Google Git
Sign in
apache / incubator-hugegraph-ai / HEAD
  1. 9e76c2a docs(llm): use AGENTS.md as LLM standard doc (#299) by LingXiao Qi · 10 days ago main
  2. dedf4ae fix(llm): add missing 'properties' in gremlin prompt formatting (#298) by Sean · 6 weeks ago
  3. 71fe026 feat(llm): add text2gremlin api (#258) by SoJGooo · 6 weeks ago
  4. 957283e feat(llm): support vector data for a graph instance by multi model (#265) by Gearless · 7 weeks ago
  5. 99cd5e4 feat(llm): support switch prompt language in EN/CN (#269) by day0n · 7 weeks ago
  6. 0c9c15c fix(llm): refactor embedding parallelization to preserve order (#295) by imbajin · 7 weeks ago
  7. cd404b8 perf(llm): optimize vector index with asyncio embedding (#264) by Linyu · 7 weeks ago
  8. a825e65 docs: update README with improved setup instructions (#294) by Linyu · 8 weeks ago
  9. 6dd9cd7 refactor(llm): replace QianFan by OpenAI-compatible format (#285) by day0n · 8 weeks ago
  10. b4e2fe9 feat(llm): add rules for AI coding guideline - V1.0 (#293) by LingXiao Qi · 8 weeks ago
  11. fe94881 chore(llm): add a basic LLM/AI coding instruction file (#290) by imbajin · 8 weeks ago
  12. 220ceb1 chore: add GitHub Actions for auto upstream sync and update SEALData subsample logic (#289) by Linyu · 8 weeks ago
  13. 8601058 fix(log): reduce 3rd-party library log output (#284) by Zequan · 9 weeks ago
  14. 6fbf164 chore: unify all modules with uv (#287) by imbajin · 9 weeks ago
  15. 409fc12 docs: update with `docker compose` command (#283) by Zhangjian He · 2 months ago
  16. b51717c feat(llm): support semi-automated generated graph schema (#274) by Gearless · 3 months ago
  17. 52a666e feat(llm): support semi-automated prompt generation (#281) by LRriver · 3 months ago
  18. b027744 chore: add docker-compose deployment and improve container networking instructions (#280) by Linyu · 3 months ago
  19. 0bf31d2 fix(llm): limit the deps version to handle critical init problems (#279) by imbajin · 3 months ago
  20. 9231272 docs: improve README clarity and deployment instructions (#276) by Linyu · 3 months ago
  21. 2eb743b docs(llm): fix grammar errors (#275) by chenzihong · 3 months ago
  22. 5ca7a1c docs(llm): synchronization with official documentation (#273) by Linyu · 3 months ago
  23. e403108 refactor(vermeer): use uv to manage pkgs & update README (#272) by imbajin · 3 months ago
  24. 6ea1102 refactor: use uv in client & ml modules & adapter the CI (#257) by HLOVI · 3 months ago
  25. e356178 feat(vermeer): add vermeer python client for graph computing (#263) by SoJGooo · 3 months ago
  26. 594b978 fix(chore): Dockerfile to add pyproject.toml anchor file (#266) by Linyu · 4 months ago
  27. cd6fd33 fix(config): enhance config path handling and add project root validation (#262) by Linyu · 4 months ago
  28. 434d691 refactor(llm): basic compatible in text2gremlin generation (#261) by SoJGooo · 4 months ago
  29. 26b9e45 fix(llm): mark wrong usage in embedding api (#250) by SoJGooo · 4 months ago
  30. 6a897ee fix(llm): skip empty chunk in LLM steaming mode (#245) by SoJGooo · 4 months ago
  31. 122b124 chore(hg-llm): use uv instead poetry as the deps management tool (#226) by HLOVI · 4 months ago
  32. 8887a3b chore(llm): using nuitka to provide a binary/perf way for the service (#242) by Linyu · 4 months ago
