4068 Commits

Author SHA1 Message Date
yangdx
8ea7d7ad85 Feat: Add document deletion for WebUI 2025-06-25 17:09:10 +08:00
yangdx
51bb0471cd Change the API for deleting documents to support deleting multiple documents at once. 2025-06-25 16:19:49 +08:00
yangdx
495d6c8cce Improve the pipeline status message for document deletetion 2025-06-25 15:46:58 +08:00
yangdx
2aaa6d5f7d Fix linting 2025-06-25 14:59:45 +08:00
yangdx
49baeb7318 Change document deletion API to async 2025-06-25 14:59:10 +08:00
yangdx
8a365533d7 Add comprehensive error handling for document deletion 2025-06-25 14:58:41 +08:00
yangdx
922484915b Remove deprecated API endpoint. 2025-06-25 13:55:47 +08:00
Daniel.y
c6a28bfe4b
Merge pull request #1697 from HKUDS/delete_doc
feat: Optimize document deletion performance
2025-06-25 13:16:20 +08:00
yangdx
72384f87c4 Remove deprecated code from Postgres_impl.py
- Stop filtering out 'base' node labels
- Match any edge type in query to improve performance
2025-06-25 12:53:07 +08:00
yangdx
492269ac44 Bump core version to 1.3.10 2025-06-25 12:39:57 +08:00
yangdx
109c2b48be Fix linting 2025-06-25 12:39:43 +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
yangdx
ebe5b1e0d2 Bump api version to 0175 2025-06-24 22:16:06 +08:00
Ken Chen
12054fa8d9
Merge branch 'HKUDS:main' into main 2025-06-24 20:20:54 +08:00
Daniel.y
3acdeeb871
Merge pull request #1693 from HKUDS/delete_doc
Feat: Add comprehensive document deletion feature with integrated knowledge graph reconstruction
v1.3.9
2025-06-24 11:33:20 +08:00
yangdx
2946bbdb71 Add TODO: There is performance when iterating get_all_labels 2025-06-24 11:32:28 +08:00
yangdx
8b6dcfb6eb Pls do not use /delete_document API endpoint 2025-06-24 11:26:38 +08:00
yangdx
5ae945c1e5 Improved error handling for document deletion
Added HTTPException for not_found status
Added HTTPException for fail status
2025-06-24 01:12:25 +08:00
yangdx
fd69c895cd Remove debug looging from Neo4j 2025-06-24 01:03:02 +08:00
yangdx
64d0df0caa Remove debug logging from Neo4J operations
- Delete node upsert debug log
- Remove edge upsert debug messages
2025-06-24 00:45:17 +08:00
yangdx
cc12460b38 Fix: Silence PostgreSQL logs during idempotent graph initialization 2025-06-23 23:08:56 +08:00
yangdx
c18065a912 Disable document deletion when LLM cache for extraction is off 2025-06-23 22:41:27 +08:00
yangdx
1973c80dca Feat: Add entity and relation deletion endpoints 2025-06-23 22:14:50 +08:00
yangdx
e6baffe10c Add retrun status to entity and relation delete operations 2025-06-23 21:39:45 +08:00
yangdx
bd487dd252 Unify document APIs returen status string 2025-06-23 21:38:47 +08:00
yangdx
ce50135efb Improved docstring for document deletion method 2025-06-23 21:08:51 +08:00
yangdx
1697ea4bf6 Fix linting 2025-06-23 19:20:35 +08:00
yangdx
f60bad92f0 Fix: Delete relations from vector DB in both directions 2025-06-23 19:20:10 +08:00
yangdx
ebcabe29ca Remove duplicated graph db lock 2025-06-23 18:46:01 +08:00
yangdx
b8a2d5b223 Bump api version to 0174 2025-06-23 18:42:34 +08:00
yangdx
5099ac8213 Fix linting 2025-06-23 18:41:30 +08:00
yangdx
a215939c41 Refac: Avoid duplicate edge processing in adelete_by_doc_id 2025-06-23 18:39:36 +08:00
yangdx
dffe659388 Feat: Add document deletion by ID API endpoint
- New DELETE endpoint for document removal
- Implements doc_id-based deletion
- Handles pipeline status during operation
- Includes proper error handling
- Updates pipeline status messages
2025-06-23 18:10:40 +08:00
yangdx
a0be65d5d9 Refac: Return status and messages for delete by doc id operaton 2025-06-23 17:59:27 +08:00
yangdx
9fae0eadff feat: Ensure thread safety for graph write operations
Add a lock to delete, adelete_by_entity, and adelete_by_relation methods to prevent race conditions and ensure data consistency during concurrent modifications to the knowledge graph.
2025-06-23 09:57:56 +08:00
zrguo
c947b20bb1 Update README.md 2025-06-22 16:43:18 +08:00
zrguo
4937de8809 Update 2025-06-22 15:12:09 +08:00
zrguo
afdc2b3da8 Merge branch 'main' into delete_doc 2025-06-22 14:39:07 +08:00
Ken Chen
a047d966ab MongoGraph: Separate edges from node collection 2025-06-21 21:05:04 +08:00
zrguo
d1aeb291d6 Update README.md 2025-06-19 17:01:21 +08:00
zrguo
bc70e6066c
Merge pull request #1671 from Chaoyingz/main
Fix incorrect spacing
2025-06-19 14:17:52 +08:00
zrguo
96b9bd8cc5 fix lint 2025-06-19 14:16:24 +08:00
zrguo
523550d9ba
Merge pull request #1643 from eddiemaru-101/fix/ollama-timeout-handling
Fix: Increase Ollama timeout values to prevent ReadTimeout errors
2025-06-19 14:15:05 +08:00
zrguo
c8b56620c1 Merge branch 'main' into delete_doc 2025-06-19 14:12:17 +08:00
chaohuang-ai
a408465602
Update README.md 2025-06-17 10:39:30 +08:00
chaohuang-ai
caf0411889
Update README.md 2025-06-17 10:38:34 +08:00
zrguo
eea64b9763
Merge pull request #1688 from HKUDS/RAGAnything
RAG-Anything Integration
2025-06-17 01:23:07 +08:00
zrguo
03dd99912d RAG-Anything Integration 2025-06-17 01:16:02 +08:00
zrguo
3abdc42549 Merge branch 'main' into delete_doc 2025-06-16 17:02:21 +08:00
Ken Chen
cf441aa84c Add missing methods for MongoGraphStorage 2025-06-15 21:22:32 +08:00