12 KiB
12 KiB
| 1 | commit | auth_date | author | subject | category | priority_idx | git_cherry_pick_cmd |
|---|---|---|---|---|---|---|---|
| 2 | ec40b17e | 2025-10-08 | Yasiru | Rangana feat: Add token tracking support to openai_embed function | embedding | 8 | git cherry-pick ec40b17e |
| 3 | 0f15fdc3 | 2025-10-09 | Daniel.y | Merge pull request #2181 from yrangana/feat/openai-embedding-token-tracking | embedding | 8 | git cherry-pick 0f15fdc3 |
| 4 | 6d1ae404 | 2025-10-15 | yangdx | Add offline Docker build support with embedded models and cache | embedding | 8 | git cherry-pick 6d1ae404 |
| 5 | 6a29b5da | 2025-10-23 | yangdx | Update Docker deployment comments for LLM and embedding hosts | embedding | 8 | git cherry-pick 6a29b5da |
| 6 | 7b8223da | 2025-11-03 | yangdx | Update env.example with host/endpoint clarifications for LLM/embedding | embedding | 8 | git cherry-pick 7b8223da |
| 7 | 9c057060 | 2025-11-05 | yangdx | Add separate endpoint configuration for LLM and embeddings in evaluation | embedding | 8 | git cherry-pick 9c057060 |
| 8 | 01b07b2b | 2025-11-07 | yangdx | Refactor Jina embedding dimension by changing param to optional with default | embedding | 8 | git cherry-pick 01b07b2b |
| 9 | 33a1482f | 2025-11-07 | yangdx | Add optional embedding dimension parameter control via env var | embedding | 8 | git cherry-pick 33a1482f |
| 10 | 9cee5a63 | 2025-11-07 | yangdx | Merge branch 'main' into apply-dim-to-embedding-call | embedding | 8 | git cherry-pick 9cee5a63 |
| 11 | ce28f30c | 2025-11-07 | yangdx | Add embedding_dim parameter support to embedding functions | embedding | 8 | git cherry-pick ce28f30c |
| 12 | d8a6355e | 2025-11-07 | yangdx | Merge branch 'main' into apply-dim-to-embedding-call | embedding | 8 | git cherry-pick d8a6355e |
| 13 | d94aae9c | 2025-11-07 | Yasiru | Rangana Add dimensions parameter support to openai_embed() | embedding | 8 | git cherry-pick d94aae9c |
| 14 | ffeeae42 | 2025-11-07 | yangdx | refactor: simplify jina embedding dimension handling | embedding | 8 | git cherry-pick ffeeae42 |
| 15 | 03cc6262 | 2025-11-08 | yangdx | Prohibit direct access to internal functions of EmbeddingFunc. | embedding | 8 | git cherry-pick 03cc6262 |
| 16 | 0b2a15c4 | 2025-11-08 | yangdx | Centralize embedding_send_dim config through args instead of env var | embedding | 8 | git cherry-pick 0b2a15c4 |
| 17 | 29a349f2 | 2025-11-08 | Daniel.y | Merge pull request #2329 from danielaskdd/gemini-embedding | embedding | 8 | git cherry-pick 29a349f2 |
| 18 | a624a950 | 2025-11-08 | yangdx | Add Gemini to APIs requiring embedding dimension parameter | embedding | 8 | git cherry-pick a624a950 |
| 19 | de4ed736 | 2025-11-08 | yangdx | Add Gemini embedding support | embedding | 8 | git cherry-pick de4ed736 |
| 20 | f4492d48 | 2025-11-08 | Daniel.y | Merge pull request #2328 from HKUDS/apply-dim-to-embedding-call | embedding | 8 | git cherry-pick f4492d48 |
| 21 | 05852e1a | 2025-11-14 | yangdx | Add max_token_size parameter to embedding function decorators | embedding | 8 | git cherry-pick 05852e1a |
| 22 | 14a6c24e | 2025-11-14 | yangdx | Add configurable embedding token limit with validation | embedding | 8 | git cherry-pick 14a6c24e |
| 23 | 2fb57e76 | 2025-11-14 | yangdx | Fix embedding token limit initialization order | embedding | 8 | git cherry-pick 2fb57e76 |
| 24 | 39b49e92 | 2025-11-14 | yangdx | Convert embedding_token_limit from property to field with __post_init__ | embedding | 8 | git cherry-pick 39b49e92 |
