yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-06-26 22:00:19 +00:00
Code Issues Packages Projects Releases Wiki Activity
3,950 Commits 2 Branches 39 Tags
Commit Graph

342 Commits

Author SHA1 Message Date
yangdx
495d6c8cce Improve the pipeline status message for document deletetion 2025-06-25 15:46:58 +08:00
yangdx
da46b341dc feat: Optimize document deletion performance 
- To enhance performance during document deletion, new batch-get methods, `get_nodes_by_chunk_ids` and `get_edges_by_chunk_ids`, have been added to the graph storage layer (`BaseGraphStorage` and its implementations). The [`adelete_by_doc_id`](lightrag/lightrag.py:1681) function now leverages these methods to avoid unnecessary iteration over the entire knowledge graph, significantly improving efficiency.
- Graph storage updated: Networkx, Neo4j, Postgres AGE
 2025-06-25 12:37:57 +08:00
zrguo
3a9494ab60 Update operate.py 2025-06-09 19:47:29 +08:00
zrguo
9a71a10bc0 Update operate.py 2025-06-09 19:40:29 +08:00
zrguo
ead82a8dbd update delete_by_doc_id 2025-06-09 18:52:34 +08:00
yangdx
36a736db0b Fix node merge error 2025-05-30 12:30:24 +08:00
zrguo
40b10e8fcf Update insert_custom_kg 2025-05-27 16:07:04 +08:00
yangdx
9ec9579a95 Fix linting 2025-05-11 11:24:52 +08:00
yangdx
68653f853a fix: handle missing 'weight' attribute in edge data to prevent KeyError 
- Add validation in _find_most_related_edges_from_entities and  _get_edge_data function during edge data construction
- Add warning logs when 'weight' attribute is missing and set default value of 0.0
 2025-05-11 11:16:32 +08:00
yangdx
d2d755db7b Normalize keyword extration result 2025-05-08 16:05:52 +08:00
yangdx
de40f1b5b3 Deduplicate merged relation keywords 2025-05-08 15:52:18 +08:00
yangdx
b92f9b9453 Optimizing query prompt 2025-05-08 12:53:28 +08:00
yangdx
10dbbe4ebf Fix linting 2025-05-08 04:29:43 +08:00
yangdx
ae1c9f8d10 Add user_prompt the QueryParam 2025-05-08 03:38:47 +08:00
yangdx
08e532eaf3 Remove unused text_chunks_db param from naive_query 2025-05-08 03:26:14 +08:00
yangdx
3eb3b170ab Remove list_of_list_to_dict function 2025-05-07 18:01:23 +08:00
yangdx
156244e260 Refactor: Unify naive context to JSON format 
- Merges 'mix' mode query handling into 'hybrid' mode, simplifying query logic by removing the dedicated `mix_kg_vector_query` function
- Standardizes vector search result by using JSON string format to build context
- Fixes a bug in `query_with_keywords` ensuring `hl_keywords` and `ll_keywords` are correctly passed to `kg_query_with_keywords`
 2025-05-07 17:42:14 +08:00
yangdx
59771b60df Optimize relationship title to entity1 and entity2 2025-05-07 13:02:22 +08:00
yangdx
1e03888cef Change function name get_kg_context to _get_kg_context 2025-05-07 10:57:33 +08:00
yangdx
3146309fde Change function name from list_of_list_to_json to list_of_list_to_dict 2025-05-07 10:52:26 +08:00
yangdx
edb3d6ac11 Improve query context format for mix mode 2025-05-07 10:51:44 +08:00
yangdx
2485bfe53c Fix linting 2025-05-07 03:57:14 +08:00
yangdx
910a7a8936 Unified vector retrieval logic for mix and naive queries 2025-05-07 03:47:09 +08:00
yangdx
1794b57b43 Ignore chat history in vector search 2025-05-07 03:20:39 +08:00
yangdx
c984ebd462 Improve mix query context format 2025-05-07 03:11:59 +08:00
yangdx
098846b651 Improve naive query context format 2025-05-07 02:52:05 +08:00
yangdx
b1f874b489 Fix linting 2025-05-07 01:51:58 +08:00
yangdx
52d8815230 Elimiate redunction chunk data fecth for niave query mode 2025-05-07 01:46:23 +08:00
yangdx
027c67a73c Skip self-referential relationships in edge processing 2025-05-05 11:58:33 +08:00
yangdx
9ff3542ab2 Fix time handling bugs for graph data 2025-05-01 15:14:15 +08:00
yangdx
6ec36ee538 Fix time handle bugs for _get_edge_data 2025-05-01 11:33:42 +08:00
yangdx
48fd250257 Optimize log messages 2025-04-29 19:02:08 +08:00
yangdx
43f255a5b4 Optimize log message 2025-04-29 18:20:35 +08:00
yangdx
a4a0643ad0 Enable graph_db_lock log 2025-04-28 23:21:07 +08:00
yangdx
90a07b0420 Remove unused params 2025-04-28 21:14:19 +08:00
yangdx
ef69009c15 Increase the priority of queries related to LLM requests 2025-04-28 19:36:21 +08:00
yangdx
5a393e563e remove duplicate priority setting for merge summerization 2025-04-28 18:37:51 +08:00
yangdx
140b1b3cbb Add priority control for limited async decorator 2025-04-28 18:12:29 +08:00
yangdx
3e385b5f81 Optimize logger info 2025-04-28 02:39:18 +08:00
yangdx
ef4a4ac8ed Optimize looger info 2025-04-28 02:35:35 +08:00
yangdx
594e7b751a Fix linting 2025-04-28 02:15:25 +08:00
yangdx
18040aa95c Improve parallel handling logic between extraction and merge operation 2025-04-28 01:14:00 +08:00
yangdx
dc498b88e0 Update logger message 2025-04-23 20:40:19 +08:00
yangdx
d89e0f7208 Fix linting 2025-04-23 19:35:05 +08:00
yangdx
a6f0c0b33b Simplify entity extraction prompt formatting logic 2025-04-23 18:55:03 +08:00
yangdx
2bfef70960 Fix context format 2025-04-22 21:17:01 +08:00
Daniel.y
a09f6eb170
Merge pull request #1423 from tackhwa/main 
friendly implementation of entity extraction and relationship weight extract for Low-Capability LLMs
 2025-04-22 19:11:04 +08:00
tackhwa
2e186ba488 remove regex 2025-04-22 15:22:37 +08:00
yangdx
1eef9b7205 Set max parallel chunks processing according to MAX_SYNC of LLM 2025-04-22 15:03:46 +08:00
yangdx
21c0bb7abf Merge branch 'context_format_csv_to_json' 2025-04-22 12:25:50 +08:00