- 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.
- 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
- Add global --temperature command line argument with env fallback
- Implement temperature priority for Ollama LLM binding:
1. --ollama-llm-temperature (highest)
2. OLLAMA_LLM_TEMPERATURE env var
3. --temperature command arg
4. TEMPERATURE env var (lowest)
- Implement same priority logic for OpenAI/Azure OpenAI LLM binding
- Ensure command line args always override environment variables
- Maintain backward compatibility with existing configurations
- Add OpenAILLMOptions dataclass with full OpenAI API parameter support
- Integrate OpenAI options in config.py for automatic binding detection
- Update server functions to inject OpenAI options for openai/azure_openai bindings
- Implement OLLAMA_LLM_TEMPERATURE env var
- Fallback to global TEMPERATURE if unset
- Remove redundant OllamaLLMOptions logic
- Update env.example with new setting
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
Add get_all_nodes() and get_all_edges() methods to Neo4JStorage, PGGraphStorage, MongoGraphStorage, and MemgraphStorage classes. These methods return all nodes and edges in the graph with consistent formatting matching NetworkXStorage for compatibility across different storage backends.
- 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
