yangdx
c5d0962872
Fix linting
2025-03-09 01:00:42 +08:00
yangdx
18c0770409
fix: duplicate nodes for same entity(label) problem in Neo4j
...
- Add entity_id field as key in Neo4j nodes
- Use entity_id for nodes retrival and upsert
2025-03-09 00:24:55 +08:00
yangdx
95c06f1bde
Add graph DB lock to shared storage system
...
• Introduced new graph_db_lock
• Added detailed lock debugging output
2025-03-08 22:36:41 +08:00
yangdx
fb4a4c736e
Add duplicate edge upsert checking and logging
2025-03-08 11:36:24 +08:00
yangdx
22a93fb717
Limit neighbor nodes fetch to 1000 in Neo4JStorage.
2025-03-08 11:29:08 +08:00
yangdx
887f6ed81a
Fix return empty list when no edges is found
2025-03-08 11:20:22 +08:00
yangdx
af26d65698
Convert _ensure_label method from async to sync
2025-03-08 10:23:27 +08:00
yangdx
78f8d7a1ce
Convert node and edge IDs to f-strings for consistency.
...
- Use f-strings for node IDs
- Use f-strings for edge IDs
- Ensure consistent ID formatting
2025-03-08 10:20:10 +08:00
yangdx
84222b8b76
Refactor Neo4JStorage methods for robustness and clarity.
...
- Add error handling and resource cleanup
- Improve method documentation
- Optimize result consumption
2025-03-08 10:19:20 +08:00
yangdx
fcb04e47e5
Refactor Neo4J APOC fall back retrival implementaion
2025-03-08 04:28:54 +08:00
yangdx
c07b592e1b
Add missing await consume
2025-03-08 02:39:51 +08:00
yangdx
af803f4e7a
Refactor Neo4J graph query with min_degree an inclusive match support
2025-03-08 01:20:36 +08:00
yangdx
0ee2e7fd48
Suppress Neo4j warning logs by setting logger level.
2025-03-07 16:56:48 +08:00
yangdx
6e3b23069c
- Remove useless _label_exists method
2025-03-07 16:43:18 +08:00
yangdx
6d5c04d561
Reduce max_depth and update edge type in NetworkXStorage.
...
- Decreased max_depth from 5 to 3
- Changed edge type from "RELATED" to "DIRECTED"
2025-03-06 20:54:02 +08:00
yangdx
5b29e760f0
Add dynamic parameter handling for storage
2025-03-06 14:29:48 +08:00
yangdx
252d1f57e0
Merge branch 'main' into add-graph-search-mode
2025-03-06 10:23:38 +08:00
yangdx
0ca7c0e230
Fix linting
2025-03-05 15:07:11 +08:00
yangdx
4e2a9b1994
Apply min_degree filter for full graph query
2025-03-05 13:21:17 +08:00
yangdx
ca9e958cad
Fix subgraph filtering bugs
2025-03-05 13:13:46 +08:00
yangdx
5f12aa3ee4
Fix linting
2025-03-05 12:32:23 +08:00
yangdx
5e40e4107d
Added min_degree exception for connected nodes
2025-03-05 11:48:04 +08:00
yangdx
1fddc8552e
Added minimum degree filter for graph queries
...
- Introduced min_degree parameter in graph query
- Updated UI to include minimum degree setting
- Modified API to handle min_degree parameter
- Updated graph query logic in LightRAG
2025-03-05 11:37:55 +08:00
zrguo
1ee6c23a53
fix linting
2025-03-04 16:12:27 +08:00
zrguo
4ebaf8026b
Update oracle_impl.py
2025-03-04 16:11:13 +08:00
yangdx
002948d342
Added search mode and min degree filtering for NetworkX
...
- Implemented exact and inclusive search modes
- Added min degree filtering for nodes
- Updated API to parse label for search options
2025-03-04 16:08:05 +08:00
zrguo
81568f3bad
fix linting
2025-03-04 15:53:20 +08:00
zrguo
3a2a636862
Implement the missing methods.
2025-03-04 15:50:53 +08:00
zrguo
0679ca4055
Update neo4j_impl.py
2025-03-04 14:20:55 +08:00
zrguo
fd9f71e0ee
fix delete_by_doc_id
2025-03-04 13:22:33 +08:00
yangdx
11fdb60fe5
Remove Chinese comments
2025-03-03 01:30:41 +08:00
yangdx
465737efed
Fix linting
2025-03-02 17:32:25 +08:00
yangdx
68bf02abb6
refactor: improve graph querying with label substring matching and security fixes
2025-03-02 16:20:37 +08:00
yangdx
0f1eb42c8d
Add node limit and prioritization for knowledge graph retrieval
...
• Add MAX_GRAPH_NODES limit from env var
• Prioritize nodes by label match & connection
2025-03-02 15:39:14 +08:00
yangdx
1ca6837219
Add max nodes limit for graph retrieval of networkX
...
• Set MAX_GRAPH_NODES env var (default 1000)
• Change edge type to "RELATED"
2025-03-02 12:52:25 +08:00
yangdx
c0b22a8ae2
Merge branch 'main' into add-multi-worker-support
2025-03-02 02:54:57 +08:00
yangdx
7cd25fe5ab
Improve shared storage cleanup and clarify initialization in multi-worker setup
2025-03-02 01:00:27 +08:00
yangdx
e8d0d065f3
fix: Improve async handling and FAISS storage reliability
...
- Add async context manager support
- Fix embedding data type conversion
- Improve error handling in FAISS ops
- Add multiprocess storage sync
2025-03-01 23:35:09 +08:00
yangdx
9aef112d51
Fix incorrect comment about update flag behavior in FAISS implementation
2025-03-01 22:27:12 +08:00
zrguo
4219454fab
fix format
2025-03-01 17:45:06 +08:00
yangdx
e3a40c2fdb
Fix linting
2025-03-01 16:23:34 +08:00
yangdx
d18eb52ccc
Add type ignore comments for asyncpg imports to suppress mypy errors
2025-03-01 15:38:39 +08:00
yangdx
40e9e26edb
feat: add update flags status to API health endpoint
2025-03-01 14:58:26 +08:00
yangdx
41eff2ca2f
Fix data persistence issue in NanoVectorDBStorage
2025-03-01 13:35:00 +08:00
yangdx
35bcfca28f
feat: add multi-process support for FAISS vector storage
...
• Add storage update flag and locks
• Support cross-process index reload
• Add async initialize method
2025-03-01 12:42:30 +08:00
yangdx
d4f6dcfd54
Improve multi-process data synchronization and persistence in storage implementations
...
• Remove _get_client() or _get_graph() from index_done_callback
• Add return value for index_done_callback
2025-03-01 12:41:30 +08:00
yangdx
c07a5039b7
Refactor shared storage locks to separate pipeline, storage and internal locks for deadlock preventing
2025-03-01 10:48:55 +08:00
yangdx
d3de57c1e4
Add multi-process support for vector database and graph storage with lock flags
...
• Implement storage lock mechanism
• Add update flag handling
• Add cross-process reload detection
2025-03-01 10:37:05 +08:00
yangdx
d704512139
Refactor shared storage module to improve async handling and naming consistency
...
• Add async support for get_namespace_data
• Rename get_update_flags to get_update_flag
• Rename set_update_flag to set_all_update_flags
• Update docstrings for clarity
• Fix typos in log messages
2025-03-01 05:01:26 +08:00
yangdx
fd76e00c6a
Refactor storage initialization to separate object creation from data loading
...
• Split __post_init__ and initialize()
• Move data loading to initialize()
• Add FastAPI lifespan integration
2025-03-01 03:48:19 +08:00
