL": request.app.state.config.IMAGES_OPENAI_API_BASE_URL, + "IMAGES_OPENAI_API_KEY": request.app.state.config.IMAGES_OPENAI_API_KEY, + "IMAGES_OPENAI_API_VERSION": request.app.state.config.IMAGES_OPENAI_API_VERSION, + "AUTOMATIC1111_BASE_URL": request.app.state.config.AUTOMATIC1111_BASE_URL, + "AUTOMATIC1111_API_AUTH": request.app.state.config.AUTOMATIC1111_API_AUTH, + "AUTOMATIC1111_PARAMS": request.app.state.config.AUTOMATIC1111_PARAMS, + "COMFYUI_BASE_URL": request.app.state.config.COMFYUI_BASE_URL, + "COMFYUI_API_KEY": request.app.state.config.COMFYUI_API_KEY, + "COMFYUI_WORKFLOW": request.app.state.config.COMFYUI_WORKFLOW, + "COMFYUI_WORKFLOW_NODES": request.app.state.config.COMFYUI_WORKFLOW_NODES, + "IMAGES_GEMINI_API_BASE_URL": request.app.state.config.IMAGES_GEMINI_API_BASE_URL, + "IMAGES_GEMINI_API_KEY": request.app.state.config.IMAGES_GEMINI_API_KEY, + "IMAGES_GEMINI_ENDPOINT_METHOD": request.app.state.config.IMAGES_GEMINI_ENDPOINT_METHOD, + "IMAGE_EDIT_ENGINE": request.app.state.config.IMAGE_EDIT_ENGINE, + "IMAGE_EDIT_MODEL": request.app.state.config.IMAGE_EDIT_MODEL, + "IMAGE_EDIT_SIZE": request.app.state.config.IMAGE_EDIT_SIZE, + "IMAGES_EDIT_OPENAI_API_BASE_URL": request.app.state.config.IMAGES_EDIT_OPENAI_API_BASE_URL, + "IMAGES_EDIT_OPENAI_API_KEY": request.app.state.config.IMAGES_EDIT_OPENAI_API_KEY, + "IMAGES_EDIT_OPENAI_API_VERSION": request.app.state.config.IMAGES_EDIT_OPENAI_API_VERSION, + "IMAGES_EDIT_GEMINI_API_BASE_URL": request.app.state.config.IMAGES_EDIT_GEMINI_API_BASE_URL, + "IMAGES_EDIT_GEMINI_API_KEY": request.app.state.config.IMAGES_EDIT_GEMINI_API_KEY, + "IMAGES_EDIT_COMFYUI_BASE_URL": request.app.state.config.IMAGES_EDIT_COMFYUI_BASE_URL, + "IMAGES_EDIT_COMFYUI_API_KEY": request.app.state.config.IMAGES_EDIT_COMFYUI_API_KEY, + "IMAGES_EDIT_COMFYUI_WORKFLOW": request.app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW, + "IMAGES_EDIT_COMFYUI_WORKFLOW_NODES": request.app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW_NODES, } +def get_automatic1111_api_auth(request: Request): + if request.app.state.config.AUTOMATIC1111_API_AUTH is None: + return "" + else: + auth1111_byte_string = request.app.state.config.AUTOMATIC1111_API_AUTH.encode( + "utf-8" + ) + auth1111_base64_encoded_bytes = base64.b64encode(auth1111_byte_string) + auth1111_base64_encoded_string = auth1111_base64_encoded_bytes.decode("utf-8") + return f"Basic {auth1111_base64_encoded_string}" + + +@router.get("/config/url/verify") +async def verify_url(request: Request, user=Depends(get_admin_user)): + if request.app.state.config.IMAGE_GENERATION_ENGINE == "automatic1111": + try: + r = requests.get( + url=f"{request.app.state.config.AUTOMATIC1111_BASE_URL}/sdapi/v1/options", + headers={"authorization": get_automatic1111_api_auth(request)}, + ) + r.raise_for_status() + return True + except Exception: + request.app.state.config.ENABLE_IMAGE_GENERATION = False + raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL) + elif request.app.state.config.IMAGE_GENERATION_ENGINE == "comfyui": + headers = None + if request.app.state.config.COMFYUI_API_KEY: + headers = { + "Authorization": f"Bearer {request.app.state.config.COMFYUI_API_KEY}" + } + try: + r = requests.get( + url=f"{request.app.state.config.COMFYUI_BASE_URL}/object_info", + headers=headers, + ) + r.raise_for_status() + return True + except Exception: + request.app.state.config.ENABLE_IMAGE_GENERATION = False + raise HTTPException(status_code=400, detail=ERROR_MESSAGES.INVALID_URL) + else: + return True + + @router.get("/models") def get_models(request: Request, user=Depends(get_verified_user)): try: @@ -430,7 +439,7 @@ def get_models(request: Request, user=Depends(get_verified_user)): raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e)) -class GenerateImageForm(BaseModel): +class CreateImageForm(BaseModel): model: Optional[str] = None prompt: str size: Optional[str] = None @@ -438,41 +447,38 @@ class GenerateImageForm(BaseModel): negative_prompt: Optional[str] = None -def load_b64_image_data(b64_str): +GenerateImageForm = CreateImageForm # Alias for backward compatibility + + +def get_image_data(data: str, headers=None): try: - if "," in b64_str: - header, encoded = b64_str.split(",", 1) - mime_type = header.split(";")[0].lstrip("data:") - img_data = base64.b64decode(encoded) + if data.startswith("http://") or data.startswith("https://"): + if headers: + r = requests.get(data, headers=headers) + else: + r = requests.get(data) + + r.raise_for_status() + if r.headers["content-type"].split("/")[0] == "image": + mime_type = r.headers["content-type"] + return r.content, mime_type + else: + log.error("Url does not point to an image.") + return None else: - mime_type = "image/png" - img_data = base64.b64decode(b64_str) - return img_data, mime_type + if "," in data: + header, encoded = data.split(",", 1) + mime_type = header.split(";")[0].lstrip("data:") + img_data = base64.b64decode(encoded) + else: + mime_type = "image/png" + img_data = base64.b64decode(data) + return img_data, mime_type except Exception as e: log.exception(f"Error loading image data: {e}") return None, None -def load_url_image_data(url, headers=None): - try: - if headers: - r = requests.get(url, headers=headers) - else: - r = requests.get(url) - - r.raise_for_status() - if r.headers["content-type"].split("/")[0] == "image": - mime_type = r.headers["content-type"] - return r.content, mime_type - else: - log.error("Url does not point to an image.") - return None - - except Exception as e: - log.exception(f"Error saving image: {e}") - return None - - def upload_image(request, image_data, content_type, metadata, user): image_format = mimetypes.guess_extension(content_type) file = UploadFile( @@ -496,7 +502,7 @@ def upload_image(request, image_data, content_type, metadata, user): @router.post("/generations") async def image_generations( request: Request, - form_data: GenerateImageForm, + form_data: CreateImageForm, user=Depends(get_verified_user), ): # if IMAGE_SIZE = 'auto', default WidthxHeight to the 512x512 default @@ -519,17 +525,14 @@ async def image_generations( r = None try: if request.app.state.config.IMAGE_GENERATION_ENGINE == "openai": - headers = {} - headers["Authorization"] = ( - f"Bearer {request.app.state.config.IMAGES_OPENAI_API_KEY}" - ) - headers["Content-Type"] = "application/json" + + headers = { + "Authorization": f"Bearer {request.app.state.config.IMAGES_OPENAI_API_KEY}", + "Content-Type": "application/json", + } if ENABLE_FORWARD_USER_INFO_HEADERS: - headers["X-OpenWebUI-User-Name"] = quote(user.name, safe=" ") - headers["X-OpenWebUI-User-Id"] = user.id - headers["X-OpenWebUI-User-Email"] = user.email - headers["X-OpenWebUI-User-Role"] = user.role + headers = include_user_info_headers(headers, user) data = { "model": model, @@ -568,31 +571,46 @@ async def image_generations( for image in res["data"]: if image_url := image.get("url", None): - image_data, content_type = load_url_image_data(image_url, headers) + image_data, content_type = get_image_data(image_url, headers) else: - image_data, content_type = load_b64_image_data(image["b64_json"]) + image_data, content_type = get_image_data(image["b64_json"]) url = upload_image(request, image_data, content_type, data, user) images.append({"url": url}) return images elif request.app.state.config.IMAGE_GENERATION_ENGINE == "gemini": - headers = {} - headers["Content-Type"] = "application/json" - headers["x-goog-api-key"] = request.app.state.config.IMAGES_GEMINI_API_KEY - - data = { - "instances": {"prompt": form_data.prompt}, - "parameters": { - "sampleCount": form_data.n, - "outputOptions": {"mimeType": "image/png"}, - }, + headers = { + "Content-Type": "application/json", + "x-goog-api-key": request.app.state.config.IMAGES_GEMINI_API_KEY, } + data = {} + + if ( + request.app.state.config.IMAGES_GEMINI_ENDPOINT_METHOD == "" + or request.app.state.config.IMAGES_GEMINI_ENDPOINT_METHOD == "predict" + ): + model = f"{model}:predict" + data = { + "instances": {"prompt": form_data.prompt}, + "parameters": { + "sampleCount": form_data.n, + "outputOptions": {"mimeType": "image/png"}, + }, + } + + elif ( + request.app.state.config.IMAGES_GEMINI_ENDPOINT_METHOD + == "generateContent" + ): + model = f"{model}:generateContent" + data = {"contents": [{"parts": [{"text": form_data.prompt}]}]} + # Use asyncio.to_thread for the requests.post call r = await asyncio.to_thread( requests.post, - url=f"{request.app.state.config.IMAGES_GEMINI_API_BASE_URL}/models/{model}:predict", + url=f"{request.app.state.config.IMAGES_GEMINI_API_BASE_URL}/models/{model}", json=data, headers=headers, ) @@ -601,12 +619,25 @@ async def image_generations( res = r.json() images = [] - for image in res["predictions"]: - image_data, content_type = load_b64_image_data( - image["bytesBase64Encoded"] - ) - url = upload_image(request, image_data, content_type, data, user) - images.append({"url": url}) + + if model.endswith(":predict"): + for image in res["predictions"]: + image_data, content_type = get_image_data( + image["bytesBase64Encoded"] + ) + url = upload_image(request, image_data, content_type, data, user) + images.append({"url": url}) + elif model.endswith(":generateContent"): + for image in res["candidates"]: + for part in image["content"]["parts"]: + if part.get("inlineData", {}).get("data"): + image_data, content_type = get_image_data( + part["inlineData"]["data"] + ) + url = upload_image( + request, image_data, content_type, data, user + ) + images.append({"url": url}) return images @@ -624,7 +655,7 @@ async def image_generations( if form_data.negative_prompt is not None: data["negative_prompt"] = form_data.negative_prompt - form_data = ComfyUIGenerateImageForm( + form_data = ComfyUICreateImageForm( **{ "workflow": ComfyUIWorkflow( **{ @@ -635,7 +666,7 @@ async def image_generations( **data, } ) - res = await comfyui_generate_image( + res = await comfyui_create_image( model, form_data, user.id, @@ -653,7 +684,7 @@ async def image_generations( "Authorization": f"Bearer {request.app.state.config.COMFYUI_API_KEY}" } - image_data, content_type = load_url_image_data(image["url"], headers) + image_data, content_type = get_image_data(image["url"], headers) url = upload_image( request, image_data, @@ -683,14 +714,8 @@ async def image_generations( if form_data.negative_prompt is not None: data["negative_prompt"] = form_data.negative_prompt - if request.app.state.config.AUTOMATIC1111_CFG_SCALE: - data["cfg_scale"] = request.app.state.config.AUTOMATIC1111_CFG_SCALE - - if request.app.state.config.AUTOMATIC1111_SAMPLER: - data["sampler_name"] = request.app.state.config.AUTOMATIC1111_SAMPLER - - if request.app.state.config.AUTOMATIC1111_SCHEDULER: - data["scheduler"] = request.app.state.config.AUTOMATIC1111_SCHEDULER + if request.app.state.config.AUTOMATIC1111_PARAMS: + data = {**data, **request.app.state.config.AUTOMATIC1111_PARAMS} # Use asyncio.to_thread for the requests.post call r = await asyncio.to_thread( @@ -706,7 +731,7 @@ async def image_generations( images = [] for image in res["images"]: - image_data, content_type = load_b64_image_data(image) + image_data, content_type = get_image_data(image) url = upload_image( request, image_data, @@ -723,3 +748,292 @@ async def image_generations( if "error" in data: error = data["error"]["message"] raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(error)) + + +class EditImageForm(BaseModel): + image: str | list[str] # base64-encoded image(s) or URL(s) + prompt: str + model: Optional[str] = None + size: Optional[str] = None + n: Optional[int] = None + negative_prompt: Optional[str] = None + + +@router.post("/edit") +async def image_edits( + request: Request, + form_data: EditImageForm, + user=Depends(get_verified_user), +): + size = None + width, height = None, None + if ( + request.app.state.config.IMAGE_EDIT_SIZE + and "x" in request.app.state.config.IMAGE_EDIT_SIZE + ) or (form_data.size and "x" in form_data.size): + size = ( + form_data.size + if form_data.size + else request.app.state.config.IMAGE_EDIT_SIZE + ) + width, height = tuple(map(int, size.split("x"))) + + model = ( + request.app.state.config.IMAGE_EDIT_MODEL + if form_data.model is None + else form_data.model + ) + + try: + + async def load_url_image(data): + if data.startswith("http://") or data.startswith("https://"): + r = await asyncio.to_thread(requests.get, data) + r.raise_for_status() + + image_data = base64.b64encode(r.content).decode("utf-8") + return f"data:{r.headers['content-type']};base64,{image_data}" + + elif data.startswith("/api/v1/files"): + file_id = data.split("/api/v1/files/")[1].split("/content")[0] + file_response = await get_file_content_by_id(file_id, user) + + if isinstance(file_response, FileResponse): + file_path = file_response.path + + with open(file_path, "rb") as f: + file_bytes = f.read() + image_data = base64.b64encode(file_bytes).decode("utf-8") + mime_type, _ = mimetypes.guess_type(file_path) + + return f"data:{mime_type};base64,{image_data}" + + return data + + # Load image(s) from URL(s) if necessary + if isinstance(form_data.image, str): + form_data.image = await load_url_image(form_data.image) + elif isinstance(form_data.image, list): + form_data.image = [await load_url_image(img) for img in form_data.image] + except Exception as e: + raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(e)) + + def get_image_file_item(base64_string): + data = base64_string + header, encoded = data.split(",", 1) + mime_type = header.split(";")[0].lstrip("data:") + image_data = base64.b64decode(encoded) + return ( + "image", + ( + f"{uuid.uuid4()}.png", + io.BytesIO(image_data), + mime_type if mime_type else "image/png", + ), + ) + + r = None + try: + if request.app.state.config.IMAGE_EDIT_ENGINE == "openai": + headers = { + "Authorization": f"Bearer {request.app.state.config.IMAGES_EDIT_OPENAI_API_KEY}", + } + + if ENABLE_FORWARD_USER_INFO_HEADERS: + headers = include_user_info_headers(headers, user) + + data = { + "model": model, + "prompt": form_data.prompt, + **({"n": form_data.n} if form_data.n else {}), + **({"size": size} if size else {}), + **( + {} + if "gpt-image-1" in request.app.state.config.IMAGE_EDIT_MODEL + else {"response_format": "b64_json"} + ), + } + + files = [] + if isinstance(form_data.image, str): + files = [get_image_file_item(form_data.image)] + elif isinstance(form_data.image, list): + for img in form_data.image: + files.append(get_image_file_item(img)) + + url_search_params = "" + if request.app.state.config.IMAGES_EDIT_OPENAI_API_VERSION: + url_search_params += f"?api-version={request.app.state.config.IMAGES_EDIT_OPENAI_API_VERSION}" + + # Use asyncio.to_thread for the requests.post call + r = await asyncio.to_thread( + requests.post, + url=f"{request.app.state.config.IMAGES_EDIT_OPENAI_API_BASE_URL}/images/edits{url_search_params}", + headers=headers, + files=files, + data=data, + ) + + r.raise_for_status() + res = r.json() + + images = [] + for image in res["data"]: + if image_url := image.get("url", None): + image_data, content_type = get_image_data(image_url, headers) + else: + image_data, content_type = get_image_data(image["b64_json"]) + + url = upload_image(request, image_data, content_type, data, user) + images.append({"url": url}) + return images + + elif request.app.state.config.IMAGE_EDIT_ENGINE == "gemini": + headers = { + "Content-Type": "application/json", + "x-goog-api-key": request.app.state.config.IMAGES_EDIT_GEMINI_API_KEY, + } + + model = f"{model}:generateContent" + data = {"contents": [{"parts": [{"text": form_data.prompt}]}]} + + if isinstance(form_data.image, str): + data["contents"][0]["parts"].append( + { + "inline_data": { + "mime_type": "image/png", + "data": form_data.image.split(",", 1)[1], + } + } + ) + elif isinstance(form_data.image, list): + data["contents"][0]["parts"].extend( + [ + { + "inline_data": { + "mime_type": "image/png", + "data": image.split(",", 1)[1], + } + } + for image in form_data.image + ] + ) + + # Use asyncio.to_thread for the requests.post call + r = await asyncio.to_thread( + requests.post, + url=f"{request.app.state.config.IMAGES_EDIT_GEMINI_API_BASE_URL}/models/{model}", + json=data, + headers=headers, + ) + + r.raise_for_status() + res = r.json() + + images = [] + for image in res["candidates"]: + for part in image["content"]["parts"]: + if part.get("inlineData", {}).get("data"): + image_data, content_type = get_image_data( + part["inlineData"]["data"] + ) + url = upload_image( + request, image_data, content_type, data, user + ) + images.append({"url": url}) + + return images + + elif request.app.state.config.IMAGE_EDIT_ENGINE == "comfyui": + try: + files = [] + if isinstance(form_data.image, str): + files = [get_image_file_item(form_data.image)] + elif isinstance(form_data.image, list): + for img in form_data.image: + files.append(get_image_file_item(img)) + + # Upload images to ComfyUI and get their names + comfyui_images = [] + for file_item in files: + res = await comfyui_upload_image( + file_item, + request.app.state.config.IMAGES_EDIT_COMFYUI_BASE_URL, + request.app.state.config.IMAGES_EDIT_COMFYUI_API_KEY, + ) + comfyui_images.append(res.get("name", file_item[1][0])) + except Exception as e: + log.debug(f"Error uploading images to ComfyUI: {e}") + raise Exception("Failed to upload images to ComfyUI.") + + data = { + "image": comfyui_images, + "prompt": form_data.prompt, + **({"width": width} if width is not None else {}), + **({"height": height} if height is not None else {}), + **({"n": form_data.n} if form_data.n else {}), + } + + form_data = ComfyUIEditImageForm( + **{ + "workflow": ComfyUIWorkflow( + **{ + "workflow": request.app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW, + "nodes": request.app.state.config.IMAGES_EDIT_COMFYUI_WORKFLOW_NODES, + } + ), + **data, + } + ) + res = await comfyui_edit_image( + model, + form_data, + user.id, + request.app.state.config.IMAGES_EDIT_COMFYUI_BASE_URL, + request.app.state.config.IMAGES_EDIT_COMFYUI_API_KEY, + ) + log.debug(f"res: {res}") + + image_urls = set() + for image in res["data"]: + image_urls.add(image["url"]) + image_urls = list(image_urls) + + # Prioritize output type URLs if available + output_type_urls = [url for url in image_urls if "type=output" in url] + if output_type_urls: + image_urls = output_type_urls + + log.debug(f"Image URLs: {image_urls}") + images = [] + + for image_url in image_urls: + headers = None + if request.app.state.config.IMAGES_EDIT_COMFYUI_API_KEY: + headers = { + "Authorization": f"Bearer {request.app.state.config.IMAGES_EDIT_COMFYUI_API_KEY}" + } + + image_data, content_type = get_image_data(image_url, headers) + url = upload_image( + request, + image_data, + content_type, + form_data.model_dump(exclude_none=True), + user, + ) + images.append({"url": url}) + + return images + except Exception as e: + error = e + if r != None: + data = r.text + try: + data = json.loads(data) + if "error" in data: + error = data["error"]["message"] + except Exception: + error = data + + raise HTTPException(status_code=400, detail=ERROR_MESSAGES.DEFAULT(error)) diff --git a/backend/open_webui/routers/models.py b/backend/open_webui/routers/models.py index 215cd8426c..d69cd4ee42 100644 --- a/backend/open_webui/routers/models.py +++ b/backend/open_webui/routers/models.py @@ -44,7 +44,9 @@ def validate_model_id(model_id: str) -> bool: ########################### -@router.get("/", response_model=list[ModelUserResponse]) +@router.get( + "/list", response_model=list[ModelUserResponse] +) # do NOT use "/" as path, conflicts with main.py async def get_models(id: Optional[str] = None, user=Depends(get_verified_user)): if user.role == "admin" and BYPASS_ADMIN_ACCESS_CONTROL: return Models.get_models() diff --git a/backend/open_webui/routers/openai.py b/backend/open_webui/routers/openai.py index 8c5e3da736..b0f283c82d 100644 --- a/backend/open_webui/routers/openai.py +++ b/backend/open_webui/routers/openai.py @@ -45,6 +45,7 @@ from open_webui.utils.payload import ( ) from open_webui.utils.misc import ( convert_logit_bias_input_to_json, + stream_chunks_handler, ) from open_webui.utils.auth import get_admin_user, get_verified_user @@ -501,50 +502,55 @@ async def get_all_models(request: Request, user: UserModel) -> dict[str, list]: return response return None - def merge_models_lists(model_lists): + def is_supported_openai_models(model_id): + if any( + name in model_id + for name in [ + "babbage", + "dall-e", + "davinci", + "embedding", + "tts", + "whisper", + ] + ): + return False + return True + + def get_merged_models(model_lists): log.debug(f"merge_models_lists {model_lists}") - merged_list = [] + models = {} - for idx, models in enumerate(model_lists): - if models is not None and "error" not in models: + for idx, model_list in enumerate(model_lists): + if model_list is not None and "error" not in model_list: + for model in model_list: + model_id = model.get("id") or model.get("name") - merged_list.extend( - [ - { + if ( + "api.openai.com" + in request.app.state.config.OPENAI_API_BASE_URLS[idx] + and not is_supported_openai_models(model_id) + ): + # Skip unwanted OpenAI models + continue + + if model_id and model_id not in models: + models[model_id] = { **model, - "name": model.get("name", model["id"]), + "name": model.get("name", model_id), "owned_by": "openai", "openai": model, "connection_type": model.get("connection_type", "external"), "urlIdx": idx, } - for model in models - if (model.get("id") or model.get("name")) - and ( - "api.openai.com" - not in request.app.state.config.OPENAI_API_BASE_URLS[idx] - or not any( - name in model["id"] - for name in [ - "babbage", - "dall-e", - "davinci", - "embedding", - "tts", - "whisper", - ] - ) - ) - ] - ) - return merged_list + return models - models = {"data": merge_models_lists(map(extract_data, responses))} + models = get_merged_models(map(extract_data, responses)) log.debug(f"models: {models}") - request.app.state.OPENAI_MODELS = {model["id"]: model for model in models["data"]} - return models + request.app.state.OPENAI_MODELS = models + return {"data": list(models.values())} @router.get("/models") @@ -947,7 +953,7 @@ async def generate_chat_completion( if "text/event-stream" in r.headers.get("Content-Type", ""): streaming = True return StreamingResponse( - r.content, + stream_chunks_handler(r.content), status_code=r.status, headers=dict(r.headers), background=BackgroundTask( diff --git a/backend/open_webui/routers/retrieval.py b/backend/open_webui/routers/retrieval.py index cb66e8926e..d57151b509 100644 --- a/backend/open_webui/routers/retrieval.py +++ b/backend/open_webui/routers/retrieval.py @@ -32,7 +32,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter, TokenTextSpl from langchain_text_splitters import MarkdownHeaderTextSplitter from langchain_core.documents import Document -from open_webui.models.files import FileModel, Files +from open_webui.models.files import FileModel, FileUpdateForm, Files from open_webui.models.knowledge import Knowledges from open_webui.storage.provider import Storage @@ -465,6 +465,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)): "DOCLING_PICTURE_DESCRIPTION_API": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_API, "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT, "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY, + "MISTRAL_OCR_API_BASE_URL": request.app.state.config.MISTRAL_OCR_API_BASE_URL, "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY, # MinerU settings "MINERU_API_MODE": request.app.state.config.MINERU_API_MODE, @@ -650,6 +651,7 @@ class ConfigForm(BaseModel): DOCLING_PICTURE_DESCRIPTION_API: Optional[dict] = None DOCUMENT_INTELLIGENCE_ENDPOINT: Optional[str] = None DOCUMENT_INTELLIGENCE_KEY: Optional[str] = None + MISTRAL_OCR_API_BASE_URL: Optional[str] = None MISTRAL_OCR_API_KEY: Optional[str] = None # MinerU settings @@ -891,6 +893,12 @@ async def update_rag_config( if