yangdx b5c230abdd optimize: avoid duplicate embedding calls in _build_query_context ... Reduces API costs and improves query performance while maintaining backward compatibility.		2025-08-21 16:49:24 +08:00
..
api	Update documentation with LLM selection guidelines and API improvements	2025-08-21 13:59:14 +08:00
kg	Fix logging level usage in Redis retry decorator	2025-08-20 05:21:15 +08:00
llm	feat: Add extra_body parameter support for OpenRouter/vLLM compatibility	2025-08-21 13:06:28 +08:00
tools
__init__.py	Bump core version to 1.4.7 and api version to 0198	2025-08-04 10:55:41 +08:00
base.py	feat: KG related chunks selection by vector similarity	2025-08-13 18:16:42 +08:00
constants.py	Set default TIMEOUT value to 150, and gunicorn timeout to TIMEOUT+30	2025-08-20 22:04:32 +08:00
exceptions.py
lightrag.py	Rename MAX_TOKENS to SUMMARY_MAX_TOKENS for clarity	2025-08-21 10:15:20 +08:00
llm.py
namespace.py	Refac: Add workspace infomation to all logger output for all storage type	2025-08-12 01:19:09 +08:00
operate.py	optimize: avoid duplicate embedding calls in _build_query_context	2025-08-21 16:49:24 +08:00
prompt.py	Refactor keyword extraction rules and remove overlap constraint	2025-08-19 15:07:40 +08:00
rerank.py	Fix: rename rerank parameter from top_k to top_n	2025-07-20 00:26:27 +08:00
types.py
utils.py	optimize: avoid duplicate embedding calls in _build_query_context	2025-08-21 16:49:24 +08:00
utils_graph.py	Fix GRAPH_FIELD_SEP import typo	2025-06-29 01:28:39 +05:00