  33. 8a61cf7 feat(llm): support batch embedding (#238) by Linyu · 4 months ago
  34. f6b547c refactor(llm): change QPS -> RPM for timer decorator (#241) by Ethereal-O · 4 months ago
  35. 279802b refactor(llm): use asyncio to embed text (#215) by Moncef · 4 months ago
  36. e1d3e44 fix(llm): failed to remove vectors when updating vid embedding (#243) by SoJGooo · 4 months ago
  37. 32abd2a chore(llm): update gradio's version for pip (#235) by Linyu · 4 months ago
  38. 6754fae refactor: replace the IP + Port with URL (#209) by Ming Fang · 5 months ago
  39. b336203 refactor(llm): change Textbox to Code (#223) by xie qizhuo · 5 months ago
  40. 6a672cd refactor(llm): enhance the multi configs for LLM (#212) by HLOVI · 5 months ago
  41. 212d9a5 chore(llm): use 4.1-mini and 0.01 temperature by default (#214) by SoJGooo · 5 months ago
  42. 6e25d23 refactor(llm): add doc & disable text2gql by default (#216) by SoJGooo · 5 months ago
  43. a972b56 fix(clien): fix documentation sample code error (#219) by John · 5 months ago
  44. aa83ec2 fix(llm): align regex extraction of json to json format of prompt (#211) by John · 5 months ago
  45. 36d5444 refactor(llm): check graph conn before updating embedding (#205) by SoJGooo · 6 months ago proxy-param
  46. 4f2f123 fix(llm): enable tasks concurrency configs in Gradio (#188) by Kryst4lDem0ni4s · 6 months ago
  47. 927e17c fix(llm): fix tiny bugs & optimize reranker layout (#202) by HaoJin Yang · 6 months ago
  48. 2eee184 chore: enable discussion & change merge way (#201) by imbajin · 6 months ago
  49. d02ec96 chore(llm): multi-stage building in Dockerfile (#199) by imbajin · 7 months ago
  50. a316258 feat(llm): support Docker & K8s deployment way (#195) by PeiChaoXu · 7 months ago
  51. e12a0bb docs(llm): add quick_start.md for UI usage (#196) by SoJGooo · 7 months ago
  52. c26f5bf refactor(llm): enhance the regex extraction func (#194) by HaoJin Yang · 7 months ago
  53. 7ae5d6f feat(llm): support async streaming output in RAG answer block (#190) by vichayturen · 7 months ago
  54. ca28faf refactor(llm): replace vid by full vertexes info (#189) by imbajin · 7 months ago
  55. 8c1ffbb refactor(llm): improve graph extraction default prompt (#187) by Kryst4lDem0ni4s · 7 months ago
  56. 759b963 feat(llm): support switch graph in api & add some query configs (#184) by PeiChaoXu · 7 months ago
  57. 3e0bf46 feat(llm): support `litellm` for multi-LLM provider (#178) by Cong Zhao · 7 months ago
  58. e78792f chore: add collaborators in asf config (#182) by imbajin · 7 months ago
  59. 2ae610c refactor(llm): use EN prompt for keywords extraction (#174) by imbajin · 7 months ago
  60. 0a33550 refactor: use uv for the CI action (#175) by imbajin · 7 months ago
  61. d01e07e fix(llm): Merge all logs into one file (#171) by Aryan Kumar Baghel · 7 months ago
  62. 9a9de77 fix(llm): enable fastapi auto reload function (#164) by Aryan Kumar Baghel · 7 months ago
  63. e00d6e7 fix(llm): update gremlin_generate prompt to apply fuzzy match (#163) by HaoJin Yang · 7 months ago
  64. a0cc3f9 refactor(llm): return schema.groovy first when backup graph data (#161) by SoJGooo · 8 months ago
  65. 1c9bb5e feat(llm): add post method for paths-api (#162) by SoJGooo · 8 months ago
  66. 88264e7 feat(llm): use poetry to manage the dependencies (#149) by Hongjun Li · 8 months ago
