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
..
api	update ollama compatible api	2025-06-30 10:41:35 +08:00
kg	feat: Flatten LLM cache structure for improved recall efficiency	2025-07-02 16:11:53 +08:00
llm	Merge pull request #1654 from a-bruhn/azure-env-vars	2025-06-26 19:11:20 +08:00
tools	Revert "Cleanup of code"	2025-02-20 15:09:43 +01:00
__init__.py	Bump core version to 1.3.10	2025-06-25 12:39:57 +08:00
base.py	Remove default get_nodes_by_chunk_ids implementation	2025-06-29 22:05:48 +08:00
constants.py	feat: Optimize document deletion performance	2025-06-25 12:37:57 +08:00
exceptions.py
lightrag.py	Refac: Add KG rebuild logging with pipeline status	2025-06-29 21:27:12 +08:00
llm.py
namespace.py
operate.py	feat: Flatten LLM cache structure for improved recall efficiency	2025-07-02 16:11:53 +08:00
prompt.py	feat: Optimize document deletion performance	2025-06-25 12:37:57 +08:00
types.py	Add is_truncated to graph query for NetworkX graph db	2025-04-02 22:12:20 +08:00
utils.py	feat: Flatten LLM cache structure for improved recall efficiency	2025-07-02 16:11:53 +08:00
utils_graph.py	Fix GRAPH_FIELD_SEP import typo	2025-06-29 01:28:39 +05:00