yangdx
f1d312a2ce
Update UI and refine node property display for compatible with legacy data
2025-03-11 15:54:41 +08:00
zrguo
418aea3895
fix linting
2025-03-11 15:44:01 +08:00
zrguo
62b304600b
clean lightrag.py
2025-03-11 15:43:04 +08:00
yangdx
30310c2845
Fix relation info in kownledge graph UI
2025-03-11 15:36:38 +08:00
zrguo
91f96f2a8b
Merge pull request #1032 from ArindamRoy23/main
...
Filter by ID during Query for Postgres VDB
2025-03-11 15:26:59 +08:00
zrguo
141de28015
Merge pull request #1046 from danielaskdd/fix-extraction-problem
...
Improve Entity Extraction Robustness for Truncated LLM Responses
2025-03-11 15:21:38 +08:00
zrguo
f5f21f6f9b
Merge pull request #1045 from zhenya-zhu/improve_keyword_extraction_prompt
...
force keywords_extraction output as JSON
2025-03-11 15:11:26 +08:00
zrguo
3fb2044273
Merge pull request #1043 from zhicwu/main
...
Resolve the issue with making API calls to Azure OpenAI service
2025-03-11 15:10:03 +08:00
yangdx
9d1dc2c9c3
Fix linting
2025-03-11 12:23:51 +08:00
yangdx
061350b2bf
Improve Entity Extraction Robustness for Truncated LLM Responses
2025-03-11 12:08:10 +08:00
Zhichun Wu
d77401961d
Resolve the issue with making API calls to Azure OpenAI service
2025-03-11 11:57:41 +08:00
Zhenya Zhu
37754f14b5
force keywords_extraction output as JSON
2025-03-11 11:54:30 +08:00
yangdx
7fddabb441
Fix linting
2025-03-11 10:28:25 +08:00
yangdx
aefd596990
Refactor Neo4JStorage to use entity_id for node identification, use entity_type for node label
2025-03-11 09:59:42 +08:00
Roy
92ae895713
Refactor requirements and code formatting
...
- Simplified requirements.txt by removing specific version constraints
- Added comment about extra library installation using pipmaster
- Improved code formatting in base.py, operate.py, and postgres_impl.py
- Cleaned up SQL templates and query method signatures with consistent formatting
2025-03-10 15:39:18 +00:00
zrguo
8317ec9757
Update __init__.py
2025-03-10 23:00:06 +08:00
zrguo
7ed7cb4ecf
Merge pull request #1036 from danielaskdd/neo4j-add-min-degree
...
Refactoring Neo4j implementation and fixing storage init problem for Gunicorn
2025-03-10 22:24:22 +08:00
zrguo
2bf40ab636
Merge branch 'main' into neo4j-add-min-degree
2025-03-10 22:24:06 +08:00
zrguo
2b230d403d
Merge pull request #1011 from ParisNeo/main
...
Added docling option to load files
2025-03-10 22:14:47 +08:00
ArindamRoy23
3fa6d8757a
Merge branch 'HKUDS:main' into main
2025-03-10 19:42:18 +05:30
zrguo
ad13009cff
fix edit_entity
2025-03-10 19:07:19 +08:00
yangdx
bbff3ed0ab
Fix linting
2025-03-10 17:30:40 +08:00
Roy
7807379bee
Remove unused ids parameter from _build_query_context function
2025-03-10 09:18:22 +00:00
yangdx
5d64f3b0a0
Improved auto-scan task initialization and status tracking.
...
- Added autoscan status tracking in pipeline
- Ensured auto-scan runs only once per startup
2025-03-10 17:14:14 +08:00
yangdx
3cca18c59c
Refactor pipeline status updates and entity extraction.
...
- Let all parrallel jobs using one pipe_status objects
- Improved thread safety with pipeline_status_lock
- Only pipeline jobs can add message to pipe_status
- Marked insert_custom_chunks as deprecated
2025-03-10 16:48:59 +08:00
yangdx
57a41eedb8
Fix linting
2025-03-10 15:41:46 +08:00
yangdx
46610682ce
Fix data persistence issue in single-process mode
...
In single-process mode, data updates and persistence were not working properly because the update flags were not being correctly handled between different objects.
2025-03-10 15:41:00 +08:00
yangdx
adca27fae9
Merge branch 'main' into neo4j-add-min-degree
2025-03-10 02:13:49 +08:00
yangdx
4065a7df92
Fix linting
2025-03-10 02:07:19 +08:00
yangdx
14e1b31d1c
Improved logging clarity in storage operations
2025-03-10 02:05:55 +08:00
yangdx
6b0acce644
Avoid redundant llm cache updates
2025-03-10 01:45:58 +08:00
yangdx
d2708b966d
Added update flag to avoid persistence if no data is changed for KV storage
2025-03-10 01:17:25 +08:00
yangdx
4977c718f1
Improve KV storage initialize logic
2025-03-10 00:12:35 +08:00
yangdx
c938989920
Fix llm cache save problem in json_kv storage
2025-03-09 23:33:03 +08:00
yangdx
bc42afe7b6
Unify llm_response_cache and hashing_kv, prevent creating an independent hashing_kv.
2025-03-09 22:15:26 +08:00
Saifeddine ALOUI
04862033d6
Made the defa&ult mode non docling
2025-03-09 13:14:39 +01:00
yangdx
e47883d872
Add atomic data initialization lock to prevent race conditions
2025-03-09 17:33:15 +08:00
yangdx
020a6b5ae0
Refactor LLM cache config to use argparse and add status display
2025-03-09 16:45:57 +08:00
yangdx
c854aabde0
Add process ID to log messages for better multi-process debugging clarity
...
- Add PID to KV and Neo4j storage logs
- Add PID to query context logs
- Improve KV data count logging for llm cache
2025-03-09 15:25:10 +08:00
yangdx
90527875fd
Fix async issues in namespace init
2025-03-09 15:22:06 +08:00
Saifeddine ALOUI
53cfb72db4
linted
2025-03-08 23:07:51 +01:00
Saifeddine ALOUI
4f42b6d933
Merge branch 'HKUDS:main' into main
2025-03-08 23:06:53 +01:00
Roy
4ce28b31bd
minor readme fix
2025-03-08 21:31:41 +00:00
Roy
a1708a2638
Add optional ids filter to QueryParam for RAG document filtering
2025-03-08 21:13:29 +00:00
Roy
d6a426d3e6
Included all requirements in the package
2025-03-08 21:09:45 +00:00
Roy
16536c870c
Commit unncessary files update
2025-03-08 21:06:19 +00:00
Roy
04fdc617bb
main_merge
2025-03-08 20:34:29 +00:00
ArindamRoy23
0695697ad0
Merge pull request #1 from ArindamRoy23/document_query_filter
...
Document query filter
2025-03-09 01:58:04 +05:30
Roy
e31c0c8f6c
Update vector query methods to support ID filtering in PostgreSQL
...
- Modified `mix_kg_vector_query` in operate.py to pass optional IDs to vector search
- Updated PostgreSQL SQL template to filter results using document IDs instead of chunk_id
- Improved query flexibility by allowing precise document selection during vector search
2025-03-08 20:25:20 +00:00
zrguo
32a7d40650
Update lightrag_openai_neo4j_milvus_redis_demo.py
2025-03-09 02:11:31 +08:00
