4716 Commits

Author SHA1 Message Date
yangdx
b6aedba7ae Add logging for empty naive query results in vector context 2025-08-25 12:21:31 +08:00
yangdx
f1ff5cf93f fix: initialize truncated_chunks variable in _build_query_context
Prevents local variable 'truncated_chunks'referenced before assignment
2025-08-25 11:56:56 +08:00
yangdx
b5682b15cb Remove json-repair from core deps, add missing api deps 2025-08-25 07:23:41 +08:00
Daniel.y
2adbafd6b0
Merge pull request #1999 from thiborose/missingDependencyAOAI
Added import of OpenAILLMOptions when using azure_openai
2025-08-24 10:38:09 +08:00
Thibo Rosemplatt
f5938f76bc Azure OpenAI requires import of OpenAILLMOptions (missing) 2025-08-24 00:28:49 +02:00
yangdx
4e79550725 Merge remote-tracking branch 'origin/main' 2025-08-24 01:08:48 +08:00
yangdx
540a83ea1c Add --use-pep517 flag to all pip install commands in Dockerfile 2025-08-24 01:07:23 +08:00
yangdx
eebc8938ed Update action name 2025-08-24 00:02:57 +08:00
yangdx
a82f126418 Rename github action name 2025-08-23 23:58:33 +08:00
yangdx
8b1e54c8b4 Update Docker workflow name to clarify release trigger
• Clarified workflow purpose
• Added "on Release" to name
2025-08-23 23:55:27 +08:00
yangdx
9a66c944e2 Add Docker build workflow for main branch with manual trigger
- Manual workflow dispatch trigger
- Multi-platform build support
- GHCR registry integration
- Git tag-based versioning
- GitHub Actions cache optimization
2025-08-23 23:50:06 +08:00
yangdx
b815e47f7c Upgrade Python to 3.12 and update pip/setuptools in Dockerfile
• Upgrade base image to Python 3.12
• Update pip, setuptools, wheel
2025-08-23 23:38:39 +08:00
yangdx
bac946fd98 Merge branch 'fix-rerank-example' 2025-08-23 23:07:38 +08:00
yangdx
49ea9a79a7 Update rerank doc in README 2025-08-23 23:06:10 +08:00
yangdx
3d5e6226a9 Refactored rerank_example file to utilize the updated rerank function. 2025-08-23 22:51:41 +08:00
Daniel.y
df4927f837
Merge pull request #1996 from danielaskdd/key-work-empty
feat: Improve Empty Keyword Handling logic
2025-08-23 11:54:26 +08:00
yangdx
9bc349ddd6 Improve Empty Keyword Handling logic 2025-08-23 11:50:58 +08:00
yangdx
1be9a54c8d Rename ENABLE_RERANK to RERANK_BY_DEFAULT and update default to true 2025-08-23 09:46:51 +08:00
yangdx
d29272e6a5 Merge branch 'add-diagnostic-tool' 2025-08-23 02:39:28 +08:00
yangdx
8a293a2c07 Fix linting 2025-08-23 02:39:12 +08:00
yangdx
4595e4b82e Merge branch 'improve-initialization-error-messages' 2025-08-23 02:34:59 +08:00
yangdx
059003c906 Rename allow_create to first_initialization for clarity 2025-08-23 02:34:39 +08:00
yangdx
3b8a540e81 Merge branch 'optimize-reranker' 2025-08-23 02:05:54 +08:00
yangdx
7f404bbecb Update webui assets and bump api version to 0207 2025-08-23 02:05:09 +08:00
yangdx
47485b130d refac(ui): Show rerank binding info on status card
- Remove separate ENABLE_RERANK flag in favor of rerank_binding="null"
- Change default rerank binding from "cohere" to "null" (disabled)
- Update UI to display both rerank binding and model information
2025-08-23 02:04:14 +08:00
yangdx
c15e4e193e Merge branch 'main' of github.com:HKUDS/LightRAG 2025-08-23 01:09:07 +08:00
yangdx
3d5eeedc36 Merge branch 'optimize-reranker' 2025-08-23 01:08:50 +08:00
yangdx
bf43e1b8c1 fix: Resolve default rerank config problem when env var missing
- Read config from selected_rerank_func when env var missing
- Make api_key optional for rerank function
- Add response format validation with proper error handling
- Update Cohere rerank default to official API endpoint
2025-08-23 01:07:59 +08:00
Daniel.y
342992def8
Merge pull request #1993 from danielaskdd/optimize-reranker
feat: Add Multiple Rerank Provider Rerank Support
2025-08-22 19:32:11 +08:00
yangdx
580cb7906c feat: Add multiple rerank provider support to LightRAG Server by adding new env vars and cli params
- Add --enable-rerank CLI argument and ENABLE_RERANK env var
- Simplify rerank configuration logic to only check enable flag and binding
- Update health endpoint to show enable_rerank and rerank_configured status
- Improve logging messages for rerank enable/disable states
- Maintain backward compatibility with default value True
2025-08-22 19:29:45 +08:00
Albert Gil López
3fca3be09b fix: Fix server startup issue with PipelineNotInitializedError
- Add allow_create parameter to get_namespace_data() to permit internal initialization
- initialize_pipeline_status() now uses allow_create=True to create the namespace
- External calls still get the error if pipeline_status is not initialized
- This maintains the improved error messages while allowing proper server startup