| 25 | 5dec4dea | 2025-11-14 | yangdx | Improve embedding config priority and add debug logging | embedding | 8 | git cherry-pick 5dec4dea |
| 26 | 6b2af2b5 | 2025-11-14 | yangdx | Refactor embedding function creation with proper attribute inheritance | embedding | 8 | git cherry-pick 6b2af2b5 |
| 27 | 77221564 | 2025-11-14 | yangdx | Add max_token_size parameter to embedding function decorators | embedding | 8 | git cherry-pick 77221564 |
| 28 | 963a0a5d | 2025-11-14 | yangdx | Refactor embedding function creation with proper attribute inheritance | embedding | 8 | git cherry-pick 963a0a5d |
| 29 | ab4d7ac2 | 2025-11-14 | yangdx | Add configurable embedding token limit with validation | embedding | 8 | git cherry-pick ab4d7ac2 |
| 30 | de4412dd | 2025-11-14 | yangdx | Fix embedding token limit initialization order | embedding | 8 | git cherry-pick de4412dd |
| 31 | e5addf4d | 2025-11-14 | yangdx | Improve embedding config priority and add debug logging | embedding | 8 | git cherry-pick e5addf4d |
| 32 | f0254773 | 2025-11-14 | yangdx | Convert embedding_token_limit from property to field with __post_init__ | embedding | 8 | git cherry-pick f0254773 |
| 33 | 3b76eea2 | 2025-11-15 | Daniel.y | Merge pull request #2359 from danielaskdd/embedding-limit | embedding | 8 | git cherry-pick 3b76eea2 |
| 34 | b5589ce4 | 2025-11-15 | yangdx | Merge branch 'main' into embedding-limit | embedding | 8 | git cherry-pick b5589ce4 |
| 35 | c13f9116 | 2025-11-17 | yangdx | Add embedding dimension validation to EmbeddingFunc wrapper | embedding | 8 | git cherry-pick c13f9116 |
| 36 | 46ce6d9a | 2025-11-20 | yangdx | Fix Azure OpenAI embedding model parameter fallback | embedding | 8 | git cherry-pick 46ce6d9a |
| 37 | 0c4cba38 | 2025-11-21 | yangdx | Fix double decoration in azure_openai_embed and document decorator usage | embedding | 8 | git cherry-pick 0c4cba38 |
| 38 | 7b762110 | 2025-11-22 | yangdx | Add fallback to AZURE_OPENAI_API_VERSION for embedding API version | embedding | 8 | git cherry-pick 7b762110 |
| 39 | 1b02684e | 2025-11-28 | Daniel.y | Merge pull request #2432 from danielaskdd/embedding-example | embedding | 8 | git cherry-pick 1b02684e |
| 40 | 1d07ff7f | 2025-11-28 | yangdx | Update OpenAI and Ollama embedding func examples in README | embedding | 8 | git cherry-pick 1d07ff7f |
| 41 | 4ab4a7ac | 2025-11-28 | yangdx | Allow embedding models to use provider defaults when unspecified | embedding | 8 | git cherry-pick 4ab4a7ac |
| 42 | 56e0365c | 2025-11-28 | yangdx | Add configurable model parameter to jina_embed function | embedding | 8 | git cherry-pick 56e0365c |
| 43 | 6e2946e7 | 2025-11-28 | yangdx | Add max_token_size parameter to azure_openai_embed wrapper | embedding | 8 | git cherry-pick 6e2946e7 |
| 44 | 97a9dfca | 2025-11-28 | yangdx | Add important note about embedding function wrapping restrictions | embedding | 8 | git cherry-pick 97a9dfca |
| 45 | b6705449 | 2025-11-28 | Daniel.y | Merge pull request #2433 from danielaskdd/fix-jina-embedding | embedding | 8 | git cherry-pick b6705449 |
| 46 | ea8d55ab | 2025-11-28 | yangdx | Add documentation for embedding provider configuration rules | embedding | 8 | git cherry-pick ea8d55ab |
| 47 | 37e8898c | 2025-10-01 | yangdx | Simplify reference formatting in LLM context generation | llm_cloud | 9 | git cherry-pick 37e8898c |
| 48 | 83d99e14 | 2025-10-01 | yangdx | fix(OllamaAPI): Add validation to ensure last message is from user role | llm_cloud | 9 | git cherry-pick 83d99e14 |
