Commit Graph

  • 612621f393 feat: pull image with progress (#777) Tim 2025-04-10 12:00:27 +08:00
  • b662f45021 feat: dump model (#776) you-n-g 2025-04-09 23:24:12 +08:00
  • bbc591b401 feat: dump model (#776) you-n-g 2025-04-09 23:24:12 +08:00
  • 92d007e179 ui updates (#778) XianBW 2025-04-09 20:11:00 +08:00
  • 835da5b918 ui updates (#778) XianBW 2025-04-09 20:11:00 +08:00
  • c40f22361c refactor: update MLEBench submission validation logic in runner and eval (#769) you-n-g 2025-04-09 13:34:48 +08:00
  • 8a11bfbf53 refactor: update MLEBench submission validation logic in runner and eval (#769) you-n-g 2025-04-09 13:34:48 +08:00
  • e22fb84fb3 update wechat qrcode (#775) Linlang 2025-04-09 12:23:38 +08:00
  • 8d5fb2eebf update wechat qrcode (#775) Linlang 2025-04-09 12:23:38 +08:00
  • 80c5eb209e catch llm_data pkl read exception (#774) XianBW 2025-04-09 12:21:54 +08:00
  • b95154c99d catch llm_data pkl read exception (#774) XianBW 2025-04-09 12:21:54 +08:00
  • 67114540b1 feat: checkpoint selection (#744) xuangu-fang 2025-04-09 09:42:30 +08:00
  • fd155d1fa8 feat: checkpoint selection (#744) xuangu-fang 2025-04-09 09:42:30 +08:00
  • 8517eb4a18 fix: update feedback.py (#772) Xu Yang 2025-04-08 09:35:11 -06:00
  • c3cc763430 fix: update feedback.py (#772) Xu Yang 2025-04-08 09:35:11 -06:00
  • a16c79e45b small bug fix in feedback (#771) Xu Yang 2025-04-08 08:17:47 -06:00
  • a50b2bba43 small bug fix in feedback (#771) Xu Yang 2025-04-08 08:17:47 -06:00
  • ce23e1c30b chore: data science scenario UI updates (#770) XianBW 2025-04-08 19:33:20 +08:00
  • 6c8fdeaa41 chore: data science scenario UI updates (#770) XianBW 2025-04-08 19:33:20 +08:00
  • 92e7932126 add rule-based eval to speed up the whole process (#768) Xu Yang 2025-04-08 03:27:21 -06:00
  • f092739ab5 add rule-based eval to speed up the whole process (#768) Xu Yang 2025-04-08 03:27:21 -06:00
  • 31752bb8f0 feat: merge failed and successful traces together (#766) Yuante Li 2025-04-08 17:04:55 +08:00
  • cd4d07c323 feat: merge failed and successful traces together (#766) Yuante Li 2025-04-08 17:04:55 +08:00
  • 7372d1011e feat: add reviewer in feedback (#765) Yuante Li 2025-04-08 16:20:13 +08:00
  • 3741611ebe feat: add reviewer in feedback (#765) Yuante Li 2025-04-08 16:20:13 +08:00
  • a918f941dd add hypothesis table (#764) XianBW 2025-04-07 20:16:37 +08:00
  • ceffbb165a add hypothesis table (#764) XianBW 2025-04-07 20:16:37 +08:00
  • dee11fbd9c fix: duplicate model names test in pipeline coder & runner (#763) XianBW 2025-04-07 19:06:42 +08:00
  • e7f3cf97ec fix: duplicate model names test in pipeline coder & runner (#763) XianBW 2025-04-07 19:06:42 +08:00
  • 0dcc990bd4 fix: Set PYTHONPATH in env.run_ret_code call in FBWorkspace class (#755) you-n-g 2025-04-07 18:15:33 +08:00
  • 4c5020f67e fix: Set PYTHONPATH in env.run_ret_code call in FBWorkspace class (#755) you-n-g 2025-04-07 18:15:33 +08:00
  • 3f41e868b3 chore: data science scenario UI updates (#757) XianBW 2025-04-07 16:24:27 +08:00
  • f0d919f04c chore: data science scenario UI updates (#757) XianBW 2025-04-07 16:24:27 +08:00
  • fac39e5588 remove buggy info in hypothesis rank (#762) Roland Minrui 2025-04-07 14:09:36 +08:00
  • 743f070d48 remove buggy info in hypothesis rank (#762) Roland Minrui 2025-04-07 14:09:36 +08:00
  • fce5342ad4 pretrained & validation alignment (#761) Xu Yang 2025-04-06 23:29:41 -06:00
