- Read config from selected_rerank_func when env var missing
- Make api_key optional for rerank function
- Add response format validation with proper error handling
- Update Cohere rerank default to official API endpoint
- Reset documents with PROCESSING/FAILED status to PENDING when they pass consistency checks
- Update doc_status storage and clear error messages/metadata on reset
- Add apipeline_enqueue_error_documents function to LightRAG class for recording file processing errors in doc_status storage
- Enhance pipeline_enqueue_file with detailed error handling for all file processing stages:
* File access errors (permissions, not found)
* UTF-8 encoding errors
* Format-specific processing errors (PDF, DOCX, PPTX, XLSX)
* Content validation errors
* Unsupported file type errors
This implementation ensures all file extraction failures are properly tracked and recorded in the doc_status storage system, providing better visibility into document processing issues and enabling improved error monitoring and debugging capabilities.
This ensures data consistency validation is part of the main processing pipeline and provides better monitoring of inconsistent document cleanup operations.
- Add _validate_and_fix_document_consistency() method to detect and fix documents with missing content in full_docs storage
- Integrate consistency check into apipeline_process_enqueue_documents() to automatically mark inconsistent documents as FAILED before processing
- Prevent processing errors caused by documents having status records but missing actual content data
- Add env switch to toggle weighted polling vs vector-similarity strategy
- Implement similarity-based sorting with fallback to weighted
- Introduce batch vector read API for vector storage
- Implement vector store and retrive funtion for Nanovector DB
- Preserve default behavior (weighted polling selection method)
- Remove optional 'modes' parameter from aclear_cache() and clear_cache() methods
- Replace deprecated drop_cache_by_modes() with drop() method for complete cache clearing
- Update API endpoint to ignore mode-specific parameters and clear all cache
- Simplify frontend clearCache() function to send empty request body
This change ensures all LLM cache is cleared together.
The `_migrate_entity_relation_data` function previously processed directed edges from `get_all_edges`, which could lead to duplicates (e.g., (A,B) and (B,A)) and an incorrect relation count.
This commit normalizes edges by sorting their source and target nodes before adding them to the relation set. This ensures all edges are treated as undirected and are properly deduplicated.
- The `initialize_storages` method must be explicitly called after LightRAG creation.
The `finalize_storages` method should be called before LightRAG destyoyed.
- Added explicit data migration check
- Introduces an index mapping documents to their corresponding entities and relations. This significantly speeds up `adelete_by_doc_id` by replacing slow graph traversal with a fast key-value lookup.
- Refactors the ingestion pipeline (`merge_nodes_and_edges`) to populate this new index. Adds a one-time data migration script to backfill the index for existing data.
Replace regex-based JSON extraction with json-repair for better handling of malformed LLM responses. Remove deprecated JSON parsing utilities and clean up keyword_extraction parameter across LLM providers.
- Remove locate_json_string_body_from_string() and convert_response_to_json()
- Use json-repair.loads() in extract_keywords_only() for robust parsing
- Clean up LLM interfaces and remove unused parameters
- Add json-repair dependency