| 49 | 0b3d3150 | 2025-10-20 | Humphry | extended to use gemini, sswitched to use gemini-flash-latest | llm_cloud | 9 | git cherry-pick 0b3d3150 |
| 50 | 74694214 | 2025-10-20 | dependabot[bot] | Update openai requirement from <2.0.0,>=1.0.0 to >=1.0.0,<3.0.0 | llm_cloud | 9 | git cherry-pick 74694214 |
| 51 | 175ef459 | 2025-10-21 | Daniel.y | Merge pull request #2238 from HKUDS/dependabot/pip/openai-gte-1.0.0-and-lt-3.0.0 | llm_cloud | 9 | git cherry-pick 175ef459 |
| 52 | 162370b6 | 2025-10-22 | yangdx | Add optional LLM cache deletion when deleting documents | llm_cloud | 9 | git cherry-pick 162370b6 |
| 53 | aa916f28 | 2025-11-01 | anouarbm | docs: add generic test_dataset.json for evaluation examples Test cases with generic examples about: - LightRAG framework features and capabilities - RAG system architecture and components - Vector database support (ChromaDB, Neo4j, Milvus, etc.) - LLM provider integrations (OpenAI, Anthropic, Ollama, etc.) - RAG evaluation metrics explanation - Deployment options (Docker, FastAPI, direct integration) - Knowledge graph-based retrieval concepts | llm_cloud | 9 | git cherry-pick aa916f28 |
| 54 | 994a82dc | 2025-11-05 | yangdx | Suppress token usage warnings for custom OpenAI-compatible endpoints | llm_cloud | 9 | git cherry-pick 994a82dc |
| 55 | 3cb4eae4 | 2025-11-07 | yangdx | Add Chain of Thought support to Gemini LLM integration | llm_cloud | 9 | git cherry-pick 3cb4eae4 |
| 56 | 6686edfd | 2025-11-07 | yangdx | Update Gemini LLM options: add seed and thinking config, remove MIME type | llm_cloud | 9 | git cherry-pick 6686edfd |
| 57 | 73284623 | 2025-11-07 | Daniel.y | Merge pull request #2326 from danielaskdd/gemini-cot | llm_cloud | 9 | git cherry-pick 73284623 |
| 58 | 8c275553 | 2025-11-07 | yangdx | Fix Gemini response parsing to avoid warnings from non-text parts | llm_cloud | 9 | git cherry-pick 8c275553 |
| 59 | 924c8cb8 | 2025-11-07 | yangdx | Merge branch 'main' into gemini-cot | llm_cloud | 9 | git cherry-pick 924c8cb8 |
| 60 | fc40a369 | 2025-11-07 | yangdx | Add timeout support to Gemini LLM and improve parameter handling | llm_cloud | 9 | git cherry-pick fc40a369 |
| 61 | 3d9de5ed | 2025-11-08 | yangdx | feat: improve Gemini client error handling and retry logic | llm_cloud | 9 | git cherry-pick 3d9de5ed |
| 62 | 55274dde | 2025-11-08 | yangdx | Add LLM cache migration tool for KV storage backends | llm_cloud | 9 | git cherry-pick 55274dde |
| 63 | 57ee7d5a | 2025-11-08 | yangdx | Merge branch 'main' into llm-cache-migrate | llm_cloud | 9 | git cherry-pick 57ee7d5a |
| 64 | 6b9f13c7 | 2025-11-08 | yangdx | Enhance LLM cache migration tool with streaming and improved UX | llm_cloud | 9 | git cherry-pick 6b9f13c7 |
| 65 | 6fc54d36 | 2025-11-08 | yangdx | Move LLM cache migration tool to lightrag.tools module | llm_cloud | 9 | git cherry-pick 6fc54d36 |
| 66 | 85bb98b3 | 2025-11-08 | Daniel.y | Merge pull request #2331 from danielaskdd/gemini-retry | llm_cloud | 9 | git cherry-pick 85bb98b3 |
| 67 | 987bc09c | 2025-11-08 | yangdx | Update LLM cache migration docs and improve UX prompts | llm_cloud | 9 | git cherry-pick 987bc09c |
| 68 | d0d31e92 | 2025-11-08 | yangdx | Improve LLM cache migration tool configuration and messaging | llm_cloud | 9 | git cherry-pick d0d31e92 |
| 69 | f83ea339 | 2025-11-08 | yangdx | Add section header comment for Gemini binding options | llm_cloud | 9 | git cherry-pick f83ea339 |
| 70 | 1485cb82 | 2025-11-09 | yangdx | Add LLM query cache cleanup tool for KV storage backends | llm_cloud | 9 | git cherry-pick 1485cb82 |
