- Updated configuration to support three tasks in the assistant's prompt: rewriting questions, classifying intent for knowledge base retrieval, and analyzing attached images.
- Implemented backend functionality to update image descriptions in user messages, ensuring that image context is preserved across conversation history.
- Modified session handling to return complete session data after updates, improving the accuracy of session information provided to users.
- Enhanced the chat pipeline to include detailed image descriptions and manage image captions effectively, enriching user interactions with visual content.
These improvements significantly enhance the application's multimodal capabilities, providing a more robust and user-friendly experience when handling image-based queries.
- Updated configuration to improve handling of multimodal queries, including clearer guidelines for when to use [NO_SEARCH] in responses.
- Enhanced the user interface to include dedicated sections for multimodal configuration, allowing users to manage image uploads and related settings more effectively.
- Added localization support for new multimodal features in both English and Chinese, improving accessibility for a broader audience.
- Implemented backend changes to support image analysis and extraction of OCR text, enriching the interaction experience for users.
These enhancements significantly improve the application's capability to process and respond to multimodal queries, fostering a more interactive and user-friendly environment.
- Added functionality for image uploads in chat, allowing users to attach images for multimodal Q&A.
- Enhanced the input field to handle image selection via drag-and-drop and paste, with validation for file types and sizes.
- Updated the backend to process images alongside text queries, including support for image analysis.
- Introduced new UI components for image previews and management, improving user interaction with uploaded content.
- Added localization strings for image upload features and error messages, enhancing accessibility for users in multiple languages.
These changes significantly improve the chat experience by enabling users to incorporate images into their queries, facilitating richer interactions and responses.
- Updated the summary length requirement for document summarization to 100-300 words.
- Added new localization strings for missing storage engine notifications in English, Korean, Russian, and Chinese.
- Implemented UI warnings for users regarding storage engine configuration when files exist, including confirmation dialogs for storage engine changes.
- Enhanced backend validation to ensure a storage engine is configured before allowing content uploads.
These changes improve user experience by providing clearer guidance on storage engine requirements and enhancing the overall functionality of the knowledge base management system.
- add StreamSender interface and streaming output for WeCom/Feishu
- refactor WeCom adapter into separate webhook and websocket files
- add output_mode config for stream/full toggle per platform
- add stream flush batching, dedup cleanup, and think-block filtering
- improve context template to handle irrelevant retrieved info gracefully
- add IM streaming integration tests
- add IM integration documentation with quick start guide
- support webhook and websocket modes for both platforms
- add im_channel_sessions migration for channel-session mapping
- register IM adapters and callback routes
- update config and docker-compose for IM env vars
Convert all LLM-facing prompts, templates, and tool output labels to
language-neutral English so the model responds in the user's input
language. Update frontend relevance/match-type mappings to match.
Output language strategy:
- User-facing: reply in user's input language
- Vector-indexed: match source document language
- LLM-internal: fixed English
- Updated `config.yaml` to adjust conversation parameters for improved search performance.
- Added a new `knowledgeSemanticSearch` API function for semantic search capabilities.
- Introduced new SVG icons for search functionality.
- Created `KnowledgeSearch.vue` component for the search interface, including query input and result display.
- Enhanced menu and routing to support navigation to the new knowledge search page.
- Updated internationalization files to include translations for the knowledge search feature.
This update provides users with a powerful tool to perform semantic searches across knowledge bases, improving content discoverability.
- Added configuration for enabling cross-tenant access in the application.
- Introduced new API endpoints for listing and searching tenants, accessible only to users with the appropriate permissions.
- Updated user and tenant models to include the `can_access_all_tenants` field.
- Enhanced the authentication middleware to handle cross-tenant requests and validate user permissions.
- Created a new TenantSelector component for selecting tenants in the frontend, improving user experience.
- Updated internationalization files to support new tenant-related strings and messages.
- Added support for query expansion in conversation settings, allowing the system to generate additional queries when recall is low.
- Updated localization files in English, Russian, and Chinese to include new strings for the query expansion feature.
- Enhanced UI in AgentSettings.vue to allow users to toggle query expansion settings.
- Refactored related API and service logic to accommodate the new query expansion functionality in session management and chat processing.
- Updated agent configuration to support separate system prompts for web search enabled and disabled states.
- Removed deprecated agent configuration parameters to streamline settings management.
- Enhanced UI components in AgentSettings.vue to allow configuration of custom prompts based on web search status.
- Improved localization in English, Russian, and Chinese for new prompt settings and UI elements.
- Refactored related API and service logic to accommodate changes in agent configuration structure.
- Added DuckDuckGo as a new web search provider in the configuration.
- Removed deprecated web search providers (Baidu, Bing, Bocha, Exa, Google, Kuaisou, Searxng, Tavily, Zhipu) to streamline the codebase.
- Enhanced knowledge base management by introducing temporary knowledge base handling in the session service.
- Updated the web search service to support RAG-based compression for improved search result processing.
- Refactored session and knowledge service interfaces to accommodate new functionalities.
- Introduced web search configuration in config.yaml, allowing multiple providers with specific settings.
- Updated InputField component to manage agent mode and web search toggles, improving user interaction.
- Enhanced chat API to include web search status in requests, enabling dynamic query handling.
- Implemented backend support for web search integration, merging results with knowledge base queries.
- Added tenant-level web search configuration management, allowing customization per tenant.