gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
5950 commits 5 branches 72 tags 705 MiB
Commit graph

5950 commits

This branch
This branch
All branches
Author SHA1 Message Date
chaohuang-ai
5c9642675b
Update README.md 2025-11-30 00:17:04 +08:00
Christian Clauss
d2ab7fb246
Add Python 3.13 and 3.14 to the testing 2025-11-28 16:15:16 +01:00
Christian Clauss
90e38c20ca
Keep GitHub Actions up to date with GitHub's Dependabot 
* [Keeping your software supply chain secure with Dependabot](https://docs.github.com/en/code-security/dependabot)
* [Keeping your actions up to date with Dependabot](https://docs.github.com/en/code-security/dependabot/working-with-dependabot/keeping-your-actions-up-to-date-with-dependabot)
* [Configuration options for the `dependabot.yml` file - package-ecosystem](https://docs.github.com/en/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file#package-ecosystem)

To see all GitHub Actions dependencies, type:
% `git grep 'uses: ' .github/workflows/`
 2025-11-28 15:04:53 +01:00
Daniel.y
8eb63d9bad
Merge pull request #2434 from cclauss/patch-1 
Fix typos discovered by codespell
 2025-11-28 21:59:29 +08:00
Daniel.y
b670544958
Merge pull request #2433 from danielaskdd/fix-jina-embedding 
Fix: Add configurable model support for Jina embedding
 2025-11-28 19:36:18 +08:00
yangdx
ea8d55ab42 Add documentation for embedding provider configuration rules 2025-11-28 17:49:30 +08:00
Christian Clauss
90f341d614
Fix typos discovered by codespell 2025-11-28 10:31:52 +01:00
yangdx
4ab4a7ac94 Allow embedding models to use provider defaults when unspecified 
- Set EMBEDDING_MODEL default to None
- Pass model param only when provided
- Let providers use their own defaults
- Fix lollms embed function params
- Add ollama embed_model default param
 2025-11-28 16:57:33 +08:00
yangdx
881b8d3a50 Bump API version to 0257 2025-11-28 15:39:55 +08:00
yangdx
56e0365cf0 Add configurable model parameter to jina_embed function 
- Add model parameter to jina_embed
- Pass model from API server
- Default to jina-embeddings-v4
- Update function documentation
- Make model selection flexible
 2025-11-28 15:38:29 +08:00
Daniel.y
1b02684e2f
Merge pull request #2432 from danielaskdd/embedding-example 
Doc: Update README examples to prevent double-wrapping of embedding functions
 2025-11-28 15:24:52 +08:00
yangdx
97a9dfcac0 Add important note about embedding function wrapping restrictions 2025-11-28 14:55:15 +08:00
yangdx
1d07ff7f60 Update OpenAI and Ollama embedding func examples in README 2025-11-28 14:41:29 +08:00
yangdx
6e2946e78a Add max_token_size parameter to azure_openai_embed wrapper 2025-11-28 13:41:01 +08:00
yangdx
4f12fe121d Change entity extraction logging from warning to info level 
• Reduce log noise for empty entities
 2025-11-27 11:00:34 +08:00
Ghazi-raad
4e8e08cf4d
Update lightrag/operate.py 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-11-26 23:18:20 +00:00
Ghazi-raad
56677ae466
Update lightrag/prompt.py 
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-11-26 23:18:12 +00:00
Ghazi-raad
207af40f54 Optimize for OpenAI Prompt Caching: Restructure entity extraction prompts 
- Remove input_text from entity_extraction_system_prompt to enable caching
- Move input_text to entity_extraction_user_prompt for per-chunk variability
- Update operate.py to format system prompt once without input_text
- Format user prompts with input_text for each chunk

This enables OpenAI's automatic prompt caching (50% discount on cached tokens):
- ~1300 token system message cached and reused for ALL chunks
- Only ~150 token user message varies per chunk
- Expected 45% cost reduction on prompt tokens during indexing
- 2-3x faster response times from cached prompts

