- Track timestamps for cache hits/misses
- Add timestamp to entity/relationship objects
- Sort descriptions by timestamp order
- Preserve temporal ordering in merges
- Add system/user prompt separation
- Set max tokens for endless output fix
- Improve extraction error logging
- Update cache type from extract to summary
The function now properly handles cases where text contains </think> closing tags
without corresponding <think> opening tags, which can occur due to content
truncation or processing errors.
- Improve reduntant quotes in entity and relation name, type and keywords
- Add HTML tag cleaning and Chinese symbol conversion
- Filter out short numeric content and malformed text
- Enhance entity type validation with character filtering
- 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
- Add --enable-rerank CLI argument and ENABLE_RERANK env var
- Simplify rerank configuration logic to only check enable flag and binding
- Update health endpoint to show enable_rerank and rerank_configured status
- Improve logging messages for rerank enable/disable states
- Maintain backward compatibility with default value True
- Remove file_path and created_at fields from entity and relationship contexts
- Update token truncation to include full JSON serialization instead of content only
• Replace pyuca with centralized utils function
• Add pinyin sort keys for file paths
• Update MongoDB indexes with zh collation
• Migrate existing indexes for compatibility
• Support Chinese chars in Redis/JSON storage
• Keep PostgreSQL sorting order controled by Database Collate order
• Track chunk sources (E/R/C types)
• Log frequency and order metadata
• Preserve chunk_id through processing
• Add debug logging for chunk tracking
• Handle rerank and truncation operations
- 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)
- Add missing query parameters (top_k, enable_rerank, max_tokens, etc.) to cache key generation in kg_query, naive_query, and extract_keywords_only functions
- Add queryparam field to CacheData structure and PostgreSQL storage for debugging
- Update PostgreSQL schema with automatic migration for queryparam JSONB column
- Prevent incorrect cache hits between queries with different parameters
Fixes issue where different query parameters incorrectly shared the same cached results.
- Delete quantize_embedding function
- Delete dequantize_embedding function
- Remove embedding fields from CacheData
- Update save_to_cache to exclude embedding data
- Clean up unused quantization-related code
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