form_data.DOCUMENT_INTELLIGENCE_KEY is not None else request.app.state.config.DOCUMENT_INTELLIGENCE_KEY ) + + request.app.state.config.MISTRAL_OCR_API_BASE_URL = ( + form_data.MISTRAL_OCR_API_BASE_URL + if form_data.MISTRAL_OCR_API_BASE_URL is not None + else request.app.state.config.MISTRAL_OCR_API_BASE_URL + ) request.app.state.config.MISTRAL_OCR_API_KEY = ( form_data.MISTRAL_OCR_API_KEY if form_data.MISTRAL_OCR_API_KEY is not None @@ -1182,6 +1190,7 @@ async def update_rag_config( "DOCLING_PICTURE_DESCRIPTION_API": request.app.state.config.DOCLING_PICTURE_DESCRIPTION_API, "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT, "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY, + "MISTRAL_OCR_API_BASE_URL": request.app.state.config.MISTRAL_OCR_API_BASE_URL, "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY, # MinerU settings "MINERU_API_MODE": request.app.state.config.MINERU_API_MODE, @@ -1565,6 +1574,7 @@ def process_file( file_path = Storage.get_file(file_path) loader = Loader( engine=request.app.state.config.CONTENT_EXTRACTION_ENGINE, + user=user, DATALAB_MARKER_API_KEY=request.app.state.config.DATALAB_MARKER_API_KEY, DATALAB_MARKER_API_BASE_URL=request.app.state.config.DATALAB_MARKER_API_BASE_URL, DATALAB_MARKER_ADDITIONAL_CONFIG=request.app.state.config.DATALAB_MARKER_ADDITIONAL_CONFIG, @@ -1597,6 +1607,7 @@ def process_file( PDF_EXTRACT_IMAGES=request.app.state.config.PDF_EXTRACT_IMAGES, DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT, DOCUMENT_INTELLIGENCE_KEY=request.app.state.config.DOCUMENT_INTELLIGENCE_KEY, + MISTRAL_OCR_API_BASE_URL=request.app.state.config.MISTRAL_OCR_API_BASE_URL, MISTRAL_OCR_API_KEY=request.app.state.config.MISTRAL_OCR_API_KEY, MINERU_API_MODE=request.app.state.config.MINERU_API_MODE, MINERU_API_URL=request.app.state.config.MINERU_API_URL, @@ -1800,7 +1811,9 @@ def process_web( ) -def search_web(request: Request, engine: str, query: str) -> list[SearchResult]: +def search_web( + request: Request, engine: str, query: str, user=None +) -> list[SearchResult]: """Search the web using a search engine and return the results as a list of SearchResult objects. Will look for a search engine API key in environment variables in the following order: - SEARXNG_QUERY_URL @@ -1875,6 +1888,7 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]: query, request.app.state.config.WEB_SEARCH_RESULT_COUNT, request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST, + referer=request.app.state.config.WEBUI_URL, ) else: raise Exception( @@ -2057,11 +2071,13 @@ def search_web(request: Request, engine: str, query: str) -> list[SearchResult]: ) elif engine == "external": return search_external( + request, request.app.state.config.EXTERNAL_WEB_SEARCH_URL, request.app.state.config.EXTERNAL_WEB_SEARCH_API_KEY, query, request.app.state.config.WEB_SEARCH_RESULT_COUNT, request.app.state.config.WEB_SEARCH_DOMAIN_FILTER_LIST, + user=user, ) else: raise Exception("No search engine API key found in environment variables") @@ -2086,6 +2102,7 @@ async def process_web_search( request, request.app.state.config.WEB_SEARCH_ENGINE, query, + user, ) for query in form_data.queries ] @@ -2435,16 +2452,19 @@ def process_files_batch( """ Process a batch of files and save them to the vector database. """ - results: List[BatchProcessFilesResult] = [] - errors: List[BatchProcessFilesResult] = [] + collection_name = form_data.collection_name + file_results: List[BatchProcessFilesResult] = [] + file_errors: List[BatchProcessFilesResult] = [] + file_updates: List[FileUpdateForm] = [] + # Prepare all documents first all_docs: List[Document] = [] + for file in form_data.files: try: text_content = file.data.get("content", "") - docs: List[Document] = [ Document( page_content=text_content.replace("
", "\n"), @@ -2458,16 +2478,21 @@ def process_files_batch( ) ] - hash = calculate_sha256_string(text_content) - Files.update_file_hash_by_id(file.id, hash) - Files.update_file_data_by_id(file.id, {"content": text_content}) - all_docs.extend(docs) - results.append(BatchProcessFilesResult(file_id=file.id, status="prepared")) + + file_updates.append( + FileUpdateForm( + hash=calculate_sha256_string(text_content), + data={"content": text_content}, + ) + ) + file_results.append( + BatchProcessFilesResult(file_id=file.id, status="prepared") + ) except Exception as e: log.error(f"process_files_batch: Error processing file {file.id}: {str(e)}") - errors.append( + file_errors.append( BatchProcessFilesResult(file_id=file.id, status="failed", error=str(e)) ) @@ -2483,20 +2508,18 @@ def process_files_batch( ) # Update all files with collection name - for result in results: - Files.update_file_metadata_by_id( - result.file_id, {"collection_name": collection_name} - ) - result.status = "completed" + for file_update, file_result in zip(file_updates, file_results): + Files.update_file_by_id(id=file_result.file_id, form_data=file_update) + file_result.status = "completed" except Exception as e: log.error( f"process_files_batch: Error saving documents to vector DB: {str(e)}" ) - for result in results: - result.status = "failed" - errors.append( - BatchProcessFilesResult(file_id=result.file_id, error=str(e)) + for file_result in file_results: + file_result.status = "failed" + file_errors.append( + BatchProcessFilesResult(file_id=file_result.file_id, error=str(e)) ) - return BatchProcessFilesResponse(results=results, errors=errors) + return BatchProcessFilesResponse(results=file_results, errors=file_errors) diff --git a/backend/open_webui/routers/users.py b/backend/open_webui/routers/users.py index 2dd229eeb7..9ee3f9f88c 100644 --- a/backend/open_webui/routers/users.py +++ b/backend/open_webui/routers/users.py @@ -361,7 +361,7 @@ async def get_user_by_id(user_id: str, user=Depends(get_verified_user)): ) -@router.get("/{user_id}/oauth/sessions", response_model=Optional[dict]) +@router.get("/{user_id}/oauth/sessions") async def get_user_oauth_sessions_by_id(user_id: str, user=Depends(get_admin_user)): sessions = OAuthSessions.get_sessions_by_user_id(user_id) if sessions and len(sessions) > 0: diff --git a/backend/open_webui/routers/utils.py b/backend/open_webui/routers/utils.py index 0e6768a671..6445a9fc28 100644 --- a/backend/open_webui/routers/utils.py +++ b/backend/open_webui/routers/utils.py @@ -126,10 +126,3 @@ async def download_db(user=Depends(get_admin_user)): ) -@router.get("/litellm/config") -async def download_litellm_config_yaml(user=Depends(get_admin_user)): - return FileResponse( - f"{DATA_DIR}/litellm/config.yaml", - media_type="application/octet-stream", - filename="config.yaml", - ) diff --git a/backend/open_webui/socket/main.py b/backend/open_webui/socket/main.py index 5aa7a4ff40..5c365f76ac 100644 --- a/backend/open_webui/socket/main.py +++ b/backend/open_webui/socket/main.py @@ -23,6 +23,7 @@ from open_webui.config import ( ) from open_webui.env import ( + VERSION, ENABLE_WEBSOCKET_SUPPORT, WEBSOCKET_MANAGER, WEBSOCKET_REDIS_URL, @@ -52,6 +53,9 @@ log.setLevel(SRC_LOG_LEVELS["SOCKET"]) REDIS = None +# Configure CORS for Socket.IO +SOCKETIO_CORS_ORIGINS = "*" if CORS_ALLOW_ORIGIN == ["*"] else CORS_ALLOW_ORIGIN + if WEBSOCKET_MANAGER == "redis": if WEBSOCKET_SENTINEL_HOSTS: mgr = socketio.AsyncRedisManager( @@ -62,7 +66,7 @@ if WEBSOCKET_MANAGER == "redis": else: mgr = socketio.AsyncRedisManager(WEBSOCKET_REDIS_URL) sio = socketio.AsyncServer( - cors_allowed_origins=CORS_ALLOW_ORIGIN, + cors_allowed_origins=SOCKETIO_CORS_ORIGINS, async_mode="asgi", transports=(["websocket"] if ENABLE_WEBSOCKET_SUPPORT else ["polling"]), allow_upgrades=ENABLE_WEBSOCKET_SUPPORT, @@ -71,7 +75,7 @@ if WEBSOCKET_MANAGER == "redis": ) else: sio = socketio.AsyncServer( - cors_allowed_origins=CORS_ALLOW_ORIGIN, + cors_allowed_origins=SOCKETIO_CORS_ORIGINS, async_mode="asgi", transports=(["websocket"] if ENABLE_WEBSOCKET_SUPPORT else ["polling"]), allow_upgrades=ENABLE_WEBSOCKET_SUPPORT, @@ -278,6 +282,8 @@ async def connect(sid, environ, auth): else: USER_POOL[user.id] = [sid] + await sio.enter_room(sid, f"user:{user.id}") + @sio.on("user-join") async def user_join(sid, data): @@ -300,6 +306,7 @@ async def user_join(sid, data): else: USER_POOL[user.id] = [sid] + await sio.enter_room(sid, f"user:{user.id}") # Join all the channels channels = Channels.get_channels_by_user_id(user.id) log.debug(f"{channels=}") @@ -645,40 +652,24 @@ async def disconnect(sid): def get_event_emitter(request_info, update_db=True): async def __event_emitter__(event_data): user_id = request_info["user_id"] + chat_id = request_info["chat_id"] + message_id = request_info["message_id"] - session_ids = list( - set( - USER_POOL.get(user_id, []) - + ( - [request_info.get("session_id")] - if request_info.get("session_id") - else [] - ) - ) + await sio.emit( + "events", + { + "chat_id": chat_id, + "message_id": message_id, + "data": event_data, + }, + room=f"user:{user_id}", ) - - chat_id = request_info.get("chat_id", None) - message_id = request_info.get("message_id", None) - - emit_tasks = [ - sio.emit( - "events", - { - "chat_id": chat_id, - "message_id": message_id, - "data": event_data, - }, - to=session_id, - ) - for session_id in session_ids - ] - - await asyncio.gather(*emit_tasks) if ( update_db and message_id and not request_info.get("chat_id", "").startswith("local:") ): + if "type" in event_data and event_data["type"] == "status": Chats.add_message_status_to_chat_by_id_and_message_id( request_info["chat_id"], @@ -768,7 +759,14 @@ def get_event_emitter(request_info, update_db=True): }, ) - return __event_emitter__ + if ( + "user_id" in request_info + and "chat_id" in request_info + and "message_id" in request_info + ): + return __event_emitter__ + else: + return None def get_event_call(request_info): @@ -784,7 +782,14 @@ def get_event_call(request_info): ) return response - return __event_caller__ + if ( + "session_id" in request_info + and "chat_id" in request_info + and "message_id" in request_info + ): + return __event_caller__ + else: + return None get_event_caller = get_event_call diff --git a/backend/open_webui/utils/files.py b/backend/open_webui/utils/files.py index b410cbab50..29573cab19 100644 --- a/backend/open_webui/utils/files.py +++ b/backend/open_webui/utils/files.py @@ -1,5 +1,5 @@ from open_webui.routers.images import ( - load_b64_image_data, + get_image_data, upload_image, ) @@ -22,7 +22,7 @@ def get_image_url_from_base64(request, base64_image_string, metadata, user): if "data:image/png;base64" in base64_image_string: image_url = "" # Extract base64 image data from the line - image_data, content_type = load_b64_image_data(base64_image_string) + image_data, content_type = get_image_data(base64_image_string) if image_data is not None: image_url = upload_image( request, diff --git a/backend/open_webui/utils/headers.py b/backend/open_webui/utils/headers.py new file mode 100644 index 0000000000..3caee50334 --- /dev/null +++ b/backend/open_webui/utils/headers.py @@ -0,0 +1,11 @@ +from urllib.parse import quote + + +def include_user_info_headers(headers, user): + return { + **headers, + "X-OpenWebUI-User-Name": quote(user.name, safe=" "), + "X-OpenWebUI-User-Id": user.id, + "X-OpenWebUI-User-Email": user.email, + "X-OpenWebUI-User-Role": user.role, + } diff --git a/backend/open_webui/utils/images/comfyui.py b/backend/open_webui/utils/images/comfyui.py index b86c257591..506723bc92 100644 --- a/backend/open_webui/utils/images/comfyui.py +++ b/backend/open_webui/utils/images/comfyui.py @@ -2,6 +2,8 @@ import asyncio import json import logging import random +import requests +import aiohttp import urllib.parse import urllib.request from typing import Optional @@ -91,6 +93,25 @@ def get_images(ws, prompt, client_id, base_url, api_key): return {"data": output_images} +async def comfyui_upload_image(image_file_item, base_url, api_key): + url = f"{base_url}/api/upload/image" + headers = {} + + if api_key: + headers["Authorization"] = f"Bearer {api_key}" + + _, (filename, file_bytes, mime_type) = image_file_item + + form = aiohttp.FormData() + form.add_field("image", file_bytes, filename=filename, content_type=mime_type) + form.add_field("type", "input") # required by ComfyUI + + async with aiohttp.ClientSession() as session: + async with session.post(url, data=form, headers=headers) as resp: + resp.raise_for_status() + return await resp.json() + + class ComfyUINodeInput(BaseModel): type: Optional[str] = None node_ids: list[str] = [] @@ -103,7 +124,7 @@ class ComfyUIWorkflow(BaseModel): nodes: list[ComfyUINodeInput] -class ComfyUIGenerateImageForm(BaseModel): +class ComfyUICreateImageForm(BaseModel): workflow: ComfyUIWorkflow prompt: str @@ -116,8 +137,8 @@ class ComfyUIGenerateImageForm(BaseModel): seed: Optional[int] = None -async def comfyui_generate_image( - model: str, payload: ComfyUIGenerateImageForm, client_id, base_url, api_key +async def comfyui_create_image( + model: str, payload: ComfyUICreateImageForm, client_id, base_url, api_key ): ws_url = base_url.replace("http://", "ws://").replace("https://", "wss://") workflow = json.loads(payload.workflow.workflow) @@ -191,3 +212,102 @@ async def comfyui_generate_image( ws.close() return images + + +class ComfyUIEditImageForm(BaseModel): + workflow: ComfyUIWorkflow + + image: str | list[str] + prompt: str + width: Optional[int] = None + height: Optional[int] = None + n: Optional[int] = None + + steps: Optional[int] = None + seed: Optional[int] = None + + +async def comfyui_edit_image( + model: str, payload: ComfyUIEditImageForm, client_id, base_url, api_key +): + ws_url = base_url.replace("http://", "ws://").replace("https://", "wss://") + workflow = json.loads(payload.workflow.workflow) + + for node in payload.workflow.nodes: + if node.type: + if node.type == "model": + for node_id in node.node_ids: + workflow[node_id]["inputs"][node.key] = model + elif node.type == "image": + if isinstance(payload.image, list): + # check if multiple images are provided + for idx, node_id in enumerate(node.node_ids): + if idx < len(payload.image): + workflow[node_id]["inputs"][node.key] = payload.image[idx] + else: + for node_id in node.node_ids: + workflow[node_id]["inputs"][node.key] = payload.image + elif node.type == "prompt": + for node_id in node.node_ids: + workflow[node_id]["inputs"][ + node.key if node.key else "text" + ] = payload.prompt + elif node.type == "negative_prompt": + for node_id in node.node_ids: + workflow[node_id]["inputs"][ + node.key if node.key else "text" + ] = payload.negative_prompt + elif node.type == "width": + for node_id in node.node_ids: + workflow[node_id]["inputs"][ + node.key if node.key else "width" + ] = payload.width + elif node.type == "height": + for node_id in node.node_ids: + workflow[node_id]["inputs"][ + node.key if node.key else "height" + ] = payload.height + elif node.type == "n": + for node_id in node.node_ids: + workflow[node_id]["inputs"][ + node.key if node.key else "batch_size" + ] = payload.n + elif node.type == "steps": + for node_id in node.node_ids: + workflow[node_id]["inputs"][ + node.key if node.key else "steps" + ] = payload.steps + elif node.type == "seed": + seed = ( + payload.seed + if payload.seed + else random.randint(0, 1125899906842624) + ) + for node_id in node.node_ids: + workflow[node_id]["inputs"][node.key] = seed + else: + for node_id in node.node_ids: + workflow[node_id]["inputs"][node.key] = node.value + + try: + ws = websocket.WebSocket() + headers = {"Authorization": f"Bearer {api_key}"} + ws.connect(f"{ws_url}/ws?clientId={client_id}", header=headers) + log.info("WebSocket connection established.") + except Exception as e: + log.exception(f"Failed to connect to WebSocket server: {e}") + return None + + try: + log.info("Sending workflow to WebSocket server.") + log.info(f"Workflow: {workflow}") + images = await asyncio.to_thread( + get_images, ws, workflow, client_id, base_url, api_key + ) + except Exception as e: + log.exception(f"Error while receiving images: {e}") + images = None + + ws.close() + + return images diff --git a/backend/open_webui/utils/middleware.py b/backend/open_webui/utils/middleware.py index e1b0bed853..8c336bfba4 100644 --- a/backend/open_webui/utils/middleware.py +++ b/backend/open_webui/utils/middleware.py @@ -45,10 +45,10 @@ from open_webui.routers.retrieval import ( SearchForm, ) from open_webui.routers.images import ( - load_b64_image_data, image_generations, - GenerateImageForm, - upload_image, + CreateImageForm, + image_edits, + EditImageForm, ) from open_webui.routers.pipelines import ( process_pipeline_inlet_filter, @@ -91,7 +91,7 @@ from open_webui.utils.misc import ( convert_logit_bias_input_to_json, get_content_from_message, ) -from open_webui.utils.tools import get_tools +from open_webui.utils.tools import get_tools, get_updated_tool_function from open_webui.utils.plugin import load_function_module_by_id from open_webui.utils.filter import ( get_sorted_filter_ids, @@ -302,19 +302,23 @@ async def chat_completion_tools_handler( def get_tools_function_calling_payload(messages, task_model_id, content): user_message = get_last_user_message(messages) + if user_message and messages and messages[-1]["role"] == "user": + # Remove the last user message to avoid duplication + messages = messages[:-1] + recent_messages = messages[-4:] if len(messages) > 4 else messages chat_history = "\n".join( f"{message['role'].upper()}: \"\"\"{get_content_from_message(message)}\"\"\"" for message in recent_messages ) - prompt = f"History:\n{chat_history}\nQuery: {user_message}" + prompt = f"History:\n{chat_history}\nQuery: {user_message}" if chat_history else f"Query: {user_message}" return { "model": task_model_id, "messages": [ {"role": "system", "content": content}, - {"role": "user", "content": f"Query: {prompt}"}, + {"role": "user", "content": prompt}, ], "stream": False, "metadata": {"task": str(TASKS.FUNCTION_CALLING)}, @@ -718,9 +722,31 @@ async def chat_web_search_handler( return form_data +def get_last_images(message_list): + images = [] + for message in reversed(message_list): + images_flag = False + for file in message.get("files", []): + if file.get("type") == "image": + images.append(file.get("url")) + images_flag = True + + if images_flag: + break + + return images + + async def chat_image_generation_handler( request: Request, form_data: dict, extra_params: dict, user ): + metadata = extra_params.get("__metadata__", {}) + chat_id = metadata.get("chat_id", None) + if not chat_id: + return form_data + + chat = Chats.get_chat_by_id_and_user_id(chat_id, user.id) + __event_emitter__ = extra_params["__event_emitter__"] await __event_emitter__( { @@ -729,87 +755,151 @@ async def chat_image_generation_handler( } ) - messages = form_data["messages"] - user_message = get_last_user_message(messages) + messages_map = chat.chat.get("history", {}).get("messages", {}) + message_id = chat.chat.get("history", {}).get("currentId") + message_list = get_message_list(messages_map, message_id) + user_message = get_last_user_message(message_list) prompt = user_message - negative_prompt = "" - - if request.app.state.config.ENABLE_IMAGE_PROMPT_GENERATION: - try: - res = await generate_image_prompt( - request, - { - "model": form_data["model"], - "messages": messages, - }, - user, - ) - - response = res["choices"][0]["message"]["content"] - - try: - bracket_start = response.find("{") - bracket_end = response.rfind("}") + 1 - - if bracket_start == -1 or bracket_end == -1: - raise Exception("No JSON object found in the response") - - response = response[bracket_start:bracket_end] - response = json.loads(response) - prompt = response.get("prompt", []) - except Exception as e: - prompt = user_message - - except Exception as e: - log.exception(e) - prompt = user_message + input_images = get_last_images(message_list) system_message_content = "" + if len(input_images) == 0: + # Create image(s) + if request.app.state.config.ENABLE_IMAGE_PROMPT_GENERATION: + try: + res = await generate_image_prompt( + request, + { + "model": form_data["model"], + "messages": form_data["messages"], + }, + user, + ) - try: - images = await image_generations( - request=request, - form_data=GenerateImageForm(**{"prompt": prompt}), - user=user, - ) + response = res["choices"][0]["message"]["content"] - await __event_emitter__( - { - "type": "status", - "data": {"description": "Image created", "done": True}, - } - ) + try: + bracket_start = response.find("{") + bracket_end = response.rfind("}") + 1 - await __event_emitter__( - { - "type": "files", - "data": { - "files": [ - { - "type": "image", - "url": image["url"], - } - for image in images - ] - }, - } - ) + if bracket_start == -1 or bracket_end == -1: + raise Exception("No JSON object found in the response") - system_message_content = "User is shown the generated image, tell the user that the image has been generated" - except Exception as e: - log.exception(e) - await __event_emitter__( - { - "type": "status", - "data": { - "description": f"An error occurred while generating an image", - "done": True, - }, - } - ) + response = response[bracket_start:bracket_end] + response = json.loads(response) + prompt = response.get("prompt", []) + except Exception as e: + prompt = user_message - system_message_content = "Unable to generate an image, tell the user that an error occurred" + except Exception as e: + log.exception(e) + prompt = user_message + + try: + images = await image_generations( + request=request, + form_data=CreateImageForm(**{"prompt": prompt}), + user=user, + ) + + await __event_emitter__( + { + "type": "status", + "data": {"description": "Image created", "done": True}, + } + ) + + await __event_emitter__( + { + "type": "files", + "data": { + "files": [ + { + "type": "image", + "url": image["url"], + } + for image in images + ] + }, + } + ) + + system_message_content = "The requested image has been created and is now being shown to the user. Let them know that it has been generated." + except Exception as e: + log.debug(e) + + error_message = "" + if isinstance(e, HTTPException): + if e.detail and isinstance(e.detail, dict): + error_message = e.detail.get("message", str(e.detail)) + else: + error_message = str(e.detail) + + await __event_emitter__( + { + "type": "status", + "data": { + "description": f"An error occurred while generating an image", + "done": True, + }, + } + ) + + system_message_content = f"Image generation was attempted but failed. The system is currently unable to generate the image. Tell the user that an error occurred: {error_message}" + else: + # Edit image(s) + try: + images = await image_edits( + request=request, + form_data=EditImageForm(**{"prompt": prompt, "image": input_images}), + user=user, + ) + + await __event_emitter__( + { + "type": "status", + "data": {"description": "Image created", "done": True}, + } + ) + + await __event_emitter__( + { + "type": "files", + "data": { + "files": [ + { + "type": "image", + "url": image["url"], + } + for image in images + ] + }, + } + ) + + system_message_content = "The requested image has been created and is now being shown to the user. Let them know that it has been generated." + except Exception as e: + log.debug(e) + + error_message = "" + if isinstance(e, HTTPException): + if e.detail and isinstance(e.detail, dict): + error_message = e.detail.get("message", str(e.detail)) + else: + error_message = str(e.detail) + + await __event_emitter__( + { + "type": "status", + "data": { + "description": f"An error occurred while generating an image", + "done": True, + }, + } + ) + + system_message_content = f"Image generation was attempted but failed. The system is currently unable to generate the image. Tell the user that an error occurred: {error_message}" if system_message_content: form_data["messages"] = add_or_update_system_message( @@ -1307,6 +1397,17 @@ async def process_chat_payload(request, form_data, user, metadata, model): } except Exception as e: log.debug(e) + if event_emitter: + await event_emitter( + { + "type": "chat:message:error", + "data": { + "error": { + "content": f"Failed to connect to MCP server '{server_id}'" + } + }, + } + ) continue tools_dict = await get_tools( @@ -1543,16 +1644,13 @@ async def process_chat_response( if not metadata.get("chat_id", "").startswith( "local:" ): # Only update titles and tags for non-temp chats - if ( - TASKS.TITLE_GENERATION in tasks - and tasks[TASKS.TITLE_GENERATION] - ): + if TASKS.TITLE_GENERATION in tasks: user_message = get_last_user_message(messages) if user_message and len(user_message) > 100: user_message = user_message[:100] + "..." + title = None if tasks[TASKS.TITLE_GENERATION]: - res = await generate_title( request, { @@ -1603,7 +1701,8 @@ async def process_chat_response( "data": title, } ) - elif len(messages) == 2: + + if title == None and len(messages) == 2: title = messages[0].get("content", user_message) Chats.update_chat_title_by_id(metadata["chat_id"], title) @@ -1949,9 +2048,11 @@ async def process_chat_response( content = f"{content}{tool_calls_display_content}" elif block["type"] == "reasoning": - reasoning_display_content = "\n".join( - (f"> {line}" if not line.startswith(">") else line) - for line in block["content"].splitlines() + reasoning_display_content = html.escape( + "\n".join( + (f"> {line}" if not line.startswith(">") else line) + for line in block["content"].splitlines() + ) ) reasoning_duration = block.get("duration", None) @@ -2852,7 +2953,16 @@ async def process_chat_response( ) else: - tool_function = tool["callable"] + tool_function = get_updated_tool_function( + function=tool["callable"], + extra_params={ + "__messages__": form_data.get( + "messages", [] + ), + "__files__": metadata.get("files", []), + }, + ) + tool_result = await tool_function( **tool_function_params ) diff --git a/backend/open_webui/utils/misc.py b/backend/open_webui/utils/misc.py index 9984e378fb..ce16691365 100644 --- a/backend/open_webui/utils/misc.py +++ b/backend/open_webui/utils/misc.py @@ -8,10 +8,11 @@ from datetime import timedelta from pathlib import Path from typing import Callable, Optional import json +import aiohttp import collections.abc -from open_webui.env import SRC_LOG_LEVELS +from open_webui.env import SRC_LOG_LEVELS, CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE log = logging.getLogger(__name__) log.setLevel(SRC_LOG_LEVELS["MAIN"]) @@ -539,3 +540,68 @@ def extract_urls(text: str) -> list[str]: r"(https?://[^\s]+)", re.IGNORECASE ) # Matches http and https URLs return url_pattern.findall(text) + + +def stream_chunks_handler(stream: aiohttp.StreamReader): + """ + Handle stream response chunks, supporting large data chunks that exceed the original 16kb limit. + When a single line exceeds max_buffer_size, returns an empty JSON string {} and skips subsequent data + until encountering normally sized data. + + :param stream: The stream reader to handle. + :return: An async generator that yields the stream data. + """ + + max_buffer_size = CHAT_STREAM_RESPONSE_CHUNK_MAX_BUFFER_SIZE + if max_buffer_size is None or max_buffer_size <= 0: + return stream + + async def yield_safe_stream_chunks(): + buffer = b"" + skip_mode = False + + async for data, _ in stream.iter_chunks(): + if not data: + continue + + # In skip_mode, if buffer already exceeds the limit, clear it (it's part of an oversized line) + if skip_mode and len(buffer) > max_buffer_size: + buffer = b"" + + lines = (buffer + data).split(b"\n") + + # Process complete lines (except the last possibly incomplete fragment) + for i in range(len(lines) - 1): + line = lines[i] + + if skip_mode: + # Skip mode: check if current line is small enough to exit skip mode + if len(line) <= max_buffer_size: + skip_mode = False + yield line + else: + yield b"data: {}" + else: + # Normal mode: check if line exceeds limit + if len(line) > max_buffer_size: + skip_mode = True + yield b"data: {}" + log.info(f"Skip mode triggered, line size: {len(line)}") + else: + yield line + + # Save the last incomplete fragment + buffer = lines[-1] + + # Check if buffer exceeds limit + if not skip_mode and len(buffer) > max_buffer_size: + skip_mode = True + log.info(f"Skip mode triggered, buffer size: {len(buffer)}") + # Clear oversized buffer to prevent unlimited growth + buffer = b"" + + # Process remaining buffer data + if buffer and not skip_mode: + yield buffer + + return yield_safe_stream_chunks() diff --git a/backend/open_webui/utils/models.py b/backend/open_webui/utils/models.py index 6661fadb9e..8b53ce5193 100644 --- a/backend/open_webui/utils/models.py +++ b/backend/open_webui/utils/models.py @@ -12,6 +12,7 @@ from open_webui.functions import get_function_models from open_webui.models.functions import Functions from open_webui.models.models import Models +from open_webui.models.groups import Groups from open_webui.utils.plugin import ( @@ -356,6 +357,7 @@ def get_filtered_models(models, user): or (user.role == "admin" and not BYPASS_ADMIN_ACCESS_CONTROL) ) and not BYPASS_MODEL_ACCESS_CONTROL: filtered_models = [] + user_group_ids = {group.id for group in Groups.get_groups_by_member_id(user.id)} for model in models: if model.get("arena"): if has_access( @@ -364,6 +366,7 @@ def get_filtered_models(models, user): access_control=model.get("info", {}) .get("meta", {}) .get("access_control", {}), + user_group_ids=user_group_ids, ): filtered_models.append(model) continue @@ -377,6 +380,7 @@ def get_filtered_models(models, user): user.id, type="read", access_control=model_info.access_control, + user_group_ids=user_group_ids, ) ): filtered_models.append(model) diff --git a/backend/open_webui/utils/oauth.py b/backend/open_webui/utils/oauth.py index e0bf7582c6..392f4cd4bf 100644 --- a/backend/open_webui/utils/oauth.py +++ b/backend/open_webui/utils/oauth.py @@ -1,4 +1,5 @@ import base64 +import copy import hashlib import logging import mimetypes @@ -41,6 +42,7 @@ from open_webui.config import ( ENABLE_OAUTH_GROUP_MANAGEMENT, ENABLE_OAUTH_GROUP_CREATION, OAUTH_BLOCKED_GROUPS, + OAUTH_GROUPS_SEPARATOR, OAUTH_ROLES_CLAIM, OAUTH_SUB_CLAIM, OAUTH_GROUPS_CLAIM, @@ -74,6 +76,8 @@ from mcp.shared.auth import ( OAuthMetadata, ) +from authlib.oauth2.rfc6749.errors import OAuth2Error + class OAuthClientInformationFull(OAuthClientMetadata): issuer: Optional[str] = None # URL of the OAuth server that issued this client @@ -150,6 +154,37 @@ def decrypt_data(data: str): raise +def _build_oauth_callback_error_message(e: Exception) -> str: + """ + Produce a user-facing callback error string with actionable context. + Keeps the message short and strips newlines for safe redirect usage. + """ + if isinstance(e, OAuth2Error): + parts = [p for p in [e.error, e.description] if p] + detail = " - ".join(parts) + elif isinstance(e, HTTPException): + detail = e.detail if isinstance(e.detail, str) else str(e.detail) + elif isinstance(e, aiohttp.ClientResponseError): + detail = f"Upstream provider returned {e.status}: {e.message}" + elif isinstance(e, aiohttp.ClientError): + detail = str(e) + elif isinstance(e, KeyError): + missing = str(e).strip("'") + if missing.lower() == "state": + detail = "Missing state parameter in callback (session may have expired)" + else: + detail = f"Missing expected key '{missing}' in OAuth response" + else: + detail = str(e) + + detail = detail.replace("\n", " ").strip() + if not detail: + detail = e.__class__.__name__ + + message = f"OAuth callback failed: {detail}" + return message[:197] + "..." if len(message) > 200 else message + + def is_in_blocked_groups(group_name: str, groups: list) -> bool: """ Check if a group name matches any blocked pattern. @@ -251,7 +286,7 @@ async def get_oauth_client_info_with_dynamic_client_registration( # Attempt to fetch OAuth server metadata to get registration endpoint & scopes discovery_urls = get_discovery_urls(oauth_server_url) for url in discovery_urls: - async with aiohttp.ClientSession() as session: + async with aiohttp.ClientSession(trust_env=True) as session: async with session.get( url, ssl=AIOHTTP_CLIENT_SESSION_SSL ) as oauth_server_metadata_response: @@ -287,7 +322,7 @@ async def get_oauth_client_info_with_dynamic_client_registration( ) # Perform dynamic client registration and return client info - async with aiohttp.ClientSession() as session: + async with aiohttp.ClientSession(trust_env=True) as session: async with session.post( registration_url, json=registration_data, ssl=AIOHTTP_CLIENT_SESSION_SSL ) as oauth_client_registration_response: @@ -371,6 +406,82 @@ class OAuthClientManager: if client_id in self.clients: del self.clients[client_id] log.info(f"Removed OAuth client {client_id}") + + if hasattr(self.oauth, "_clients"): + if client_id in self.oauth._clients: + self.oauth._clients.pop(client_id, None) + + if hasattr(self.oauth, "_registry"): + if client_id in self.oauth._registry: + self.oauth._registry.pop(client_id, None) + + return True + + async def _preflight_authorization_url( + self, client, client_info: OAuthClientInformationFull + ) -> bool: + # TODO: Replace this logic with a more robust OAuth client registration validation + # Only perform preflight checks for Starlette OAuth clients + if not hasattr(client, "create_authorization_url"): + return True + + redirect_uri = None + if client_info.redirect_uris: + redirect_uri = str(client_info.redirect_uris[0]) + + try: + auth_data = await client.create_authorization_url(redirect_uri=redirect_uri) + authorization_url = auth_data.get("url") + + if not authorization_url: + return True + except Exception as e: + log.debug( + f"Skipping OAuth preflight for client {client_info.client_id}: {e}", + ) + return True + + try: + async with aiohttp.ClientSession(trust_env=True) as session: + async with session.get( + authorization_url, + allow_redirects=False, + ssl=AIOHTTP_CLIENT_SESSION_SSL, + ) as resp: + if resp.status < 400: + return True + response_text = await resp.text() + + error = None + error_description = "" + + content_type = resp.headers.get("content-type", "") + if "application/json" in content_type: + try: + payload = json.loads(response_text) + error = payload.get("error") + error_description = payload.get("error_description", "") + except: + pass + else: + error_description = response_text + + error_message = f"{error or ''} {error_description or ''}".lower() + + if any( + keyword in error_message + for keyword in ("invalid_client", "invalid client", "client id") + ): + log.warning( + f"OAuth client preflight detected invalid registration for {client_info.client_id}: {error} {error_description}" + ) + + return False + except Exception as e: + log.debug( + f"Skipping OAuth preflight network check for client {client_info.client_id}: {e}" + ) + return True def get_client(self, client_id): @@ -561,7 +672,6 @@ class OAuthClientManager: client = self.get_client(client_id) if client is None: raise HTTPException(404) - client_info = self.get_client_info(client_id) if client_info is None: raise HTTPException(404) @@ -569,7 +679,8 @@ class OAuthClientManager: redirect_uri = ( client_info.redirect_uris[0] if client_info.redirect_uris else None ) - return await client.authorize_redirect(request, str(redirect_uri)) + redirect_uri_str = str(redirect_uri) if redirect_uri else None + return await client.authorize_redirect(request, redirect_uri_str) async def handle_callback(self, request, client_id: str, user_id: str, response): client = self.get_client(client_id) @@ -621,8 +732,14 @@ class OAuthClientManager: error_message = "Failed to obtain OAuth token" log.warning(error_message) except Exception as e: - error_message = "OAuth callback error" - log.warning(f"OAuth callback error: {e}") + error_message = _build_oauth_callback_error_message(e) + log.warning( + "OAuth callback error for user_id=%s client_id=%s: %s", + user_id, + client_id, + error_message, + exc_info=True, + ) redirect_url = ( str(request.app.state.config.WEBUI_URL or request.base_url) @@ -630,7 +747,9 @@ class OAuthClientManager: if