Ken Chen
d0f4eee404
Fix accidentally hardcoded edge collection name in searching upstream nodes
2025-06-28 16:25:44 +08:00
Ken Chen
6574dfb7ea
Fix accidentally hardcode max depth in searching upstream nodes
2025-06-28 11:40:39 +08:00
Ken Chen
b586bdc02f
Fix accidentally hardcode label in searching upstream nodes
2025-06-28 10:50:56 +08:00
Ken Chen
7c8f65d020
Add search on neighbor nodes which are source to selected one
2025-06-28 08:50:32 +08:00
Ken Chen
f40bc43d5e
Fix nodes & edges are missing when retrieving knowledge subgraph by selecting particular node_id
2025-06-26 23:11:31 +08:00
yangdx
6e1ca8f461
Merge branch 'patch-1'
2025-06-26 18:45:23 +08:00
yangdx
687ccd4923
fix: optimize MongoDB aggregation pipeline to prevent memory limit errors
...
- Move $limit operation early in pipeline for "*" queries to reduce memory usage
- Remove memory-intensive $sort operation for large dataset queries
- Add fallback mechanism for memory limit errors with simple query
- Implement additional safety checks to enforce max_nodes limit
- Improve error handling and logging for memory-related issues
2025-06-26 14:37:04 +08:00
yangdx
d8b544ab6f
Fix linting
2025-06-26 14:15:11 +08:00
yangdx
c51079335e
Optimize node label retrieval with aggregation
...
- Enable allowDiskUse for large datasets
2025-06-26 14:14:52 +08:00
yangdx
d60db573dc
Add allowDiskUse flag to MongoDB aggregations
...
- Enable disk use for large aggregations
- Fix cursor handling for list_search_indexes
- Improve query performance for big datasets
- Update vector search index check
- Set proper length for to_list results
2025-06-26 13:51:53 +08:00
yangdx
71565f4794
Add get_all method to MongoKVStorage
2025-06-26 13:51:15 +08:00
yangdx
d512db26e4
Fix MongoDB set handling in delete operations
2025-06-26 13:50:19 +08:00
yangdx
6364d076aa
Enable MongoGraphStorage
2025-06-26 13:47:50 +08:00
Ken Chen
a3865caaea
Implement get_nodes_by_chunk_ids and get_edges_by_chunk_ids,
2025-06-25 22:17:17 +08:00
Ken Chen
81cff6e97f
Merge branch 'HKUDS:main' into main
2025-06-25 20:35:55 +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
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
Ken Chen
12054fa8d9
Merge branch 'HKUDS:main' into main
2025-06-24 20:20:54 +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
zrguo
4937de8809
Update
2025-06-22 15:12:09 +08:00
Ken Chen
a047d966ab
MongoGraph: Separate edges from node collection
2025-06-21 21:05:04 +08:00
Ken Chen
cf441aa84c
Add missing methods for MongoGraphStorage
2025-06-15 21:22:32 +08:00
zrguo
ead82a8dbd
update delete_by_doc_id
2025-06-09 18:52:34 +08:00
pablo-statsig
4a8202138c
Remove graspologic pip installation that no longer seems to be used
...
As far as I can tell this is no longer actually used and its usage was removed in this commit:
83353ab9a6 (diff-a346bcfb05aab0cc0c0baa6018976f4efab339e8cade9f6f8fb658fcbd54ae2e)
Our systems are flagging this package as having a dependency on a package with a less permissive license so I would appreciate if it can be removed if its no longer needed. Let me know if that is not the case.
2025-06-05 18:01:00 -07:00
yangdx
ada2443653
Optimize default setting of PostgreSQL
2025-05-22 17:09:26 +08:00
yangdx
2ee809cf58
Increase PG connection pool to 20
2025-05-22 16:37:18 +08:00
zrguo
cf4bb148fb
fix linting
2025-05-12 16:28:36 +08:00
zrguo
61a21f8d5d
Merge pull request #1325 from venkateshpabbati/main
...
security fix
2025-05-12 16:25:11 +08:00
yangdx
ebdc7cea49
Merge branch 'allow_max_connection_config' into pg-max-connection
2025-05-09 14:16:53 +08:00
Arjun Rao
6ebd76d5da
bugfix: convert config val to int
2025-05-09 04:22:46 +10:00
Arjun Rao
f2c522ce7a
Allow max_connections to be configured in postgres
2025-05-08 11:00:56 +10:00
widgit
e070c19414
Update postgres_impl.py
...
Was missing , on the SQL Table create command
2025-05-05 23:55:19 +10:00
yangdx
e46a4b2079
Optimize log message
2025-05-04 22:31:57 +08:00
yangdx
9a41de51fb
Optimize log message
2025-05-04 22:20:44 +08:00
yangdx
dcb2a72462
Fix JSON handling error for PostgreSQL graph storage
2025-05-04 22:18:56 +08:00
yangdx
1213f53fc9
Fix mistakenly interpreting a string as JSON for PostgreSQL AGE graph storage
2025-05-04 02:20:43 +08:00
yangdx
2063f6c6c8
Fix created_at handling bug for Milvus
2025-05-03 21:51:45 +08:00
yangdx
ca240fa463
Remove buggy data migration function
2025-05-03 16:23:03 +08:00
yangdx
045993f7d2
Remove deprecated search_by_prefix
2025-05-03 11:17:49 +08:00
yangdx
3b4015f6fd
Translate commnet to English
2025-05-03 00:54:17 +08:00
yangdx
08e8a7ead1
Fix linting
2025-05-03 00:46:28 +08:00
yangdx
debe8f329a
Fix created_at problem for Tidb vector storage
2025-05-03 00:46:10 +08:00
yangdx
81071df982
Fix timezone bugs for PostgreSQL vector storage
2025-05-03 00:44:55 +08:00
yangdx
c3df1908dc
Fix created_at probelm for MongoDB vector storage
2025-05-02 21:48:01 +08:00
yangdx
02de7420b2
Fix create_at problem for Tidb vector db
2025-05-02 21:28:49 +08:00
yangdx
6021796a61
Fix created_at problem for Qdrant vector db
2025-05-02 16:38:35 +08:00
yangdx
ce96947502
Fix created_at problem for Milvus vector db
2025-05-02 16:31:22 +08:00