* feat(web): remove mock data
* feat(knowledgeBase): Refactor document list API and improve polling logic
- Update getDocumentList API to accept kb_id as separate parameter instead of extracting from query object
- Fix parameter name from auto_question to auto_questions in parser config
- Add progress field initialization in document update params
- Improve polling logic to handle both auto-return and manual stay scenarios with proper loading state management
- Add console logging for debugging polling status and document processing
- Reduce polling interval from 5000ms to 3000ms for faster status updates
- Enhance cleanup logic with route change detection to prevent memory leaks
- Add record parameter to progress render function for better data access
- Refactor confirm dialog callbacks to properly manage loading state timing
- Ensure loading indicator displays correctly when user chooses to stay on page
* feat(web): Add Workflow
* feat(web): Workflow
* feat(web): node show id; update reflection engine example
* feat(components): Add markdown editing capability and enhance component styling
- Add editable mode to Markdown component with edit/save/cancel buttons
- Import EditOutlined, SaveOutlined, CloseOutlined icons from ant-design
- Add useState, useRef, useEffect hooks for managing edit state
- Add editable, onContentChange, and onSave props to RbMarkdownProps interface
- Create RbModal component with new index.css stylesheet for modal styling
- Add index.css stylesheet to KnowledgeBase components for consistent styling
- Update i18n translations in en.ts and zh.ts for new UI elements
- Refactor Markdown component handlers to accept and spread additional props
- Update InsertModal and RecallTestResult components for improved UX
- Fix prop spreading in component handlers to maintain compatibility with Ant Design components
* feat(web): Graph user memory update
* feat(web): update routes.json
* fix(web): workflow bug
* fix(web): workflow variable
* fix(web): workflow properties
* feat(web): workflow support lexical editor
* feat(web): workflow support lexical editor
* feat(web): update reflection engine result
* feat(web): workflow's chat support abort output
* fix:git commit
* fix:vite config
* fix:breadcrumbs
* feat(i18n): add document processing confirmation dialog translations
- Add "processingDocuments" translation key for loading state message in English and Chinese
- Add "startUploadConfirmTitle" translation for confirmation dialog title
- Add "startUploadConfirmContent" translation for confirmation dialog description
- Add "returnToList" translation for returning to list page action
- Add "stayOnPage" translation for staying on current page action
- Support user choice to either return to list or stay on page during background document processing
* fix(web): user memory detail
* feat(web): order
* fix:面包屑修改
* feat(web): 1. user memory; 2. update workspace's model config
* feat(web): update zh.ts / en.ts
* fix(web): update user profile
* feat(web): Agent add ai prompt
* feat(web): Agent add ai prompt
* feat(web): add pricing menu
* feat(knowledgeBase): add media file validation and PDF enhancement method selection
- Add i18n translations for file size and duration validation errors in English and Chinese
- Implement media file validation with 256MB size limit and 150-second duration limit
- Add support for audio and video file formats (mp3, mp4, mov, wav) in dataset creation
- Add checkMediaDuration helper function to validate media file duration using HTML5 media API
- Add PDF enhancement method selection dropdown with options (DeepDoc, MinerU, TextLN)
- Change default PDF enhancement setting from disabled to enabled
- Update file type array to include media formats
- Add error messaging for file size and duration validation failures
- Improve UI spacing for file parsing settings section
* feat(knowledgeBase): add media dataset support and improve file handling
- Add media dataset translations in English and Chinese locales
- Add "mediaDataSet" and "uploadMedia" i18n keys for UI labels
- Enable media dataset creation option in Private component by uncommenting menu item
- Import and display image icon for media dataset menu option
- Refactor file ID handling in CreateDataset to support both string and array types
- Improve fileIds initialization logic to handle mixed input types
- Update CreateImageDataset component to use file chunking workflow
- Add navigation to parameter settings step after file upload
- Pass file IDs to dataset creation flow for media processing
- Add message API and navigate hook for improved UX feedback
* fix(knowledgeBase): improve navigation and folder tree refresh logic
- Add path comparison check in breadcrumb navigation to avoid unnecessary route changes when already on target page
- Implement delayed folder tree refresh with setTimeout to ensure state reset completes before refreshing