  67. fa2672a refactor(llm): support mathjax in rag query block V1 (#157) by SoJGooo · 8 months ago
  68. def84a2 refactor(llm): change vid embedding x:yy to yy & use multi-thread (#158) by SoJGooo · 8 months ago
  69. 7f7c82c feat(llm): support intent recognition V1 (#159) by HaoJin Yang · 8 months ago
  70. 84c4d7e feat(llm): modify clear buttons (#156) by SoJGooo · 9 months ago
  71. 9239799 refactor(llm): extract `topk_per_keyword` & `topk_return_results` to .env by SoJGooo · 9 months ago
  72. 2441d2b fix(llm): use empty str for llm config (#155) by chenzihong · 9 months ago
  73. 820bfb2 refactor(llm): add a button to backup data & count together (#153) by SoJGooo · 9 months ago
  74. 4c97cd6 feat(llm): automatic backup graph data timely (#151) by SoJGooo · 9 months ago
  75. 3ad572f feat(llm): modify the summary info and enhance the request logic (#147) by SoJGooo · 9 months ago
  76. 65e831e doc(client): update README for python-client/SDK (#150) by HaoJin Yang · 9 months ago
  77. 39e8d48 refactor(llm): remove enable_gql logic in api & rag block (#148) by HaoJin Yang · 9 months ago
  78. 2854948 feat(llm): use retry from tenacity (#143) by chenzihong · 9 months ago
  79. 030fd2e fix(llm): extract_graph_data use wrong method (#145) by SoJGooo · 9 months ago
  80. f1713b0 feat(llm): timely execute vid embedding & enhance some HTTP logic (#141) by SoJGooo · 9 months ago
  81. e6aa61a chore: enable pip cache (#142) by imbajin · 9 months ago
  82. d2fcfdb fix(llm): update prompt to fit prefix cache (#137) by HaoJin Yang · 9 months ago
  83. 9be3305 fix(ml): correct header writing errors by SoJGooo · 9 months ago
  84. 9018271 fix(llm): support choose template in /rag & /rag/graph api (#135) by HaoJin Yang · 9 months ago
  85. 900a465 fix(llm): replace getenv usage to settings (#133) by chenzihong · 9 months ago
  86. 560fe03 refactor(llm): use pydantic-settings for config management (#122) by chenzihong · 9 months ago
  87. 9512459 fix(llm): multi vid k-neighbor query only return the data of first vid by yc319 · 10 months ago
  88. cbfca3c feat(llm): added the process of text2gql in graphrag V1.0 (#105) by vichayturen · 10 months ago
  89. 71b6261 fix(lint): critical bug with pylint usage (#131) by SoJGooo · 10 months ago
  90. 672aeef fix: pylint in ml (#125) by SoJ · 10 months ago
  91. f8500f9 fix(llm): limit the length of log & improve the format (#121) by Dylan · 10 months ago
  92. ef56263 refactor(llm): merge & update keyword extraction logic/prompt (#120) by HaoJin Yang · 10 months ago release-1.5.0 1.5.0 1.5.0-rc3
  93. 2d8e6c8 chore: enable allow-license & exclude style dir (#119) by imbajin · 10 months ago
  94. df9adf8 chore(dist): add license header for files under style directory (#118) by V_Galaxy · 10 months ago
  95. 265d43c feat(llm): separate multi llm configs/models (#112) by HaoJin Yang · 10 months ago
  96. f8b4582 fix(llm): correct e_cache type (#117) by chenzihong · 10 months ago
  97. 153d7f4 fix(llm): answer prompt None value effect (#116) by Hongjun Li · 10 months ago
  98. 943e750 fix: null value detection on vid attributes (#115) by chenzihong · 10 months ago
  99. aeb25bd fix(rag): rag api critical bug & rename some params (#114) by Hongjun Li · 10 months ago
  100. 41412a6 feat(llm): support log_block in RAG platform & rest-api (#110) by Dylan · 10 months ago