LightRAG/docs/diff_hku/waves/wave_2.csv
2025-12-04 19:13:48 +08:00

12 KiB

1commitauth_dateauthorsubjectcategorypriority_idxgit_cherry_pick_cmd
2ec40b17e2025-10-08YasiruRangana feat: Add token tracking support to openai_embed functionembedding8git cherry-pick ec40b17e
30f15fdc32025-10-09Daniel.yMerge pull request #2181 from yrangana/feat/openai-embedding-token-trackingembedding8git cherry-pick 0f15fdc3
46d1ae4042025-10-15yangdxAdd offline Docker build support with embedded models and cacheembedding8git cherry-pick 6d1ae404
56a29b5da2025-10-23yangdxUpdate Docker deployment comments for LLM and embedding hostsembedding8git cherry-pick 6a29b5da
67b8223da2025-11-03yangdxUpdate env.example with host/endpoint clarifications for LLM/embeddingembedding8git cherry-pick 7b8223da
79c0570602025-11-05yangdxAdd separate endpoint configuration for LLM and embeddings in evaluationembedding8git cherry-pick 9c057060
801b07b2b2025-11-07yangdxRefactor Jina embedding dimension by changing param to optional with defaultembedding8git cherry-pick 01b07b2b
933a1482f2025-11-07yangdxAdd optional embedding dimension parameter control via env varembedding8git cherry-pick 33a1482f
109cee5a632025-11-07yangdxMerge branch 'main' into apply-dim-to-embedding-callembedding8git cherry-pick 9cee5a63
11ce28f30c2025-11-07yangdxAdd embedding_dim parameter support to embedding functionsembedding8git cherry-pick ce28f30c
12d8a6355e2025-11-07yangdxMerge branch 'main' into apply-dim-to-embedding-callembedding8git cherry-pick d8a6355e
13d94aae9c2025-11-07YasiruRangana Add dimensions parameter support to openai_embed()embedding8git cherry-pick d94aae9c
14ffeeae422025-11-07yangdxrefactor: simplify jina embedding dimension handlingembedding8git cherry-pick ffeeae42
1503cc62622025-11-08yangdxProhibit direct access to internal functions of EmbeddingFunc.embedding8git cherry-pick 03cc6262
160b2a15c42025-11-08yangdxCentralize embedding_send_dim config through args instead of env varembedding8git cherry-pick 0b2a15c4
1729a349f22025-11-08Daniel.yMerge pull request #2329 from danielaskdd/gemini-embeddingembedding8git cherry-pick 29a349f2
18a624a9502025-11-08yangdxAdd Gemini to APIs requiring embedding dimension parameterembedding8git cherry-pick a624a950
19de4ed7362025-11-08yangdxAdd Gemini embedding supportembedding8git cherry-pick de4ed736
20f4492d482025-11-08Daniel.yMerge pull request #2328 from HKUDS/apply-dim-to-embedding-callembedding8git cherry-pick f4492d48
2105852e1a2025-11-14yangdxAdd max_token_size parameter to embedding function decoratorsembedding8git cherry-pick 05852e1a
2214a6c24e2025-11-14yangdxAdd configurable embedding token limit with validationembedding8git cherry-pick 14a6c24e
232fb57e762025-11-14yangdxFix embedding token limit initialization orderembedding8git cherry-pick 2fb57e76
2439b49e922025-11-14yangdxConvert embedding_token_limit from property to field with __post_init__embedding8git cherry-pick 39b49e92
255dec4dea2025-11-14yangdxImprove embedding config priority and add debug loggingembedding8git cherry-pick 5dec4dea
266b2af2b52025-11-14yangdxRefactor embedding function creation with proper attribute inheritanceembedding8git cherry-pick 6b2af2b5
27772215642025-11-14yangdxAdd max_token_size parameter to embedding function decoratorsembedding8git cherry-pick 77221564
28963a0a5d2025-11-14yangdxRefactor embedding function creation with proper attribute inheritanceembedding8git cherry-pick 963a0a5d
29ab4d7ac22025-11-14yangdxAdd configurable embedding token limit with validationembedding8git cherry-pick ab4d7ac2
30de4412dd2025-11-14yangdxFix embedding token limit initialization orderembedding8git cherry-pick de4412dd
31e5addf4d2025-11-14yangdxImprove embedding config priority and add debug loggingembedding8git cherry-pick e5addf4d