Fixes server startup failure reported in PR #1978
2025-08-22 10:55:56 +00:00
Albert Gil López
c66fc3483a fix: Implement PipelineNotInitializedError usage in get_namespace_data
- Add PipelineNotInitializedError import to shared_storage.py
- Raise PipelineNotInitializedError when accessing uninitialized pipeline_status namespace
- This provides clear error messages to users about initialization requirements
- Other namespaces continue to be created dynamically as before

Addresses review feedback from PR #1978 about unused exception class
2025-08-22 02:52:51 +00:00
Albert Gil López
3a64b267cb Merge upstream/main and resolve conflicts 2025-08-21 16:56:11 +00:00
Albert Gil López
ba7b3cedb5 Merge remote-tracking branch 'upstream/main' into add-diagnostic-tool 2025-08-21 16:52:09 +00:00
Daniel.y
0019a3adc6
Merge pull request #1989 from OnesoftQwQ/patch-1
Update README-zh.md
2025-08-21 23:20:21 +08:00
yangdx
16a1ef1178 Update summary_max_tokens default from 10k to 30k tokens 2025-08-21 23:16:07 +08:00
Daniel.y
dce678642a
Merge pull request #1992 from danielaskdd/doc-list-refresh
Fix: Preserve Document List Pagination During Pipeline Status Changes
2025-08-21 23:14:08 +08:00
yangdx
105fb43a54 Updat webui assets and bump api version to 0206 2025-08-21 22:56:44 +08:00
yangdx
ec1bf43667 fix(webui): preserve current page when pipeline status changes
- Add intelligent refresh function to handle boundary cases
- Replace manual refresh with smart page preservation logic
- Auto-redirect to last page when current page becomes invalid
- Maintain user's browsing position during pipeline start/stop
- Fix issue where document list would reset to first page after pipeline operations
2025-08-21 22:53:24 +08:00
Onesoft
b4db084816
Update README-zh.md 2025-08-21 20:01:41 +08:00
yangdx
8c6b5f4a3a Update README 2025-08-21 18:14:27 +08:00
yangdx
718025dbea Update embedding configuration docs and add aws_bedrock option 2025-08-21 17:55:04 +08:00
yangdx
b5c230abdd optimize: avoid duplicate embedding calls in _build_query_context
Reduces API costs and improves query performance while maintaining backward compatibility.
2025-08-21 16:49:24 +08:00
Daniel.y
10bcf1479f
Merge pull request #1987 from danielaskdd/llm-optimization
feat: Support turning off thinking on OpenRouter/vLLM
2025-08-21 15:22:34 +08:00
yangdx
62cdc7d7eb Update documentation with LLM selection guidelines and API improvements 2025-08-21 13:59:14 +08:00
yangdx
4b2ef71c25 feat: Add extra_body parameter support for OpenRouter/vLLM compatibility
- Enhanced add_args function to handle dict types with JSON parsing
- Added reasoning and extra_body parameters for OpenRouter/vLLM compatibility
- Updated env.example with OpenRouter/vLLM parameter examples
2025-08-21 13:06:28 +08:00
yangdx
5d34007f2c Add presence penalty config option for smaller models
- Add OPENAI_LLM_PRESENCE_PENALTY setting
- Recommend 1.5 for Qwen3 <32B params
- Update max completion tokens comment
2025-08-21 11:35:23 +08:00
yangdx
0dd245e847 Add OpenAI reasoning effort and max completion tokens config options 2025-08-21 11:04:06 +08:00
yangdx
0e67ead8fa Rename MAX_TOKENS to SUMMARY_MAX_TOKENS for clarity 2025-08-21 10:15:20 +08:00
yangdx
aa22772721 Refactor LLM temperature handling to be provider-specific
• Remove global temperature parameter
• Add provider-specific temp configs
• Update env example with new settings
• Fix Bedrock temperature handling
• Clean up splash screen display
2025-08-20 23:52:33 +08:00