yangdx 271722405f feat: Flatten LLM cache structure for improved recall efficiency ... Refactored the LLM cache to a flat Key-Value (KV) structure, replacing the previous nested format. The old structure used the 'mode' as a key and stored specific cache content as JSON nested under it. This change significantly enhances cache recall efficiency.		2025-07-02 16:11:53 +08:00
..
unofficial-sample	feat: Flatten LLM cache structure for improved recall efficiency	2025-07-02 16:11:53 +08:00
graph_visual_with_html.py	fixed networkx	2025-02-19 13:48:18 +01:00
graph_visual_with_neo4j.py	Fix linting	2025-05-18 07:17:21 +08:00
insert_custom_kg.py	Updated documentation examples to include chunk_order_index case	2025-02-19 14:58:51 +01:00
lightrag_azure_openai_demo.py	fix demo	2025-03-04 12:25:07 +08:00
lightrag_gemini_demo.py	fix linting	2025-03-03 18:40:03 +08:00
lightrag_gemini_demo_no_tiktoken.py	fix linting	2025-04-18 16:24:43 +02:00
lightrag_gemini_track_token_demo.py	feat(TokenTracker): Add context manager support to simplify token tracking	2025-03-30 00:59:23 +08:00
lightrag_ollama_demo.py	Fix linting	2025-05-14 01:14:45 +08:00
lightrag_openai_compatible_demo.py	Update openai compatible demo	2025-05-13 17:48:45 +08:00
lightrag_openai_demo.py	Update openai demo	2025-05-13 18:27:55 +08:00
lightrag_openai_mongodb_graph_demo.py	fix linting	2025-03-03 18:40:03 +08:00
modalprocessors_example.py	Update RAGAnything related	2025-06-26 16:08:14 +08:00
raganything_example.py	Update RAGAnything related	2025-06-26 16:08:14 +08:00