  • 8dd0b74da5 pretrained & validation alignment (#761) Xu Yang 2025-04-06 23:29:41 -06:00
  • 44ada185f4 feat: add naive experiment generator and update proposal configurations (#759) you-n-g 2025-04-07 13:01:29 +08:00
  • 6be6b8408f feat: add naive experiment generator and update proposal configurations (#759) you-n-g 2025-04-07 13:01:29 +08:00
  • 6818ada2cf fix: fix some minor bugs (#758) Yuante Li 2025-04-04 23:54:54 +08:00
  • ebff475f14 fix: fix some minor bugs (#758) Yuante Li 2025-04-04 23:54:54 +08:00
  • 11e8acc88b feat: add a check for whether values in score_df are NaN (#756) Yuante Li 2025-04-04 22:44:55 +08:00
  • 0a75a4d987 feat: add a check for whether values in score_df are NaN (#756) Yuante Li 2025-04-04 22:44:55 +08:00
  • 9415113e01 feat: add reasoning_effort parameter to LiteLLMAPIBackend and LLMSett… (#754) you-n-g 2025-04-04 19:37:40 +08:00
  • 121628173f feat: add reasoning_effort parameter to LiteLLMAPIBackend and LLMSett… (#754) you-n-g 2025-04-04 19:37:40 +08:00
  • d3414ea07d fix: task_gen for better understanding (#752) Xu Yang 2025-04-04 03:09:26 -06:00
  • be29254345 fix: task_gen for better understanding (#752) Xu Yang 2025-04-04 03:09:26 -06:00
  • 8bd2714814 feat: joblib cache (#749) Tim 2025-04-04 12:08:18 +08:00
  • 43c8ed2aaf feat: joblib cache (#749) Tim 2025-04-04 12:08:18 +08:00
  • 200764d38b workflow entrypoint check (#748) Tim 2025-04-04 12:07:46 +08:00
  • 7f82894fc2 workflow entrypoint check (#748) Tim 2025-04-04 12:07:46 +08:00
  • c1c1342a9e chore(main): release 0.4.0 (#454) v0.4.0 you-n-g 2025-04-04 11:51:31 +08:00
  • fce638942d chore(main): release 0.4.0 (#454) you-n-g 2025-04-04 11:51:31 +08:00
  • 756dfba53f fix: fix kaggle templates path error (#747) Linlang 2025-04-04 11:20:33 +08:00
  • cd5681ea96 fix: fix kaggle templates path error (#747) Linlang 2025-04-04 11:20:33 +08:00
  • 1f0032bc50 fix when score is a string (#750) Xu Yang 2025-04-03 09:48:38 -06:00
  • af9582a0a7 fix when score is a string (#750) Xu Yang 2025-04-03 09:48:38 -06:00
  • 9eded6faa8 feat: add hypothesis guidelines and rule-based ranking (#746) Roland Minrui 2025-04-03 18:48:28 +08:00
  • 1e43ffcbfc feat: add hypothesis guidelines and rule-based ranking (#746) Roland Minrui 2025-04-03 18:48:28 +08:00
  • 8783781daa refactor: Improve data handling and representation in eval tests and prompts (#740) you-n-g 2025-04-03 13:53:25 +08:00
  • d82442f2ed refactor: Improve data handling and representation in eval tests and prompts (#740) you-n-g 2025-04-03 13:53:25 +08:00
  • da8fbcf4ee feat: add pipeline coder (#742) Roland Minrui 2025-04-03 13:00:11 +08:00
  • 6cc1e5da3c feat: add pipeline coder (#742) Roland Minrui 2025-04-03 13:00:11 +08:00
  • 22ed8b522b fix: fix KeyError direct_exp_gen (#735) Linlang 2025-04-03 12:01:10 +08:00
  • 6b09ade605 fix: fix KeyError direct_exp_gen (#735) Linlang 2025-04-03 12:01:10 +08:00
  • 7fc5e73f76 fix: replace func "len()" in ensemble test code to support various data type (#739) Haoran Pan 2025-04-02 19:52:54 +08:00
  • f752cf5a48 fix: replace func "len()" in ensemble test code to support various data type (#739) Haoran Pan 2025-04-02 19:52:54 +08:00
  • e30768969d feat: add describe_data_folder_v2 (#738) Yuante Li 2025-04-02 19:38:43 +08:00
  • 66e484101b feat: add describe_data_folder_v2 (#738) Yuante Li 2025-04-02 19:38:43 +08:00