error_message: log.debug(error_message) - redirect_url = f"{redirect_url}/?error={error_message}" + redirect_url = ( + f"{redirect_url}/?error={urllib.parse.quote_plus(error_message)}" + ) return RedirectResponse(url=redirect_url, headers=response.headers) response = RedirectResponse(url=redirect_url, headers=response.headers) @@ -917,7 +1036,11 @@ class OAuthManager: if isinstance(claim_data, list): user_oauth_groups = claim_data elif isinstance(claim_data, str): - user_oauth_groups = [claim_data] + # Split by the configured separator if present + if OAUTH_GROUPS_SEPARATOR in claim_data: + user_oauth_groups = claim_data.split(OAUTH_GROUPS_SEPARATOR) + else: + user_oauth_groups = [claim_data] else: user_oauth_groups = [] @@ -1104,7 +1227,13 @@ class OAuthManager: try: token = await client.authorize_access_token(request) except Exception as e: - log.warning(f"OAuth callback error: {e}") + detailed_error = _build_oauth_callback_error_message(e) + log.warning( + "OAuth callback error during authorize_access_token for provider %s: %s", + provider, + detailed_error, + exc_info=True, + ) raise HTTPException(400, detail=ERROR_MESSAGES.INVALID_CRED) # Try to get userinfo from the token first, some providers include it there diff --git a/backend/open_webui/utils/task.py b/backend/open_webui/utils/task.py index 84c9308dc1..7f90e96330 100644 --- a/backend/open_webui/utils/task.py +++ b/backend/open_webui/utils/task.py @@ -208,20 +208,21 @@ def rag_template(template: str, context: str, query: str): if "[query]" in context: query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}" template = template.replace("[query]", query_placeholder) - query_placeholders.append(query_placeholder) + query_placeholders.append((query_placeholder, "[query]")) if "{{QUERY}}" in context: query_placeholder = "{{QUERY" + str(uuid.uuid4()) + "}}" template = template.replace("{{QUERY}}", query_placeholder) - query_placeholders.append(query_placeholder) + query_placeholders.append((query_placeholder, "{{QUERY}}")) template = template.replace("[context]", context) template = template.replace("{{CONTEXT}}", context) + template = template.replace("[query]", query) template = template.replace("{{QUERY}}", query) - for query_placeholder in query_placeholders: - template = template.replace(query_placeholder, query) + for query_placeholder, original_placeholder in query_placeholders: + template = template.replace(query_placeholder, original_placeholder) return template diff --git a/backend/open_webui/utils/tools.py b/backend/open_webui/utils/tools.py index 16f50dfb20..1d1254f184 100644 --- a/backend/open_webui/utils/tools.py +++ b/backend/open_webui/utils/tools.py @@ -85,9 +85,26 @@ def get_async_tool_function_and_apply_extra_params( update_wrapper(new_function, function) new_function.__signature__ = new_sig + new_function.__function__ = function # type: ignore + new_function.__extra_params__ = extra_params # type: ignore + return new_function +def get_updated_tool_function(function: Callable, extra_params: dict): + # Get the original function and merge updated params + __function__ = getattr(function, "__function__", None) + __extra_params__ = getattr(function, "__extra_params__", None) + + if __function__ is not None and __extra_params__ is not None: + return get_async_tool_function_and_apply_extra_params( + __function__, + {**__extra_params__, **extra_params}, + ) + + return function + + async def get_tools( request: Request, tool_ids: list[str], user: UserModel, extra_params: dict ) -> dict[str, dict]: diff --git a/backend/open_webui/utils/webhook.py b/backend/open_webui/utils/webhook.py index 7ea29f3988..4424c651ac 100644 --- a/backend/open_webui/utils/webhook.py +++ b/backend/open_webui/utils/webhook.py @@ -51,7 +51,7 @@ async def post_webhook(name: str, url: str, message: str, event_data: dict) -> b payload = {**event_data} log.debug(f"payload: {payload}") - async with aiohttp.ClientSession() as session: + async with aiohttp.ClientSession(trust_env=True) as session: async with session.post(url, json=payload) as r: r_text = await r.text() r.raise_for_status() diff --git a/docs/SECURITY.md b/docs/SECURITY.md index a9463269df..90951e5265 100644 --- a/docs/SECURITY.md +++ b/docs/SECURITY.md @@ -57,22 +57,28 @@ We appreciate the community's interest in identifying potential vulnerabilities. > [!NOTE] > **Note**: If you believe you have found a security issue that > -> 1. affects default configurations **or** -> 2. represents a genuine bypass of intended security controls **or** -> 3. works only with non-default configurations **but the configuration in question is likely to be used by production deployments** > **then we absolutely want to hear about it.** This policy is intended to filter configuration issues and deployment problems, not to discourage legitimate security research. +> 1. affects default configurations, **or** +> 2. represents a genuine bypass of intended security controls, **or** +> 3. works only with non-default configurations, **but the configuration in question is likely to be used by production deployments**, **then we absolutely want to hear about it.** This policy is intended to filter configuration issues and deployment problems, not to discourage legitimate security research. 8. **Threat Model Understanding Required**: Reports must demonstrate understanding of Open WebUI's self-hosted, authenticated, role-based access control architecture. Comparing Open WebUI to services with fundamentally different security models without acknowledging the architectural differences may result in report rejection. 9. **CVSS Scoring Accuracy:** If you include a CVSS score with your report, it must accurately reflect the vulnerability according to CVSS methodology. Common errors include 1) rating PR:N (None) when authentication is required, 2) scoring hypothetical attack chains instead of the actual vulnerability, or 3) inflating severity without evidence. **We will adjust inaccurate CVSS scores.** Intentionally inflated scores may result in report rejection. -> [!WARNING] > **Using CVE Precedents:** If you cite other CVEs to support your report, ensure they are **genuinely comparable** in vulnerability type, threat model, and attack vector. Citing CVEs from different product categories, different vulnerability classes or different deployment models will lead us to suspect the use of AI in your report. +> [!WARNING] +> +> **Using CVE Precedents:** If you cite other CVEs to support your report, ensure they are **genuinely comparable** in vulnerability type, threat model, and attack vector. Citing CVEs from different product categories, different vulnerability classes or different deployment models will lead us to suspect the use of AI in your report. -11. **Admin Actions Are Out of Scope:** Vulnerabilities that require an administrator to actively perform unsafe actions are **not considered valid vulnerabilities**. Admins have full system control and are expected to understand the security implications of their actions and configurations. This includes but is not limited to: adding malicious external servers (models, tools, webhooks), pasting untrusted code into Functions/Tools, or intentionally weakening security settings. **Reports requiring admin negligence or social engineering of admins may be rejected.** - -12. **AI report transparency:** Due to an extreme spike in AI-aided vulnerability reports **YOU MUST DISCLOSE if AI was used in any capacity** - whether for writing the report, generating the PoC, or identifying the vulnerability. If AI helped you in any way shape or form in the creation of the report, PoC or finding the vulnerability, you MUST disclose it. +10. **Admin Actions Are Out of Scope:** Vulnerabilities that require an administrator to actively perform unsafe actions are **not considered valid vulnerabilities**. Admins have full system control and are expected to understand the security implications of their actions and configurations. This includes but is not limited to: adding malicious external servers (models, tools, webhooks), pasting untrusted code into Functions/Tools, or intentionally weakening security settings. **Reports requiring admin negligence or social engineering of admins may be rejected.** > [!NOTE] -> AI-aided vulnerability reports **will not be rejected by us by default.** But: +> Similar to rule "Default Configuration Testing": If you believe you have found a vulnerability that affects admins and is NOT caused by admin negligence or intentionally malicious actions, +> **then we absolutely want to hear about it.** This policy is intended to filter social engineering attacks on admins, malicious plugins being deployed by admins and similar malicious actions, not to discourage legitimate security research. + +11. **AI report transparency:** Due to an extreme spike in AI-aided vulnerability reports **YOU MUST DISCLOSE if AI was used in any capacity** - whether for writing the report, generating the PoC, or identifying the vulnerability. If AI helped you in any way shape or form in the creation of the report, PoC or finding the vulnerability, you MUST disclose it. + +> [!NOTE] +> AI-aided vulnerability reports **will not be rejected by us by default**. But: > > - If we suspect you used AI (but you did not disclose it to us), we will be asking tough follow-up questions to validate your understanding of the reported vulnerability and Open WebUI itself. > - If we suspect you used AI (but you did not disclose it to us) **and** your report ends up being invalid/not a vulnerability/not reproducible, then you **may be banned** from reporting future vulnerabilities. @@ -94,7 +100,7 @@ We appreciate the community's interest in identifying potential vulnerabilities. If you want to report a vulnerability and can meet the outlined requirements, [open a vulnerability report here](https://github.com/open-webui/open-webui/security/advisories/new). If you feel like you are not able to follow ALL outlined requirements for vulnerability-specific reasons, still do report it, we will check every report either way. -## Product Security And For Non-Vulnerability Security Concerns: +## Product Security And For Non-Vulnerability Related Security Concerns: If your concern does not meet the vulnerability requirements outlined above, is not a vulnerability, **but is still related to security concerns**, then use the following channels instead: @@ -121,4 +127,4 @@ For any other immediate concerns, please create an issue in our [issue tracker]( --- -_Last updated on **2025-10-17**._ +_Last updated on **2025-11-06**._ diff --git a/package-lock.json b/package-lock.json index a584046549..c86757e9a5 100644 --- a/package-lock.json +++ b/package-lock.json @@ -1,12 +1,12 @@ { "name": "open-webui", - "version": "0.6.34", + "version": "0.6.36", "lockfileVersion": 3, "requires": true, "packages": { "": { "name": "open-webui", - "version": "0.6.34", + "version": "0.6.36", "dependencies": { "@azure/msal-browser": "^4.5.0", "@codemirror/lang-javascript": "^6.2.2", diff --git a/package.json b/package.json index fc09323156..9065bda0ce 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "open-webui", - "version": "0.6.34", + "version": "0.6.36", "private": true, "scripts": { "dev": "npm run pyodide:fetch && vite dev --host", diff --git a/src/app.css b/src/app.css index 6a85c69d7e..f4e3225d3b 100644 --- a/src/app.css +++ b/src/app.css @@ -129,8 +129,8 @@ li p { } ::-webkit-scrollbar { - height: 0.4rem; - width: 0.4rem; + height: 0.45rem; + width: 0.45rem; } ::-webkit-scrollbar-track { diff --git a/src/lib/apis/files/index.ts b/src/lib/apis/files/index.ts index 6a1763edb8..8351393e3c 100644 --- a/src/lib/apis/files/index.ts +++ b/src/lib/apis/files/index.ts @@ -63,6 +63,10 @@ export const uploadFile = async (token: string, file: File, metadata?: object | console.error(data.error); res.error = data.error; } + + if (res?.data) { + res.data = data; + } } } } diff --git a/src/lib/apis/index.ts b/src/lib/apis/index.ts index 75a289d631..126c59ad2f 100644 --- a/src/lib/apis/index.ts +++ b/src/lib/apis/index.ts @@ -1401,6 +1401,33 @@ export const getChangelog = async () => { return res; }; +export const getVersion = async (token: string) => { + let error = null; + + const res = await fetch(`${WEBUI_BASE_URL}/api/version`, { + method: 'GET', + headers: { + 'Content-Type': 'application/json', + Authorization: `Bearer ${token}` + } + }) + .then(async (res) => { + if (!res.ok) throw await res.json(); + return res.json(); + }) + .catch((err) => { + console.error(err); + error = err; + return null; + }); + + if (error) { + throw error; + } + + return res?.version ?? null; +}; + export const getVersionUpdates = async (token: string) => { let error = null; diff --git a/src/lib/apis/models/index.ts b/src/lib/apis/models/index.ts index d324fa9173..32a7151b5d 100644 --- a/src/lib/apis/models/index.ts +++ b/src/lib/apis/models/index.ts @@ -1,9 +1,9 @@ import { WEBUI_API_BASE_URL } from '$lib/constants'; -export const getModels = async (token: string = '') => { +export const getModelItems = async (token: string = '') => { let error = null; - const res = await fetch(`${WEBUI_API_BASE_URL}/models/`, { + const res = await fetch(`${WEBUI_API_BASE_URL}/models/list`, { method: 'GET', headers: { Accept: 'application/json', diff --git a/src/lib/apis/utils/index.ts b/src/lib/apis/utils/index.ts index 1fc30ddbba..79f56514a2 100644 --- a/src/lib/apis/utils/index.ts +++ b/src/lib/apis/utils/index.ts @@ -180,38 +180,3 @@ export const downloadDatabase = async (token: string) => { } }; -export const downloadLiteLLMConfig = async (token: string) => { - let error = null; - - const res = await fetch(`${WEBUI_API_BASE_URL}/utils/litellm/config`, { - method: 'GET', - headers: { - 'Content-Type': 'application/json', - Authorization: `Bearer ${token}` - } - }) - .then(async (response) => { - if (!response.ok) { - throw await response.json(); - } - return response.blob(); - }) - .then((blob) => { - const url = window.URL.createObjectURL(blob); - const a = document.createElement('a'); - a.href = url; - a.download = 'config.yaml'; - document.body.appendChild(a); - a.click(); - window.URL.revokeObjectURL(url); - }) - .catch((err) => { - console.error(err); - error = err.detail; - return null; - }); - - if (error) { - throw error; - } -}; diff --git a/src/lib/components/admin/Functions.svelte b/src/lib/components/admin/Functions.svelte index 4bbcebd15f..bd438257cb 100644 --- a/src/lib/components/admin/Functions.svelte +++ b/src/lib/components/admin/Functions.svelte @@ -158,6 +158,7 @@ if (res) { toast.success($i18n.t('Function deleted successfully')); + functions = functions.filter((f) => f.id !== func.id); _functions.set(await getFunctions(localStorage.token)); models.set( diff --git a/src/lib/components/admin/Settings/Audio.svelte b/src/lib/components/admin/Settings/Audio.svelte index dcd7ad3029..863cbe34cc 100644 --- a/src/lib/components/admin/Settings/Audio.svelte +++ b/src/lib/components/admin/Settings/Audio.svelte @@ -50,6 +50,9 @@ let STT_AZURE_BASE_URL = ''; let STT_AZURE_MAX_SPEAKERS = ''; let STT_DEEPGRAM_API_KEY = ''; + let STT_MISTRAL_API_KEY = ''; + let STT_MISTRAL_API_BASE_URL = ''; + let STT_MISTRAL_USE_CHAT_COMPLETIONS = false; let STT_WHISPER_MODEL_LOADING = false; @@ -135,7 +138,10 @@ AZURE_REGION: STT_AZURE_REGION, AZURE_LOCALES: STT_AZURE_LOCALES, AZURE_BASE_URL: STT_AZURE_BASE_URL, - AZURE_MAX_SPEAKERS: STT_AZURE_MAX_SPEAKERS + AZURE_MAX_SPEAKERS: STT_AZURE_MAX_SPEAKERS, + MISTRAL_API_KEY: STT_MISTRAL_API_KEY, + MISTRAL_API_BASE_URL: STT_MISTRAL_API_BASE_URL, + MISTRAL_USE_CHAT_COMPLETIONS: STT_MISTRAL_USE_CHAT_COMPLETIONS } }); @@ -184,6 +190,9 @@ STT_AZURE_BASE_URL = res.stt.AZURE_BASE_URL; STT_AZURE_MAX_SPEAKERS = res.stt.AZURE_MAX_SPEAKERS; STT_DEEPGRAM_API_KEY = res.stt.DEEPGRAM_API_KEY; + STT_MISTRAL_API_KEY = res.stt.MISTRAL_API_KEY; + STT_MISTRAL_API_BASE_URL = res.stt.MISTRAL_API_BASE_URL; + STT_MISTRAL_USE_CHAT_COMPLETIONS = res.stt.MISTRAL_USE_CHAT_COMPLETIONS; } await getVoices(); @@ -201,7 +210,7 @@
-
{$i18n.t('Speech-to-Text')}
+
{$i18n.t('Speech-to-Text')}
@@ -235,6 +244,7 @@ +
@@ -367,6 +377,67 @@
+ {:else if STT_ENGINE === 'mistral'} +
+
+ + + +
+
+ +
+ +
+
{$i18n.t('STT Model')}
+
+
+ +
+
+
+ {$i18n.t('Leave empty to use the default model (voxtral-mini-latest).')} + + {$i18n.t('Learn more about Voxtral transcription.')} + +
+
+ +
+ +
+
+
{$i18n.t('Use Chat Completions API')}
+ +
+
+ {$i18n.t( + 'Use /v1/chat/completions endpoint instead of /v1/audio/transcriptions for potentially better accuracy.' + )} +
+
{:else if STT_ENGINE === ''}
{$i18n.t('STT Model')}
@@ -427,7 +498,7 @@
-
{$i18n.t('Text-to-Speech')}
+
{$i18n.t('Text-to-Speech')}
diff --git a/src/lib/components/admin/Settings/CodeExecution.svelte b/src/lib/components/admin/Settings/CodeExecution.svelte index 6050fb26bb..5838a2f4d1 100644 --- a/src/lib/components/admin/Settings/CodeExecution.svelte +++ b/src/lib/components/admin/Settings/CodeExecution.svelte @@ -41,7 +41,7 @@ {#if config}
-
{$i18n.t('General')}
+
{$i18n.t('General')}
@@ -164,7 +164,7 @@
-
{$i18n.t('Code Interpreter')}
+
{$i18n.t('Code Interpreter')}
diff --git a/src/lib/components/admin/Settings/Connections.svelte b/src/lib/components/admin/Settings/Connections.svelte index 100e440d5d..93cf755be8 100644 --- a/src/lib/components/admin/Settings/Connections.svelte +++ b/src/lib/components/admin/Settings/Connections.svelte @@ -219,7 +219,7 @@
{#if ENABLE_OPENAI_API !== null && ENABLE_OLLAMA_API !== null && connectionsConfig !== null}
-
{$i18n.t('General')}
+
{$i18n.t('General')}
diff --git a/src/lib/components/admin/Settings/Database.svelte b/src/lib/components/admin/Settings/Database.svelte index d5bebed221..1c966ac356 100644 --- a/src/lib/components/admin/Settings/Database.svelte +++ b/src/lib/components/admin/Settings/Database.svelte @@ -2,7 +2,7 @@ import fileSaver from 'file-saver'; const { saveAs } = fileSaver; - import { downloadDatabase, downloadLiteLLMConfig } from '$lib/apis/utils'; + import { downloadDatabase } from '$lib/apis/utils'; import { onMount, getContext } from 'svelte'; import { config, user } from '$lib/stores'; import { toast } from 'svelte-sonner'; diff --git a/src/lib/components/admin/Settings/Documents.svelte b/src/lib/components/admin/Settings/Documents.svelte index 35e0484916..1d55bf872f 100644 --- a/src/lib/components/admin/Settings/Documents.svelte +++ b/src/lib/components/admin/Settings/Documents.svelte @@ -212,6 +212,15 @@ await embeddingModelUpdateHandler(); } + if (RAGConfig.MINERU_PARAMS) { + try { + JSON.parse(RAGConfig.MINERU_PARAMS); + } catch (e) { + toast.error($i18n.t('Invalid JSON format in MinerU Parameters')); + return; + } + } + const res = await updateRAGConfig(localStorage.token, { ...RAGConfig, ALLOWED_FILE_EXTENSIONS: RAGConfig.ALLOWED_FILE_EXTENSIONS.split(',') @@ -220,7 +229,13 @@ DOCLING_PICTURE_DESCRIPTION_LOCAL: JSON.parse( RAGConfig.DOCLING_PICTURE_DESCRIPTION_LOCAL || '{}' ), - DOCLING_PICTURE_DESCRIPTION_API: JSON.parse(RAGConfig.DOCLING_PICTURE_DESCRIPTION_API || '{}') + DOCLING_PICTURE_DESCRIPTION_API: JSON.parse( + RAGConfig.DOCLING_PICTURE_DESCRIPTION_API || '{}' + ), + MINERU_PARAMS: + typeof RAGConfig.MINERU_PARAMS === 'string' && RAGConfig.MINERU_PARAMS.trim() !== '' + ? JSON.parse(RAGConfig.MINERU_PARAMS) + : {} }); dispatch('save'); }; @@ -261,6 +276,11 @@ 2 ); + config.MINERU_PARAMS = + typeof config.MINERU_PARAMS === 'object' + ? JSON.stringify(config.MINERU_PARAMS ?? {}, null, 2) + : config.MINERU_PARAMS; + RAGConfig = config; }); @@ -317,7 +337,7 @@
-
{$i18n.t('General')}
+
{$i18n.t('General')}
@@ -746,6 +766,11 @@
{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'mistral_ocr'}
+ -
-
+
+
-
+
{/if}
diff --git a/src/lib/components/layout/SearchModal.svelte b/src/lib/components/layout/SearchModal.svelte index 4fcdae309a..6aed01d145 100644 --- a/src/lib/components/layout/SearchModal.svelte +++ b/src/lib/components/layout/SearchModal.svelte @@ -56,12 +56,7 @@ } const loadChatPreview = async (selectedIdx) => { - if ( - !chatList || - chatList.length === 0 || - selectedIdx === null || - chatList[selectedIdx] === undefined - ) { + if (!chatList || chatList.length === 0 || selectedIdx === null) { selectedChat = null; messages = null; history = null; @@ -70,8 +65,11 @@ } const selectedChatIdx = selectedIdx - actions.length; - if (selectedChatIdx < 0) { + if (selectedChatIdx < 0 || selectedChatIdx >= chatList.length) { selectedChat = null; + messages = null; + history = null; + selectedModels = ['']; return; } diff --git a/src/lib/components/layout/Sidebar.svelte b/src/lib/components/layout/Sidebar.svelte index 14e73f2046..c8d8a19018 100644 --- a/src/lib/components/layout/Sidebar.svelte +++ b/src/lib/components/layout/Sidebar.svelte @@ -183,6 +183,7 @@ console.log('initChatList'); currentChatPage.set(1); allChatsLoaded = false; + scrollPaginationEnabled.set(false); initFolders(); await Promise.all([ @@ -368,10 +369,6 @@ navElement.style['-webkit-app-region'] = 'drag'; } } - - if (!$showSidebar && !value) { - showSidebar.set(true); - } }), showSidebar.subscribe(async (value) => { localStorage.sidebar = value; @@ -751,7 +748,10 @@ -
+
{$WEBUI_NAME}
diff --git a/src/lib/components/layout/Sidebar/SearchInput.svelte b/src/lib/components/layout/Sidebar/SearchInput.svelte index 700b0fe881..1f95ff5bb7 100644 --- a/src/lib/components/layout/Sidebar/SearchInput.svelte +++ b/src/lib/components/layout/Sidebar/SearchInput.svelte @@ -76,7 +76,7 @@ .filter((tag) => { const tagName = lastWord.slice(4); if (tagName) { - const tagId = tagName.replace(' ', '_').toLowerCase(); + const tagId = tagName.replaceAll(' ', '_').toLowerCase(); if (tag.id !== tagId) { return tag.id.startsWith(tagId); @@ -99,8 +99,8 @@ .filter((folder) => { const folderName = lastWord.slice(7); if (folderName) { - const id = folder.name.replace(' ', '_').toLowerCase(); - const folderId = folderName.replace(' ', '_').toLowerCase(); + const id = folder.name.replaceAll(' ', '_').toLowerCase(); + const folderId = folderName.replaceAll(' ', '_').toLowerCase(); if (id !== folderId) { return id.startsWith(folderId); @@ -113,7 +113,7 @@ }) .map((folder) => { return { - id: folder.name.replace(' ', '_').toLowerCase(), + id: folder.name.replaceAll(' ', '_').toLowerCase(), name: folder.name, type: 'folder' }; diff --git a/src/lib/components/layout/Sidebar/UserMenu.svelte b/src/lib/components/layout/Sidebar/UserMenu.svelte index b4385fc39f..c3775ebf22 100644 --- a/src/lib/components/layout/Sidebar/UserMenu.svelte +++ b/src/lib/components/layout/Sidebar/UserMenu.svelte @@ -66,8 +66,8 @@ fade(e, { duration: 100 })} > { - try { - const [{ default: jsPDF }, { default: html2canvas }] = await Promise.all([ - import('jspdf'), - import('html2canvas-pro') - ]); - - // Define a fixed virtual screen size - const virtualWidth = 1024; // Fixed width (adjust as needed) - const virtualHeight = 1400; // Fixed height (adjust as needed) - - // STEP 1. Get a DOM node to render - const html = note.data?.content?.html ?? ''; - const isDarkMode = document.documentElement.classList.contains('dark'); - - let node; - if (html instanceof HTMLElement) { - node = html; - } else { - const virtualWidth = 800; // px, fixed width for cloned element - - // Clone and style - node = document.createElement('div'); - - // title node - const titleNode = document.createElement('div'); - titleNode.textContent = note.title; - titleNode.style.fontSize = '24px'; - titleNode.style.fontWeight = 'medium'; - titleNode.style.paddingBottom = '20px'; - titleNode.style.color = isDarkMode ? 