gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
4393 commits 5 branches 72 tags 705 MiB
Commit graph

2806 commits

Author SHA1 Message Date
yangdx
ee53e43568 Update webui assets 2025-07-28 02:52:32 +08:00
yangdx
769f77ef8f Update webui assets 2025-07-28 02:26:07 +08:00
yangdx
98ac6fb3f0 Bump api version to 0192 2025-07-28 01:42:51 +08:00
yangdx
f2ffff063b feat: refactor ollama server configuration management 
- Add ollama_server_infos attribute to LightRAG class with default initialization
- Move default values to constants.py for centralized configuration
- Refactor OllamaServerInfos class with property accessors and CLI support
- Update OllamaAPI to get configuration through rag object instead of direct import
- Add command line arguments for simulated model name and tag
- Fix type imports to avoid circular dependencies
 2025-07-28 01:38:35 +08:00
yangdx
598eecd06d Refactor: Rename llm_model_max_token_size to summary_max_tokens 
This commit renames the parameter 'llm_model_max_token_size' to 'summary_max_tokens' for better clarity, as it specifically controls the token limit for entity relation summaries.
 2025-07-28 00:49:08 +08:00
yangdx
d0d57a45b6 feat: add environment variables to /health endpoint and centralize defaults 
- Add 9 environment variables to /health endpoint configuration section
- Centralize default constants in lightrag/constants.py for consistency
- Update config.py to use centralized defaults for better maintainability
 2025-07-28 00:30:56 +08:00
yangdx
9c4e98ec3b Unify entity extraction prompt between passes 
- Disallow hallucinated info in descriptions
- Align reminder steps with main extraction
 2025-07-27 23:06:55 +08:00
Daniel.y
4eef9f3778
Merge pull request #1845 from AkosLukacs/patch-2 
Better prompt for entity description extraction to avoid hallucinations
 2025-07-27 22:38:08 +08:00
yangdx
3951a44666 Revert file_path build method, built from related chunks 2025-07-27 21:56:20 +08:00
yangdx
d70c584d80 Bump api version to 0191 2025-07-27 21:24:53 +08:00
yangdx
f2d051eea5 Fix: Improve keyword extraction prompt for robust JSON output. 
*   Emphasize strict JSON output in key extration prompt
*   Clean up prompt examples in key extration prompt
*   Log raw LLM response on JSON error
 2025-07-27 21:10:47 +08:00
yangdx
3f5ade47cd Update README 2025-07-27 17:26:49 +08:00
yangdx
e09929b42e Refine rerank filtering log message for clarity 2025-07-27 16:57:38 +08:00
yangdx
f4bca7bfb2 Fix linting 2025-07-27 16:50:45 +08:00
yangdx
a9565d7379 feat: Skip rerank filtering when min_rerank_score is 0.0 2025-07-27 16:50:12 +08:00
yangdx
ebaff228aa feat: Add rerank score filtering with configurable threshold 
- Add DEFAULT_MIN_RERANK_SCORE constant (default: 0.0)
- Add MIN_RERANK_SCORE environment variable support
- Filter chunks with rerank scores below threshold in process_chunks_unified
- Add info-level logging for filtering operations
- Handle empty results gracefully after filtering
- Maintain backward compatibility with non-reranked chunks
 2025-07-27 16:37:44 +08:00
yangdx
99e3812c38 refactor: unify file_path handling across merge and rebuild functions 
- Replace simple string concatenation with build_file_path() in:
  - _merge_edges_then_upsert
  - _rebuild_single_entity
  - _rebuild_single_relationship
- Ensures consistent deduplication, length limiting, and error handling
- Aligns with existing _merge_nodes_then_upsert implementation
 2025-07-27 12:37:24 +08:00
yangdx
cf1ca39b3f Refine entity continuation prompt to avoid duplicates. 