Fixes #2355
 2025-11-26 21:56:25 +00:00
palanisd
a898f0548d
Merge branch 'HKUDS:main' into cohere-rerank 2025-11-25 14:21:43 -05:00
yangdx
93d445dfdd Add pipeline status lock function for legacy compatibility 
- Add get_pipeline_status_lock function
- Return NamespaceLock for consistency
- Support workspace parameter
- Enable logging option
- Legacy code compatibility
 2025-11-25 18:24:39 +08:00
Daniel.y
d2cd1c0722
Merge pull request #2421 from EightyOliveira/fix_catch_order 
fix:exception handling order error
 2025-11-25 17:52:56 +08:00
yangdx
777c91794b Add Langfuse observability configuration to env.example 
- Add Langfuse environment variables
- Include setup instructions
- Support OpenAI compatible APIs
- Enable tracing configuration
- Add cloud/self-host options
 2025-11-25 17:16:55 +08:00
EightyOliveira
8994c70f2f fix:exception handling order error 2025-11-25 16:36:41 +08:00
Daniel.y
2539b4e2c8
Merge pull request #2418 from danielaskdd/start-without-webui 
Refact: Allow API Server to Start Without Built WebUI Assets
 2025-11-25 03:02:15 +08:00
yangdx
48b67d3077 Handle missing WebUI assets gracefully without blocking server startup 
- Change build check from error to warning
- Redirect to /docs when WebUI unavailable
- Add webui_available to health endpoint
- Only mount /webui if assets exist
- Return status tuple from build check
 2025-11-25 02:51:55 +08:00
Daniel.y
2832a2ca7e
Merge pull request #2417 from danielaskdd/neo4j-retry 
Fix: Add Comprehensive Retry Mechanism for Neo4j Storage Operations
 2025-11-25 02:03:48 +08:00
yangdx
5f91063c7a Add ruff as dependency to pytest and evaluation extras 2025-11-25 02:03:28 +08:00
yangdx
8c4d7a00ad Refactor: Extract retry decorator to reduce code duplication in Neo4J storage 
• Define READ_RETRY_EXCEPTIONS constant
• Create reusable READ_RETRY decorator
• Replace 11 duplicate retry decorators
• Improve code maintainability
• Add missing retry to edge_degrees_batch
 2025-11-25 01:35:21 +08:00
Daniel.y
5b81ef000e
Merge pull request #2410 from netbrah/create-copilot-setup-steps 
feat: create copilot-setup-steps.yml
 2025-11-24 22:36:33 +08:00
yangdx
7aaa51cda9 Add retry decorators to Neo4j read operations for resilience 2025-11-24 22:28:15 +08:00
palanisd
dd18eb5b9c
Merge pull request #3 from netbrah/copilot/fix-overlap-tokens-validation 
Fix infinite loop in chunk_documents_for_rerank when overlap_tokens >= max_tokens
 2025-11-24 09:11:24 -05:00
copilot-swe-agent[bot]
8835fc244a Improve edge case handling for max_tokens=1 
Co-authored-by: netbrah <162479981+netbrah@users.noreply.github.com>
 2025-11-24 03:43:05 +00:00
copilot-swe-agent[bot]
1d6ea0c5f7 Fix chunking infinite loop when overlap_tokens >= max_tokens 
Co-authored-by: netbrah <162479981+netbrah@users.noreply.github.com>
 2025-11-24 03:40:58 +00:00
copilot-swe-agent[bot]
e136da968b Initial plan 2025-11-24 03:33:26 +00:00
palanisd
c233da6318
Update copilot-setup-steps.yml 2025-11-23 17:42:04 -05:00
netbrah
a05bbf105e Add Cohere reranker config, chunking, and tests 2025-11-22 16:43:13 -05:00
palanisd
1b0413ee74
Create copilot-setup-steps.yml 2025-11-22 15:29:05 -05:00
chaohuang-ai
16eb0d5bee
Merge pull request #2409 from HKUDS/chaohuang-ai-patch-3 
Update README.md
 2025-11-23 00:54:04 +08:00
chaohuang-ai
37178462ab
Update README.md 2025-11-23 00:53:39 +08:00
chaohuang-ai
6d3bfe46d0
Merge pull request #2408 from HKUDS/chaohuang-ai-patch-2 
Update README.md
 2025-11-23 00:50:16 +08:00
chaohuang-ai
babbcb566b
Update README.md 2025-11-23 00:48:52 +08:00
yangdx
5f53de8866 Fix Azure configuration examples and correct typos in env.example 2025-11-22 09:05:52 +08:00
yangdx
fa6797f246 Update env.example 2025-11-22 00:32:12 +08:00
yangdx
49fb11e205 Update Azure OpenAI configuration examples 2025-11-22 00:19:23 +08:00
yangdx
7b76211066 Add fallback to AZURE_OPENAI_API_VERSION for embedding API version 2025-11-22 00:14:35 +08:00
yangdx
ffd8da512e Improve Azure OpenAI compatibility and error handling 
• Reduce log noise for Azure content filters
• Add default API version fallback
• Change warning to debug log level
• Handle empty choices in streaming
• Better Azure OpenAI integration
 2025-11-21 23:51:18 +08:00
yangdx
fafa1791f4 Fix Azure OpenAI model parameter to use deployment name consistently 
- Use deployment name for Azure API calls
- Fix model param in embed function
- Consistent api_model logic
- Prevent Azure model name conflicts
 2025-11-21 23:41:52 +08:00
Daniel.y
021b637dc3
Merge pull request #2403 from danielaskdd/azure-cot-handling 
Refact: Consolidate Azure OpenAI and OpenAI implementations
 2025-11-21 19:36:12 +08:00
yangdx
ac9f2574a5 Improve Azure OpenAI wrapper functions with full parameter support 
• Add missing parameters to wrappers
• Update docstrings for clarity
• Ensure API consistency
• Fix parameter forwarding
• Maintain backward compatibility
 2025-11-21 19:24:32 +08:00
yangdx
45f4f82392 Refactor Azure OpenAI client creation to support client_configs merging 
- Handle None client_configs case
- Merge configs with explicit params
- Override client_configs with params
- Use dict unpacking for client init
- Maintain parameter precedence
 2025-11-21 19:14:16 +08:00