Commit Graph

2005 Commits

Author SHA1 Message Date
ArnoChen
cf7c45b5dd format 2025-02-17 01:05:48 +08:00
ArnoChen
c2a7079392 finish document manager 2025-02-17 01:05:31 +08:00
ArnoChen
be4cdedfa1 add API tab to display backend documentation 2025-02-17 01:04:14 +08:00
ArnoChen
ca85b82a47 implement endpoint to retrieve document statuses 2025-02-17 01:03:24 +08:00
Yannick Stephan
87a13fd3ea cleaned code 2025-02-16 16:22:28 +01:00
Yannick Stephan
0b16718f9f add missing final 2025-02-16 16:21:28 +01:00
Yannick Stephan
49bea486a7 cleaned code 2025-02-16 16:04:35 +01:00
Yannick Stephan
2b2c81a722 added some comments 2025-02-16 16:04:07 +01:00
Yannick Stephan
abad9f235c make value on str enum 2025-02-16 15:54:54 +01:00
yangdx
9ec920661d Improve token estimation accuracy by using tiktoken instead of regex-based approach
• Replace regex token estimation method
• Use tiktoken for more precise counting
• Support all types of text input
• Simplify code implementation
2025-02-16 22:53:58 +08:00
Yannick Stephan
2bf238396e updated wrong status 2025-02-16 15:52:59 +01:00
yangdx
b450430109 Change log level from info to debug for token count logging 2025-02-16 22:42:53 +08:00
yangdx
8f6e9fcf50 Merge branch 'main' into add-env-settings 2025-02-16 22:34:39 +08:00
yangdx
cfb49fc013 Delete inline comment about config.ini 2025-02-16 22:31:12 +08:00
Yannick Stephan
a1607bbcb9 Merge remote-tracking branch 'origin/main' into make-clear-what-implemented-or-not
# Conflicts:
#	lightrag/base.py
#	lightrag/kg/json_doc_status_impl.py
#	lightrag/kg/mongo_impl.py
#	lightrag/kg/postgres_impl.py
2025-02-16 15:29:16 +01:00
Yannick Stephan
0c21442ca4 fixed default init 2025-02-16 15:20:46 +01:00
ArnoChen
801a980c03 Merge branch 'main' into light-webui 2025-02-16 22:09:18 +08:00
Yannick Stephan
0e7aff96bb back to not making breaks 2025-02-16 15:08:50 +01:00
zrguo
200319f293 Merge pull request #791 from ArnoChenFx/refactor-server
Refactor File Indexing for Background Asynchronous Processing
2025-02-16 22:07:30 +08:00
ArnoChen
e5b89c5400 fix retrieval testing and query settings 2025-02-16 21:58:30 +08:00
Yannick Stephan
0a8c94a1e0 fix value 2025-02-16 14:51:24 +01:00
Yannick Stephan
9a5fbaaa5f removed unused methods 2025-02-16 14:50:04 +01:00
Yannick Stephan
a0844bca28 cleaned import 2025-02-16 14:45:45 +01:00
ArnoChen
fc3ca2777f add query settings 2025-02-16 21:43:14 +08:00
Yannick Stephan
3fef8201c6 added final, required methods and cleaned import 2025-02-16 14:38:09 +01:00
ArnoChen
893b645506 unify doc status retrieval with get_docs_by_status 2025-02-16 21:28:58 +08:00
yangdx
41cbecdbe6 Add token size limit truncation for node data retrieval
• Add truncate_list_by_token_size function
• Limit max tokens for local context
• Add logging for truncation info
• Apply truncation to node_datas list
2025-02-16 21:26:29 +08:00
ArnoChen
b580e47324 format 2025-02-16 21:20:43 +08:00
ArnoChen
1a6c6f30a1 Merge remote-tracking branch 'origin/main' into refactor-server
# Conflicts:
#	lightrag/api/lightrag_server.py
2025-02-16 21:19:30 +08:00
Yannick Stephan
7848a38a45 added all abstractmethod 2025-02-16 14:11:19 +01:00
ArnoChen
bbe24ab7ce enhance query and indexing with pipeline 2025-02-16 21:11:05 +08:00
Yannick Stephan
931c31fa8c cleaned code 2025-02-16 13:55:30 +01:00
Yannick Stephan
882190a515 updated clean of what implemented on DocStatusStorage 2025-02-16 13:53:59 +01:00
zrguo
2a0c7c0322 Merge pull request #785 from danielaskdd/improve-CORS-handling
improve CORS and streaming response headers
2025-02-16 20:31:33 +08:00
Yannick Stephan
71a18d1de9 updated clean of what implemented on BaseKVStorage 2025-02-16 13:31:12 +01:00
Yannick Stephan
3eba41aab6 updated clean of what implemented on BaseVectorStorage 2025-02-16 13:24:42 +01:00
yangdx
7f13b779e1 Fix linting 2025-02-16 20:15:14 +08:00
yangdx
4e354451b7 Fix load_dotenv() missing problem for base.py 2025-02-16 20:05:45 +08:00
zrguo
ef0e81315f fix linting 2025-02-16 19:53:28 +08:00
zrguo
517ceb16fa Merge pull request #794 from St1veLiu/main
Update json_kv_impl.py
2025-02-16 19:51:43 +08:00
zrguo
31f14cf505 Merge pull request #793 from VeiledTee/patch-1
Update HuggingFace example in README.md
2025-02-16 19:49:05 +08:00
yangdx
36ff0bfa85 Improve logging message clarity by including max tokens info for truncation 2025-02-16 19:47:20 +08:00
zrguo
07178f6c2c Merge pull request #782 from YanSte/code-cleaning
Code Cleanup & Maintenance Improvements
2025-02-16 19:46:42 +08:00
Yannick Stephan
1051ff402d fixed lint 2025-02-16 12:45:27 +01:00
zrguo
f868c1da78 Merge branch 'main' into code-cleaning 2025-02-16 19:41:05 +08:00
zrguo
9ba3279424 Merge pull request #784 from YanSte/improve-docker
Improve .gitignore and .dockerignore
2025-02-16 19:37:41 +08:00
St1ve
edaba428ac Update json_kv_impl.py
There is no delete function in chunks_vdb and text_chunks in lines 1300-1302 of the lightrag.py file:
    if chunk_ids:
                await self.chunks_vdb.delete(chunk_ids)
                await self.text_chunks.delete(chunk_ids)
2025-02-16 19:33:59 +08:00
zrguo
5189a9438c Merge pull request #780 from spo0nman/fix-bug-778
Enhance Neo4j graph storage with error handling and label validation
2025-02-16 19:30:32 +08:00
yangdx
601df31edf feat: move query-related settings to env file for better configuration
• Add env vars for token and chunk settings
• Add token count logging for prompts
• Add token count logging for context
• Move hardcoded values to env variables
• Improve logging clarity and consistency
2025-02-16 19:26:57 +08:00
zrguo
292b65320a Merge pull request #781 from ArnoChenFx/enhance-mongodb-backends
Add MongoDB VectorDB Support and Optimize Existing MongoDB Implementations
2025-02-16 19:26:35 +08:00