BREAKING CHANGE: content field is now List[str] instead of str
- Add ReferenceItem Pydantic model for type safety
- Update /query and /query/stream to return content as list
- Update OpenAPI schema and examples
- Add migration guide to API README
- Fix RAGAS evaluation to handle list format
Addresses PR #2297 feedback. Tested with RAGAS: 97.37% score.
BREAKING CHANGE: The `content` field in query response references is now
an array of strings instead of a concatenated string. This preserves
individual chunk boundaries when a single file has multiple chunks.
Changes:
- Update QueryResponse Pydantic model to accept List[str] for content
- Modify query_text endpoint to return content as list (query_routes.py:425)
- Modify query_text_stream endpoint to support chunk content enrichment
- Update OpenAPI schema and examples to reflect array structure
- Update API README with breaking change notice and migration guide
- Fix RAGAS evaluation to flatten chunk content lists
Added comprehensive documentation for the new include_chunk_content parameter
that enables retrieval of actual chunk text content in API responses.
Documentation Updates:
- Added "Include Chunk Content in References" section to API README
- Explained use cases: RAG evaluation, debugging, citations, transparency
- Provided JSON request/response examples
- Clarified parameter interaction with include_references
OpenAPI/Swagger Examples:
- Added "Response with chunk content" example to /query endpoint
- Shows complete reference structure with content field
- Demonstrates realistic chunk text content
This makes the feature discoverable through:
1. API documentation (README.md)
2. Interactive Swagger UI (http://localhost:9621/docs)
3. Code examples for developers
- **API:** The `graph/entity/edit` endpoint now returns a detailed `operation_summary` for better client-side handling of update, rename, and merge outcomes.
- **Web UI:** Added an "auto-merge on rename" option. The UI now gracefully handles merge success, partial failures (update OK, merge fail), and other errors with specific user feedback.
• Use "preprocessed" to indicate multimodal processing is required
• Update DocProcessingStatus to process status convertion automatically
• Remove multimodal_processed from DocStatus enum value
• Update UI filter logic
• Add delete_llm_cache parameter to API
• Collect cache IDs from text chunks
• Delete cache after graph operations
• Update UI with new checkbox option
• Add i18n translations for cache option
- Add entity_chunks & relation_chunks storage
- Implement KEEP/FIFO limit strategies
- Update env.example with new settings
- Add migration for chunk tracking data
- Support all KV storage
• Add DocStatus.PREPROCESSED enum value
• Update API routes and response models
• Add preprocessed filter in web UI
• Update localization files
• Handle preprocessed status in deletion
- Changed create_entity to use rag.acreate_entity() instead of direct graph manipulation
- Changed create_relation to use rag.acreate_relation() instead of direct graph manipulation
- This ensures vector embeddings are created and entities/relations are searchable
- Adds proper concurrency locks and metadata population
Added three new REST API endpoints for direct knowledge graph manipulation:
- POST /graph/entity/create: Create new entities in the knowledge graph
- POST /graph/relation/create: Create relationships between entities
- POST /graph/entities/merge: Merge duplicate/misspelled entities while preserving relationships
The merge endpoint is particularly useful for consolidating entities discovered after document processing, fixing spelling errors, and cleaning up the knowledge graph. All relationships from source entities are transferred to the target entity, with intelligent handling of duplicate relationships.
Updated API documentation in lightrag/api/README.md with usage examples for all three endpoints.
Add a new `/documents/reprocess_failed` API endpoint and corresponding
UI button to retry processing of failed and pending documents. This
addresses a common recovery scenario when document processing fails due
to server crashes, network errors, or LLM service outages.
Backend changes:
- Add ReprocessResponse model with status, message, and track_id fields
- Add POST /documents/reprocess_failed endpoint that triggers background
reprocessing of FAILED, PENDING, and interrupted PROCESSING documents
- Reuses existing apipeline_process_enqueue_documents for consistency
- Includes comprehensive docstring and logging for observability
Frontend changes:
- Add TypeScript types and API function for the new endpoint
- Add retry handler with intelligent polling (fast refresh → normal)
- Add "Retry Failed" button in Documents page toolbar
- Button disabled when pipeline is busy to prevent duplicate operations
- Complete i18n support (English and Chinese translations)
This feature provides a convenient way to recover from processing
failures without requiring a full filesystem rescan.
- Add new aquery_llm/query_llm methods providing structured responses
- Consolidate /query and /query/stream endpoints to use unified aquery_llm
- Optimize cache handling by moving cache checks before LLM calls
• Add include_references param to QueryRequest
• Extend QueryResponse with references field
• Create unified QueryResult data structures
• Refactor kg_query and naive_query functions
• Update streaming to send references first
- Add get_doc_by_file_path to all storages
- Skip processed files in scan operation
- Check duplicates in upload endpoints
- Check duplicates in text insert APIs
- Return status info in duplicate responses
• Limit history to 1000 latest messages
• Add truncation message when needed
• Show count of truncated messages
• Update API documentation
• Prevent memory issues with large logs
