yangdx 4ab4a7ac94 Allow embedding models to use provider defaults when unspecified ... - Set EMBEDDING_MODEL default to None - Pass model param only when provided - Let providers use their own defaults - Fix lollms embed function params - Add ollama embed_model default param		2025-11-28 16:57:33 +08:00
..
api	Allow embedding models to use provider defaults when unspecified	2025-11-28 16:57:33 +08:00
evaluation	Update LLM cache migration docs and improve UX prompts	2025-11-08 23:48:19 +08:00
kg	Add pipeline status lock function for legacy compatibility	2025-11-25 18:24:39 +08:00
llm	Allow embedding models to use provider defaults when unspecified	2025-11-28 16:57:33 +08:00
tools	Refactor main function to provide sync CLI entry point	2025-11-21 13:11:55 +08:00
__init__.py	Bump core version to 1.4.9.9 and API to 0252	2025-11-08 11:27:26 +08:00
base.py	Remove unused chunk-based node/edge retrieval methods	2025-11-06 18:17:10 +08:00
constants.py	Refactor entity merging with unified attribute merge function	2025-10-27 00:04:17 +08:00
exceptions.py	Fix ChunkTokenLimitExceededError message formatting	2025-11-19 18:50:45 +08:00
lightrag.py	Fix linting	2025-11-18 22:38:43 +08:00
namespace.py	Add entity/relation chunk tracking with configurable source ID limits	2025-10-20 15:24:15 +08:00
operate.py	Change entity extraction logging from warning to info level	2025-11-27 11:00:34 +08:00
prompt.py	Fix typo in 'equipment' in prompt.py	2025-10-22 11:13:22 +08:00
rerank.py	fix: Resolve default rerank config problem when env var missing	2025-08-23 01:07:59 +08:00
types.py
utils.py	Fix double decoration in azure_openai_embed and document decorator usage	2025-11-21 18:03:53 +08:00
utils_graph.py	Improve entity merge logging by removing redundant message and fixing typo	2025-10-31 17:16:59 +08:00