- Add manual table refresh trigger to ensure data updates after navigation
- Reset expanded keys in FolderTree component during load to ensure consistent state from root directory
- Add expanded keys reset in breadcrumb navigation to prevent stale expansion state
- Improve navigation state handling by using replace flag only when on target path to reduce history stack pollution
* fix:pdfEnhancementEnabled
* feat(web): add tool management
* fix(web): get the parent domain name adaptation IP
* fix(web): Conversation add initialValue
* feat(web): workflow’s Editor Variable support Tag
* fix(web): pricing UI
* feat(web): JSON Tool update
* fix(web): update get llm,chat model list function
* fix(web): time tool / cluster chat
* fix(web): time tool add time zone
* feat(web): neo4j type user memory detail
* fix(web): update parseSchema api param
* feat: workflow add knowledge-retrieval node
* feat(knowledgeBase): enhance file upload and dataset creation with abort support and improved UX
- Add AbortSignal support to uploadFile API for cancellable uploads
- Implement custom onRemove callback in UploadFiles component with confirmation dialog
- Add i18n translations for file removal confirmation and error messages
- Update supported file types documentation to include IMAGE and MEDIA formats
- Improve file removal UI with cursor pointer styling
- Refactor getModelList API to remove unused type parameter
- Add Form import and UploadFile type for better type safety in CreateDataset
- Enhance error handling and user feedback for file operations
* feat(web): MCP add bearer token auth type
* fix(web): UI update
---------
Co-authored-by: zhaoying <yzhao96@best-inc.com>
Co-authored-by: yujiangping <yujiangping@taofen8.com>
Co-authored-by: 赵莹 <zhaoying@redbearai.com>
Co-authored-by: vrhs@163.com <accounts_660b6454a0eb398d3f8d2c76@mail.teambition.com>
Merge branch 'develop' into feature/20251219_myh
* feature/20251219_myh: (8 commits squashed)
- feat(workflow): update reranker model configuration for knowledge base retrieval
- fix(workflow): fix output issue in parameter extraction node
- fix(workflow): fix output issue in parameter extraction node
- feat(workflow): add user prompt to parameter extraction node
- perf(workflow): change grouped variable input to key-value format in variable aggregator
- feat(workflow): Add new cycle node for iterative workflow execution
- Introduce a new Loop/Iteration node in the workflow engine.
- Supports both conditional loops and iteration over lists.
- Allows parallel execution and flattening of iteration outputs.
- Maintains runtime state, node outputs, and loop variables for downstream nodes.
- Enhances workflow flexibility for complex, repeated operations.
- Merge branch 'develop' into feature/20251219_myh
# Conflicts:
#	api/app/core/workflow/nodes/configs.py
#	api/app/core/workflow/nodes/node_factory.py
- feat(workflow): Add new cycle node for iterative workflow execution
- Introduce a new Loop/Iteration node in the workflow engine.
- Supports both conditional loops and iteration over lists.
- Allows parallel execution and flattening of iteration outputs.
- Maintains runtime state, node outputs, and loop variables for downstream nodes.
- Enhances workflow flexibility for complex, repeated operations.
Signed-off-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Reviewed-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
Merged-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/78
Add new predicates for learning/education domain to support educational content extraction. Also add field validator to filter empty statements in extraction response to handle malformed LLM outputs.
Add functions related to knowledge base graph:
1. Entity type generation,
2. Knowledge base graph acquisition,
3. Hard deletion of knowledge base graph,
4. Knowledge base graph reconstruction (asynchronous)
1. Optimization of the JSON tool, add insert, replace, delete, parse
2. Optimization of the mcp test_connection
3. tool list desc
4. datetime_tool default timezone set Asia/Shanghai
- Implemented ParameterExtractorNode to extract structured parameters from input text using LLM.
- Supports dynamic Jinja2 prompt rendering with field descriptions and types.
- Integrates with RedBearLLM and ModelConfigService for model retrieval.
- Handles JSON repair and raises clear BusinessException on parsing errors.
- Add MemoryAPIService with read_memory and write_memory methods for managing user memories
- Create memory_api_schema.py with request/response schemas for read and write operations
- Implement write_memory_api_service endpoint for storing memory content with configurable storage backends
- Implement read_memory_api_service endpoint for querying memories with context-aware responses
- Add memory-specific error codes (MEMORY_WRITE_FAILED, MEMORY_READ_FAILED, MEMORY_CONFIG_NOT_FOUND) to error_codes.py