'white' : 'black'; - node.appendChild(titleNode); - - const contentNode = document.createElement('div'); - - contentNode.innerHTML = html; - - node.appendChild(contentNode); - - node.classList.add('text-black'); - node.classList.add('dark:text-white'); - node.style.width = `${virtualWidth}px`; - node.style.position = 'absolute'; - node.style.left = '-9999px'; - node.style.height = 'auto'; - node.style.padding = '40px 40px'; - - console.log(node); - document.body.appendChild(node); + try { + await downloadPdf(note); + } catch (error) { + toast.error(`${error}`); } - - // Render to canvas with predefined width - const canvas = await html2canvas(node, { - useCORS: true, - backgroundColor: isDarkMode ? '#000' : '#fff', - scale: 2, // Keep at 1x to avoid unexpected enlargements - width: virtualWidth, // Set fixed virtual screen width - windowWidth: virtualWidth, // Ensure consistent rendering - windowHeight: virtualHeight - }); - - // Remove hidden node if needed - if (!(html instanceof HTMLElement)) { - document.body.removeChild(node); - } - - const imgData = canvas.toDataURL('image/jpeg', 0.7); - - // A4 page settings - const pdf = new jsPDF('p', 'mm', 'a4'); - const imgWidth = 210; // A4 width in mm - const pageWidthMM = 210; // A4 width in mm - const pageHeight = 297; // A4 height in mm - const pageHeightMM = 297; // A4 height in mm - - if (isDarkMode) { - pdf.setFillColor(0, 0, 0); - pdf.rect(0, 0, pageWidthMM, pageHeightMM, 'F'); // black bg - } - - // Maintain aspect ratio - const imgHeight = (canvas.height * imgWidth) / canvas.width; - let heightLeft = imgHeight; - let position = 0; - - pdf.addImage(imgData, 'JPEG', 0, position, imgWidth, imgHeight); - heightLeft -= pageHeight; - - // Handle additional pages - while (heightLeft > 0) { - position -= pageHeight; - pdf.addPage(); - - if (isDarkMode) { - pdf.setFillColor(0, 0, 0); - pdf.rect(0, 0, pageWidthMM, pageHeightMM, 'F'); // black bg - } - - pdf.addImage(imgData, 'JPEG', 0, position, imgWidth, imgHeight); - heightLeft -= pageHeight; - } - - pdf.save(`${note.title}.pdf`); - } catch (error) { - console.error('Error generating PDF', error); - - toast.error(`${error}`); } }; diff --git a/src/lib/components/notes/NoteEditor/Chat.svelte b/src/lib/components/notes/NoteEditor/Chat.svelte index 3f6b691549..2430f602e1 100644 --- a/src/lib/components/notes/NoteEditor/Chat.svelte +++ b/src/lib/components/notes/NoteEditor/Chat.svelte @@ -35,12 +35,7 @@ import { goto } from '$app/navigation'; import { onMount, tick, getContext } from 'svelte'; - import { - OLLAMA_API_BASE_URL, - OPENAI_API_BASE_URL, - WEBUI_API_BASE_URL, - WEBUI_BASE_URL - } from '$lib/constants'; + import { WEBUI_BASE_URL } from '$lib/constants'; import { WEBUI_NAME, config, user, models, settings } from '$lib/stores'; import { chatCompletion } from '$lib/apis/openai'; @@ -189,7 +184,10 @@ Based on the user's instruction, update and enhance the existing notes or select { model: model.id, stream: true, - messages: chatMessages + messages: chatMessages.map((m) => ({ + role: m.role, + content: m.content + })) // ...(files && files.length > 0 ? { files } : {}) // TODO: Decide whether to use native file handling or not }, `${WEBUI_BASE_URL}/api` @@ -327,7 +325,7 @@ Based on the user's instruction, update and enhance the existing notes or select }); -
+
-
+
@@ -377,7 +375,7 @@ Based on the user's instruction, update and enhance the existing notes or select
{#if selectedContent} -
+
{selectedContent?.text} diff --git a/src/lib/components/notes/NoteEditor/Controls.svelte b/src/lib/components/notes/NoteEditor/Controls.svelte index df988c28d9..675056ee41 100644 --- a/src/lib/components/notes/NoteEditor/Controls.svelte +++ b/src/lib/components/notes/NoteEditor/Controls.svelte @@ -17,7 +17,7 @@ }; -
+
-
+
{#if files.length > 0} -
{$i18n.t('Files')}
+
{$i18n.t('Files')}
{#each files.filter((file) => file.type !== 'image') as file, fileIdx} diff --git a/src/lib/components/notes/NotePanel.svelte b/src/lib/components/notes/NotePanel.svelte index 676d86b83d..96e687854e 100644 --- a/src/lib/components/notes/NotePanel.svelte +++ b/src/lib/components/notes/NotePanel.svelte @@ -99,7 +99,7 @@ {#if show}
diff --git a/src/lib/components/notes/Notes.svelte b/src/lib/components/notes/Notes.svelte index 3f4294cf5b..14f1392625 100644 --- a/src/lib/components/notes/Notes.svelte +++ b/src/lib/components/notes/Notes.svelte @@ -36,6 +36,8 @@ import { createNewNote, deleteNoteById, getNotes } from '$lib/apis/notes'; import { capitalizeFirstLetter, copyToClipboard, getTimeRange } from '$lib/utils'; + import { downloadPdf } from './utils'; + import EllipsisHorizontal from '../icons/EllipsisHorizontal.svelte'; import DeleteConfirmDialog from '$lib/components/common/ConfirmDialog.svelte'; import Search from '../icons/Search.svelte'; @@ -124,82 +126,18 @@ }; const downloadHandler = async (type) => { - console.log('downloadHandler', type); - console.log('selectedNote', selectedNote); - if (type === 'md') { + if (type === 'txt') { + const blob = new Blob([selectedNote.data.content.md], { type: 'text/plain' }); + saveAs(blob, `${selectedNote.title}.txt`); + } else if (type === 'md') { const blob = new Blob([selectedNote.data.content.md], { type: 'text/markdown' }); saveAs(blob, `${selectedNote.title}.md`); } else if (type === 'pdf') { - await downloadPdf(selectedNote); - } - }; - - const downloadPdf = async (note) => { - try { - const [{ default: jsPDF }, { default: html2canvas }] = await Promise.all([ - import('jspdf'), - import('html2canvas-pro') - ]); - - // Define a fixed virtual screen size - const virtualWidth = 1024; // Fixed width (adjust as needed) - const virtualHeight = 1400; // Fixed height (adjust as needed) - - // STEP 1. Get a DOM node to render - const html = note.data?.content?.html ?? ''; - let node; - if (html instanceof HTMLElement) { - node = html; - } else { - // If it's HTML string, render to a temporary hidden element - node = document.createElement('div'); - node.innerHTML = html; - document.body.appendChild(node); + try { + await downloadPdf(selectedNote); + } catch (error) { + toast.error(`${error}`); } - - // Render to canvas with predefined width - const canvas = await html2canvas(node, { - useCORS: true, - scale: 2, // Keep at 1x to avoid unexpected enlargements - width: virtualWidth, // Set fixed virtual screen width - windowWidth: virtualWidth, // Ensure consistent rendering - windowHeight: virtualHeight - }); - - // Remove hidden node if needed - if (!(html instanceof HTMLElement)) { - document.body.removeChild(node); - } - - const imgData = canvas.toDataURL('image/jpeg', 0.7); - - // A4 page settings - const pdf = new jsPDF('p', 'mm', 'a4'); - const imgWidth = 210; // A4 width in mm - const pageHeight = 297; // A4 height in mm - - // Maintain aspect ratio - const imgHeight = (canvas.height * imgWidth) / canvas.width; - let heightLeft = imgHeight; - let position = 0; - - pdf.addImage(imgData, 'JPEG', 0, position, imgWidth, imgHeight); - heightLeft -= pageHeight; - - // Handle additional pages - while (heightLeft > 0) { - position -= pageHeight; - pdf.addPage(); - - pdf.addImage(imgData, 'JPEG', 0, position, imgWidth, imgHeight); - heightLeft -= pageHeight; - } - - pdf.save(`${note.title}.pdf`); - } catch (error) { - console.error('Error generating PDF', error); - - toast.error(`${error}`); } }; diff --git a/src/lib/components/notes/utils.ts b/src/lib/components/notes/utils.ts new file mode 100644 index 0000000000..46a7ea8458 --- /dev/null +++ b/src/lib/components/notes/utils.ts @@ -0,0 +1,103 @@ +export const downloadPdf = async (note) => { + const [{ default: jsPDF }, { default: html2canvas }] = await Promise.all([ + import('jspdf'), + import('html2canvas-pro') + ]); + + // Define a fixed virtual screen size + const virtualWidth = 1024; // Fixed width (adjust as needed) + const virtualHeight = 1400; // Fixed height (adjust as needed) + + // STEP 1. Get a DOM node to render + const html = note.data?.content?.html ?? ''; + const isDarkMode = document.documentElement.classList.contains('dark'); + + let node; + if (html instanceof HTMLElement) { + node = html; + } else { + const virtualWidth = 800; // px, fixed width for cloned element + + // Clone and style + node = document.createElement('div'); + + // title node + const titleNode = document.createElement('div'); + titleNode.textContent = note.title; + titleNode.style.fontSize = '24px'; + titleNode.style.fontWeight = 'medium'; + titleNode.style.paddingBottom = '20px'; + titleNode.style.color = isDarkMode ? 'white' : 'black'; + node.appendChild(titleNode); + + const contentNode = document.createElement('div'); + + contentNode.innerHTML = html; + + node.appendChild(contentNode); + + node.classList.add('text-black'); + node.classList.add('dark:text-white'); + node.style.width = `${virtualWidth}px`; + node.style.position = 'absolute'; + node.style.left = '-9999px'; + node.style.height = 'auto'; + node.style.padding = '40px 40px'; + + console.log(node); + document.body.appendChild(node); + } + + // Render to canvas with predefined width + const canvas = await html2canvas(node, { + useCORS: true, + backgroundColor: isDarkMode ? '#000' : '#fff', + scale: 2, // Keep at 1x to avoid unexpected enlargements + width: virtualWidth, // Set fixed virtual screen width + windowWidth: virtualWidth, // Ensure consistent rendering + windowHeight: virtualHeight + }); + + // Remove hidden node if needed + if (!(html instanceof HTMLElement)) { + document.body.removeChild(node); + } + + const imgData = canvas.toDataURL('image/jpeg', 0.7); + + // A4 page settings + const pdf = new jsPDF('p', 'mm', 'a4'); + const imgWidth = 210; // A4 width in mm + const pageWidthMM = 210; // A4 width in mm + const pageHeight = 297; // A4 height in mm + const pageHeightMM = 297; // A4 height in mm + + if (isDarkMode) { + pdf.setFillColor(0, 0, 0); + pdf.rect(0, 0, pageWidthMM, pageHeightMM, 'F'); // black bg + } + + // Maintain aspect ratio + const imgHeight = (canvas.height * imgWidth) / canvas.width; + let heightLeft = imgHeight; + let position = 0; + + pdf.addImage(imgData, 'JPEG', 0, position, imgWidth, imgHeight); + heightLeft -= pageHeight; + + // Handle additional pages + while (heightLeft > 0) { + position -= pageHeight; + pdf.addPage(); + + if (isDarkMode) { + pdf.setFillColor(0, 0, 0); + pdf.rect(0, 0, pageWidthMM, pageHeightMM, 'F'); // black bg + } + + pdf.addImage(imgData, 'JPEG', 0, position, imgWidth, imgHeight); + heightLeft -= pageHeight; + } + + pdf.save(`${note.title}.pdf`); +}; diff --git a/src/lib/components/workspace/Knowledge/KnowledgeBase.svelte b/src/lib/components/workspace/Knowledge/KnowledgeBase.svelte index 3c494e7609..0054eb2964 100644 --- a/src/lib/components/workspace/Knowledge/KnowledgeBase.svelte +++ b/src/lib/components/workspace/Knowledge/KnowledgeBase.svelte @@ -184,12 +184,6 @@ if (uploadedFile) { console.log(uploadedFile); - - if (uploadedFile.error) { - console.warn('File upload warning:', uploadedFile.error); - toast.warning(uploadedFile.error); - } - knowledge.files = knowledge.files.map((item) => { if (item.itemId === tempItemId) { item.id = uploadedFile.id; @@ -199,7 +193,14 @@ delete item.itemId; return item; }); - await addFileHandler(uploadedFile.id); + + if (uploadedFile.error) { + console.warn('File upload warning:', uploadedFile.error); + toast.warning(uploadedFile.error); + knowledge.files = knowledge.files.filter((file) => file.id !== uploadedFile.id); + } else { + await addFileHandler(uploadedFile.id); + } } else { toast.error($i18n.t('Failed to upload file.')); } diff --git a/src/lib/components/workspace/Models.svelte b/src/lib/components/workspace/Models.svelte index a2d7258b65..2f9c5b5910 100644 --- a/src/lib/components/workspace/Models.svelte +++ b/src/lib/components/workspace/Models.svelte @@ -16,7 +16,7 @@ import { createNewModel, deleteModelById, - getModels as getWorkspaceModels, + getModelItems as getWorkspaceModels, toggleModelById, updateModelById } from '$lib/apis/models'; diff --git a/src/lib/components/workspace/Models/ToolsSelector.svelte b/src/lib/components/workspace/Models/ToolsSelector.svelte index 5f1b3b4821..af5f9f09f2 100644 --- a/src/lib/components/workspace/Models/ToolsSelector.svelte +++ b/src/lib/components/workspace/Models/ToolsSelector.svelte @@ -1,5 +1,6 @@