- Refactor parser_config assignment to use spread operator for better merging
- Preserve existing parser_config values when initializing defaults
- Merge graphrag configuration from record if present
- Ensure default values are applied while maintaining user-provided settings
- Extend model options merging logic to include 'image2text' type alongside 'llm'
- Combine image2text model options with llm and chat options for unified selection
- Enable image2text models to be available in the CreateModal component
- Add API endpoints for creating sync tasks and checking Feishu/Yuque authentication
- Add new sync-related UI components for Feishu and Yuque platform integration
- Add internationalization strings for sync operations and authentication messages in English and Chinese
- Add form fields for Feishu (App ID, App Secret, Folder Token) and Yuque (User ID, Token) credentials
- Add web crawler configuration fields (entry URL, max pages, delay, timeout, user agent)
- Add sync status messages (syncing, success, completed, timeout, failed, error states)
- Update CreateDataset component to support new data source types
- Update KnowledgeBase types to include new sync-related properties
- Enable users to synchronize knowledge base content from Feishu and Yuque platforms with proper authentication and error handling
* [add]Integration of the core engineering and memory extraction
* [add]The import and export function of the main body engineering files
* [add]Improve the import interface
* [add]Introducing generic types helps with entity extraction
* [add]Modify the references of the main repository to the sub-repositories
* [add]The extraction trial run introduces the ontology type.
* [add]Integration of the core engineering and memory extraction
* [add]The import and export function of the main body engineering files
* [add]Improve the import interface
* [add]Introducing generic types helps with entity extraction
* [add]Modify the references of the main repository to the sub-repositories
* [add]The extraction trial run introduces the ontology type.
* [add]Complete the second phase of the main project content
* [add]The dependencies and configurations of the main body project
* [add]Modify the code based on the AI review
- Add support for both memory_config_id (new) and memory_content (legacy) field names
- Implement detection and handling of legacy int format memory configurations
- Add validation for numeric string formats with appropriate warning logs
- Support case-insensitive memory node type matching (MemoryRead/MemoryWrite and memory-read/memory-write)
- Improve error handling with more descriptive logging for invalid UUID strings
- Fix config_id field reference in memory config resolution
- Ensure backward compatibility with existing agent configurations while supporting new format
- Add workspace_id fallback parameter to memory config loading across all services
- Update hot_memory_tags.py to pass workspace_id when resolving memory configuration
- Enhance emotion_analytics_service.py to support workspace_id as fallback for config resolution
- Improve implicit_memory_service.py with workspace_id fallback in config loading
- Update memory_agent_service.py to handle workspace_id resolution and add refactoring TODO
- Enhance preference_analysis.jinja2 prompt with critical guidance on supporting_evidence extraction
- Add validation to check both config_id and workspace_id before raising configuration errors
- Improve error handling and logging for memory configuration resolution across services
- This enables more flexible memory configuration resolution when config_id is unavailable
1. Three party web website data access - Web site synchronization
Building a knowledge base by crawling web page data in batches through web crawlers
Web site synchronization utilizes crawler technology, which can automatically capture all websites under the same domain name through a single entry website. Currently, it supports up to 200 subpages. For compliance and security reasons, only static site crawling is supported, mainly used for quickly building knowledge bases on various document sites.
2. Feishu Knowledge Base
By configuring Feishu document permissions, a knowledge base can be built using Feishu documents, and the documents will not undergo secondary storage
3. Language Bird Knowledge Base
You can configure the permissions of the language bird document to build a knowledge base using the language bird document, and the document will not undergo secondary storage