32f02547732025-11-14yangdxConvert embedding_token_limit from property to field with __post_init__embedding8git cherry-pick f0254773
333b76eea22025-11-15Daniel.yMerge pull request #2359 from danielaskdd/embedding-limitembedding8git cherry-pick 3b76eea2
34b5589ce42025-11-15yangdxMerge branch 'main' into embedding-limitembedding8git cherry-pick b5589ce4
35c13f91162025-11-17yangdxAdd embedding dimension validation to EmbeddingFunc wrapperembedding8git cherry-pick c13f9116
3646ce6d9a2025-11-20yangdxFix Azure OpenAI embedding model parameter fallbackembedding8git cherry-pick 46ce6d9a
370c4cba382025-11-21yangdxFix double decoration in azure_openai_embed and document decorator usageembedding8git cherry-pick 0c4cba38
387b7621102025-11-22yangdxAdd fallback to AZURE_OPENAI_API_VERSION for embedding API versionembedding8git cherry-pick 7b762110
391b02684e2025-11-28Daniel.yMerge pull request #2432 from danielaskdd/embedding-exampleembedding8git cherry-pick 1b02684e
401d07ff7f2025-11-28yangdxUpdate OpenAI and Ollama embedding func examples in READMEembedding8git cherry-pick 1d07ff7f
414ab4a7ac2025-11-28yangdxAllow embedding models to use provider defaults when unspecifiedembedding8git cherry-pick 4ab4a7ac
4256e0365c2025-11-28yangdxAdd configurable model parameter to jina_embed functionembedding8git cherry-pick 56e0365c
436e2946e72025-11-28yangdxAdd max_token_size parameter to azure_openai_embed wrapperembedding8git cherry-pick 6e2946e7
4497a9dfca2025-11-28yangdxAdd important note about embedding function wrapping restrictionsembedding8git cherry-pick 97a9dfca
45b67054492025-11-28Daniel.yMerge pull request #2433 from danielaskdd/fix-jina-embeddingembedding8git cherry-pick b6705449
46ea8d55ab2025-11-28yangdxAdd documentation for embedding provider configuration rulesembedding8git cherry-pick ea8d55ab
4737e8898c2025-10-01yangdxSimplify reference formatting in LLM context generationllm_cloud9git cherry-pick 37e8898c
4883d99e142025-10-01yangdxfix(OllamaAPI): Add validation to ensure last message is from user rolellm_cloud9git cherry-pick 83d99e14
490b3d31502025-10-20Humphryextended to use gemini, sswitched to use gemini-flash-latestllm_cloud9git cherry-pick 0b3d3150
50746942142025-10-20dependabot[bot]Update openai requirement from <2.0.0,>=1.0.0 to >=1.0.0,<3.0.0llm_cloud9git cherry-pick 74694214
51175ef4592025-10-21Daniel.yMerge pull request #2238 from HKUDS/dependabot/pip/openai-gte-1.0.0-and-lt-3.0.0llm_cloud9git cherry-pick 175ef459
52162370b62025-10-22yangdxAdd optional LLM cache deletion when deleting documentsllm_cloud9git cherry-pick 162370b6
53aa916f282025-11-01anouarbmdocs: 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 conceptsllm_cloud9git cherry-pick aa916f28
54994a82dc2025-11-05yangdxSuppress token usage warnings for custom OpenAI-compatible endpointsllm_cloud9git cherry-pick 994a82dc
553cb4eae42025-11-07yangdxAdd Chain of Thought support to Gemini LLM integrationllm_cloud9git cherry-pick 3cb4eae4
566686edfd2025-11-07yangdxUpdate Gemini LLM options: add seed and thinking config, remove MIME typellm_cloud9git cherry-pick 6686edfd
57732846232025-11-07Daniel.yMerge pull request #2326 from danielaskdd/gemini-cotllm_cloud9git cherry-pick 73284623
588c2755532025-11-07yangdxFix Gemini response parsing to avoid warnings from non-text partsllm_cloud9git cherry-pick 8c275553
59924c8cb82025-11-07yangdxMerge branch 'main' into gemini-cotllm_cloud9git cherry-pick 924c8cb8
60fc40a3692025-11-07yangdxAdd timeout support to Gemini LLM and improve parameter handlingllm_cloud9git cherry-pick fc40a369
613d9de5ed2025-11-08yangdxfeat: improve Gemini client error handling and retry logicllm_cloud9git cherry-pick 3d9de5ed
6255274dde2025-11-08yangdxAdd LLM cache migration tool for KV storage backendsllm_cloud9git cherry-pick 55274dde