- Clarify finding missing entities
- Instruct not to repeat extractions
 2025-07-27 10:48:29 +08:00
yangdx
0dfbce0bb4 Update the README to clarify the explanation of concurrent processes. 2025-07-27 10:39:28 +08:00
yangdx
055629d30d Reduce default max total tokens to 30k 2025-07-27 10:33:06 +08:00
yangdx
a67f93acc9 Replace hardcoded max tokens with DEFAULT_MAX_TOTAL_TOKENS constant 
- Use constant in process_chunks_unified
- Update WebUI default to match (32000)
 2025-07-26 11:23:54 +08:00
yangdx
7b915b34f6 Refactor: move build_file_path function from operate.py to utils.py 2025-07-26 10:52:59 +08:00
yangdx
c8c3545454 refactor: extract file path length limit to shared constant 
• Add DEFAULT_MAX_FILE_PATH_LENGTH constant
• Replace hardcoded 4090 in Milvus impl
 2025-07-26 10:45:03 +08:00
yangdx
8e7014d366 Merge branch 'separator_file_path' 2025-07-26 10:39:03 +08:00
yangdx
a943265257 fix: preserve file path order in build_file_path function 2025-07-26 10:21:32 +08:00
yangdx
6efa8ab263 Improve file path length warning message clarity and urgency 
• Change debug to warning level
• Simplify message wording
 2025-07-26 10:00:18 +08:00
yangdx
e7baf54ec2 Update webui assets 2025-07-26 08:43:12 +08:00
xuewei
56c3cb2dbe Improve build_file_path log 2025-07-26 08:38:02 +08:00
okxuewei
912fc0fc31
Merge branch 'HKUDS:main' into separator_file_path 2025-07-26 08:17:35 +08:00
yangdx
b3c2987006 Reduce default MAX_TOKENS from 32000 to 10000 2025-07-26 08:13:49 +08:00
xuewei
a49b7758e1 Merge branch 'main' of https://github.com/okxuewei/LightRAG into separator_file_path 2025-07-26 00:47:48 +08:00
xuewei
b4da3de7d9 Improve file_path drop policy 2025-07-26 00:46:02 +08:00
xuewei
55e2678a1e Improve file_path FieldSchema 4090 2025-07-26 00:22:25 +08:00
yangdx
6a99d7ac28 Update webui assets 2025-07-25 22:03:58 +08:00
yangdx
4ae44bb24b Bump core version to 1.4.5 and api version to 0190 2025-07-25 11:15:04 +08:00
yangdx
983bacd87e Update logger messages 2025-07-24 16:49:28 +08:00
yangdx
bf58c73c3f Update webui assets 2025-07-24 16:48:45 +08:00
yangdx
44b7ce222e feat: add default storage dependencies and optimize imports 
- Add nano-vectordb and networkx to pyproject.toml dependencies
- Replace dynamic imports with direct imports for 4 default storage implementations
- Improve startup performance while maintaining backward compatibility
 2025-07-24 16:14:26 +08:00
yangdx
51231c7647 Update README 2025-07-24 15:48:49 +08:00
yangdx
5437509824 Bump api version to 0189 2025-07-24 14:07:48 +08:00
yangdx
f57ed21593 Merge branch 'main' into context-builder 2025-07-24 14:07:05 +08:00
yangdx
5574a30856 fix(postgres): handle ssl_mode="allow" in _create_ssl_context 
Add "allow" to the list of recognized SSL modes in PostgreSQL connection helper. Previously, ssl_mode="allow" would fall through to "Unknown SSL mode" warning. Now it's properly handled alongside "require" and "prefer" modes.
 2025-07-24 12:45:13 +08:00
yangdx
d8e7b77099 Bump api version to 0188 2025-07-24 12:27:30 +08:00
yangdx
2767212ba0 Fix linting 2025-07-24 12:25:50 +08:00
yangdx
d979e9078f feat: Integrate Jina embeddings API support 
- Implemented Jina embedding function
- Add new EMBEDDING_BINDING type of jina for LightRAG Server
- Add env var sample
 2025-07-24 12:15:00 +08:00
yangdx
d78fda1d89 Optimize logger message 2025-07-24 04:31:06 +08:00
yangdx
baad473b67 Bump api version to 0188 2025-07-24 04:00:43 +08:00
yangdx
d97913873b Update logger message 2025-07-24 03:44:02 +08:00
yangdx
3075691f72 Refactor: move reranking utilities from operate.py to utils.py 
• Move apply_rerank_if_enabled to utils
• Move process_chunks_unified to utils
 2025-07-24 03:33:38 +08:00
yangdx
2c940f0728 reduce RELATED_CHUNK_NUMBER from 10 to 5 2025-07-24 02:49:05 +08:00