| 71 | 3110ca51 | 2025-11-09 | Daniel.y | Merge pull request #2335 from danielaskdd/llm-cache-cleanup | llm_cloud | 9 | git cherry-pick 3110ca51 |
| 72 | 754d2ad2 | 2025-11-09 | yangdx | Add documentation for LLM cache migration between storage types | llm_cloud | 9 | git cherry-pick 754d2ad2 |
| 73 | 88ab73f6 | 2025-11-09 | yangdx | HotFix: Restore streaming response in OpenAI LLM | llm_cloud | 9 | git cherry-pick 88ab73f6 |
| 74 | 8adf3180 | 2025-11-09 | Daniel.y | Merge pull request #2330 from danielaskdd/llm-cache-migrate | llm_cloud | 9 | git cherry-pick 8adf3180 |
| 75 | 18893015 | 2025-11-13 | yangdx | Merge branch 'feat/add_cloud_ollama_support' | llm_cloud | 9 | git cherry-pick 18893015 |
| 76 | 680e36c6 | 2025-11-14 | yangdx | Improve Bedrock error handling with retry logic and custom exceptions | llm_cloud | 9 | git cherry-pick 680e36c6 |
| 77 | f5b48587 | 2025-11-14 | yangdx | Improve Bedrock error handling with retry logic and custom exceptions | llm_cloud | 9 | git cherry-pick f5b48587 |
| 78 | 95e1fb16 | 2025-11-17 | yangdx | Remove final_namespace attribute for in-memory storage and use namespace in clean_llm_query_cache.py | llm_cloud | 9 | git cherry-pick 95e1fb16 |
| 79 | a990c1d4 | 2025-11-17 | BukeLy | fix: Correct Mock LLM output format in E2E test | llm_cloud | 9 | git cherry-pick a990c1d4 |
| 80 | 021b637d | 2025-11-21 | Daniel.y | Merge pull request #2403 from danielaskdd/azure-cot-handling | llm_cloud | 9 | git cherry-pick 021b637d |
| 81 | 02fdceb9 | 2025-11-21 | yangdx | Update OpenAI client to use stable API and bump minimum version to 2.0.0 | llm_cloud | 9 | git cherry-pick 02fdceb9 |
| 82 | 1e477e95 | 2025-11-21 | yangdx | Add lightrag-clean-llmqc console script entry point | llm_cloud | 9 | git cherry-pick 1e477e95 |
| 83 | 45f4f823 | 2025-11-21 | yangdx | Refactor Azure OpenAI client creation to support client_configs merging | llm_cloud | 9 | git cherry-pick 45f4f823 |
| 84 | 8777895e | 2025-11-21 | Daniel.y | Merge pull request #2401 from danielaskdd/fix-openai-keyword-extraction | llm_cloud | 9 | git cherry-pick 8777895e |
| 85 | 9f69c5bf | 2025-11-21 | yangdx | feat: Support structured output `parsed` from OpenAI | llm_cloud | 9 | git cherry-pick 9f69c5bf |
| 86 | ac9f2574 | 2025-11-21 | yangdx | Improve Azure OpenAI wrapper functions with full parameter support | llm_cloud | 9 | git cherry-pick ac9f2574 |
| 87 | b709f8f8 | 2025-11-21 | yangdx | Consolidate Azure OpenAI implementation into main OpenAI module | llm_cloud | 9 | git cherry-pick b709f8f8 |
| 88 | fafa1791 | 2025-11-21 | yangdx | Fix Azure OpenAI model parameter to use deployment name consistently | llm_cloud | 9 | git cherry-pick fafa1791 |
| 89 | ffd8da51 | 2025-11-21 | yangdx | Improve Azure OpenAI compatibility and error handling | llm_cloud | 9 | git cherry-pick ffd8da51 |
| 90 | 49fb11e2 | 2025-11-22 | yangdx | Update Azure OpenAI configuration examples | llm_cloud | 9 | git cherry-pick 49fb11e2 |
| 91 | 5f53de88 | 2025-11-22 | yangdx | Fix Azure configuration examples and correct typos in env.example | llm_cloud | 9 | git cherry-pick 5f53de88 |
| 92 | a898f054 | 2025-11-25 | palanisd | Merge branch 'HKUDS:main' into cohere-rerank | rerank | 10 | git cherry-pick a898f054 |
| 93 | 8e50eef5 | 2025-12-02 | yangdx | Merge branch 'main' into cohere-rerank | rerank | 10 | git cherry-pick 8e50eef5 |
| 94 | f0d67f16 | 2025-12-03 | yangdx | Merge branch 'cohere-rerank' | rerank | 10 | git cherry-pick f0d67f16 |