6357ee7d5a2025-11-08yangdxMerge branch 'main' into llm-cache-migratellm_cloud9git cherry-pick 57ee7d5a
646b9f13c72025-11-08yangdxEnhance LLM cache migration tool with streaming and improved UXllm_cloud9git cherry-pick 6b9f13c7
656fc54d362025-11-08yangdxMove LLM cache migration tool to lightrag.tools modulellm_cloud9git cherry-pick 6fc54d36
6685bb98b32025-11-08Daniel.yMerge pull request #2331 from danielaskdd/gemini-retryllm_cloud9git cherry-pick 85bb98b3
67987bc09c2025-11-08yangdxUpdate LLM cache migration docs and improve UX promptsllm_cloud9git cherry-pick 987bc09c
68d0d31e922025-11-08yangdxImprove LLM cache migration tool configuration and messagingllm_cloud9git cherry-pick d0d31e92
69f83ea3392025-11-08yangdxAdd section header comment for Gemini binding optionsllm_cloud9git cherry-pick f83ea339
701485cb822025-11-09yangdxAdd LLM query cache cleanup tool for KV storage backendsllm_cloud9git cherry-pick 1485cb82
713110ca512025-11-09Daniel.yMerge pull request #2335 from danielaskdd/llm-cache-cleanupllm_cloud9git cherry-pick 3110ca51
72754d2ad22025-11-09yangdxAdd documentation for LLM cache migration between storage typesllm_cloud9git cherry-pick 754d2ad2
7388ab73f62025-11-09yangdxHotFix: Restore streaming response in OpenAI LLMllm_cloud9git cherry-pick 88ab73f6
748adf31802025-11-09Daniel.yMerge pull request #2330 from danielaskdd/llm-cache-migratellm_cloud9git cherry-pick 8adf3180
75188930152025-11-13yangdxMerge branch 'feat/add_cloud_ollama_support'llm_cloud9git cherry-pick 18893015
76680e36c62025-11-14yangdxImprove Bedrock error handling with retry logic and custom exceptionsllm_cloud9git cherry-pick 680e36c6
77f5b485872025-11-14yangdxImprove Bedrock error handling with retry logic and custom exceptionsllm_cloud9git cherry-pick f5b48587
7895e1fb162025-11-17yangdxRemove final_namespace attribute for in-memory storage and use namespace in clean_llm_query_cache.pyllm_cloud9git cherry-pick 95e1fb16
79a990c1d42025-11-17BukeLyfix: Correct Mock LLM output format in E2E testllm_cloud9git cherry-pick a990c1d4
80021b637d2025-11-21Daniel.yMerge pull request #2403 from danielaskdd/azure-cot-handlingllm_cloud9git cherry-pick 021b637d
8102fdceb92025-11-21yangdxUpdate OpenAI client to use stable API and bump minimum version to 2.0.0llm_cloud9git cherry-pick 02fdceb9
821e477e952025-11-21yangdxAdd lightrag-clean-llmqc console script entry pointllm_cloud9git cherry-pick 1e477e95
8345f4f8232025-11-21yangdxRefactor Azure OpenAI client creation to support client_configs mergingllm_cloud9git cherry-pick 45f4f823
848777895e2025-11-21Daniel.yMerge pull request #2401 from danielaskdd/fix-openai-keyword-extractionllm_cloud9git cherry-pick 8777895e
859f69c5bf2025-11-21yangdxfeat: Support structured output `parsed` from OpenAIllm_cloud9git cherry-pick 9f69c5bf
86ac9f25742025-11-21yangdxImprove Azure OpenAI wrapper functions with full parameter supportllm_cloud9git cherry-pick ac9f2574
87b709f8f82025-11-21yangdxConsolidate Azure OpenAI implementation into main OpenAI modulellm_cloud9git cherry-pick b709f8f8
88fafa17912025-11-21yangdxFix Azure OpenAI model parameter to use deployment name consistentlyllm_cloud9git cherry-pick fafa1791
89ffd8da512025-11-21yangdxImprove Azure OpenAI compatibility and error handlingllm_cloud9git cherry-pick ffd8da51
9049fb11e22025-11-22yangdxUpdate Azure OpenAI configuration examplesllm_cloud9git cherry-pick 49fb11e2
915f53de882025-11-22yangdxFix Azure configuration examples and correct typos in env.examplellm_cloud9git cherry-pick 5f53de88
92a898f0542025-11-25palanisdMerge branch 'HKUDS:main' into cohere-rerankrerank10git cherry-pick a898f054
938e50eef52025-12-02yangdxMerge branch 'main' into cohere-rerankrerank10git cherry-pick 8e50eef5
94f0d67f162025-12-03yangdxMerge branch 'cohere-rerank'rerank10git cherry-pick f0d67f16