  • bc8e9dc23a costeer max loop as hyperp & skip workflow in eval (#737) Xu Yang 2025-04-02 00:18:42 -06:00
  • f18c1828c8 costeer max loop as hyperp & skip workflow in eval (#737) Xu Yang 2025-04-02 00:18:42 -06:00
  • 1474478768 feat: new exp gen v2 implementation (#725) Roland Minrui 2025-04-02 13:37:47 +08:00
  • 1db6063345 feat: new exp gen v2 implementation (#725) Roland Minrui 2025-04-02 13:37:47 +08:00
  • 260b563710 feat: loader prompt & simplify YAML loading and update data loader specifications (#736) you-n-g 2025-04-01 22:36:25 +08:00
  • 3d6ae62ad5 feat: loader prompt & simplify YAML loading and update data loader specifications (#736) you-n-g 2025-04-01 22:36:25 +08:00
  • 3ef0b21350 chore: split dsapp to pages & add llm_logs showing (#733) XianBW 2025-04-01 20:55:10 +08:00
  • 67ee1a90bd chore: split dsapp to pages & add llm_logs showing (#733) XianBW 2025-04-01 20:55:10 +08:00
  • 473b9000b9 feat: update prompts and descriptions for data science components (#731) you-n-g 2025-04-01 20:54:42 +08:00
  • cc063dd646 feat: update prompts and descriptions for data science components (#731) you-n-g 2025-04-01 20:54:42 +08:00
  • 00b31fa752 fix: fix a bug in regular expression exception processing (#734) Yuante Li 2025-04-01 16:54:05 +08:00
  • c5dcd3b704 fix: fix a bug in regular expression exception processing (#734) Yuante Li 2025-04-01 16:54:05 +08:00
  • cc8ae7e1f0 update wechat group qrcode (#732) Haoran Pan 2025-03-31 19:20:04 +08:00
  • 9a6e18ad82 update wechat group qrcode (#732) Haoran Pan 2025-03-31 19:20:04 +08:00
  • 752de9dc67 feat: add a tool to enable saving workspace files into a specific folder (#728) Yuante Li 2025-03-28 16:22:27 +08:00
  • 7ee5bc2e19 feat: add a tool to enable saving workspace files into a specific folder (#728) Yuante Li 2025-03-28 16:22:27 +08:00
  • a99276d59b feat: track and log accumulated completion cost in LiteLLMAPIBackend (#727) you-n-g 2025-03-28 12:24:19 +08:00
  • aa8ceed2fa feat: track and log accumulated completion cost in LiteLLMAPIBackend (#727) you-n-g 2025-03-28 12:24:19 +08:00
  • 450571e86e fix: add metric name check for valid scores (#724) XianBW 2025-03-27 19:36:57 +08:00
  • b13575dc69 fix: add metric name check for valid scores (#724) XianBW 2025-03-27 19:36:57 +08:00
  • 7fc9e18a71 feat: make spec optional (#719) XianBW 2025-03-27 17:17:41 +08:00
  • 7733841f1c feat: make spec optional (#719) XianBW 2025-03-27 17:17:41 +08:00
  • 031d264957 docs: Add note on running Docker without sudo in installation guides (#721) you-n-g 2025-03-27 10:28:06 +08:00
  • 487ea4f6bf docs: Add note on running Docker without sudo in installation guides (#721) you-n-g 2025-03-27 10:28:06 +08:00
  • 6da6fb5ee5 refactor: remove unused code and update documentation in CoSTEER module (#720) Linlang 2025-03-26 22:48:01 +08:00
  • 78757aeed7 refactor: remove unused code and update documentation in CoSTEER module (#720) Linlang 2025-03-26 22:48:01 +08:00
  • 525b1a2136 update wechat qrcode (#718) Haoran Pan 2025-03-25 22:23:33 +08:00
  • 11df79d5e3 update wechat qrcode (#718) Haoran Pan 2025-03-25 22:23:33 +08:00
  • 61813cba67 chore: update data science scenario UI (#717) XianBW 2025-03-21 18:11:06 +08:00
  • 9bc4d8d1d6 chore: update data science scenario UI (#717) XianBW 2025-03-21 18:11:06 +08:00
  • b33be5ed5b docs: add contributing guidelines for rdagent (#710) Hamza Bouajila 2025-03-21 08:56:13 +01:00