Commit Graph

89 Commits (b53ed6a190caf603055ce7ddde813ff658bb7af3)

Author SHA1 Message Date
merwanehamadi c4554225bd
Update submodules (#212)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-29 10:18:35 -07:00
Silen Naihin ecc386ec7b
returning scores (#210)
Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
2023-07-29 11:43:22 +01:00
Silen Naihin f07e7b60d4
Advanced LLM Evaluation Implementation (#205)
Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>
2023-07-29 10:26:19 +01:00
merwanehamadi 80bd0c4260
Fix tests not being run (#207)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-27 20:50:53 -07:00
merwanehamadi 6098b70408
Use beebot autopackai (#203)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-27 12:21:43 -07:00
merwanehamadi 31897e7892
Delete reports (#201) 2023-07-27 11:42:24 -07:00
Silen Naihin 71e0c598d6 forcing AGENT_NAME to be defined from repo 2023-07-27 14:28:11 +01:00
Silen Naihin 0e6be16d07 helicone and llm eval fixes 2023-07-27 14:07:46 +01:00
merwanehamadi eb57b15380
Add dynamic headers using environment variables (#200)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-26 21:26:03 -07:00
merwanehamadi 5df710fd35
Add helicone dynamic headers (#199)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-26 16:03:13 -07:00
Silen Naihin 66d1fec07e attempting more logs 2023-07-26 23:36:45 +01:00
merwanehamadi 01b118e590
Add llm eval (#197)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-26 14:00:24 -07:00
Silen Naihin 80506e9a3b
report # bug, adding submodule challenges (#193) 2023-07-26 13:53:10 +01:00
merwanehamadi a1e02f243c
Add safety suite (#196)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-25 20:13:01 -07:00
Silen Naihin 5e3bbb946f
fix suite dependencies (#194) 2023-07-26 01:50:53 +01:00
Silen Naihin b82277515f
hotfix reports (#191) 2023-07-25 19:07:24 +01:00
Silen Naihin d9b3d7da37
Safety challenges, adaptability challenges, suite same_task (#177) 2023-07-24 13:57:44 -07:00
Silen Naihin 2b3abeff4e
Integrate baby-agi (#168)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
2023-07-21 11:15:42 -07:00
Erik Peterson 5a3b4f3d1d
Kill subprocesses when test ends (#172)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-20 15:41:59 -07:00
Silen Naihin 12c5d54583
Fixing memory challenges, naming, testing mini-agi, smooth retrieval scaling (#166) 2023-07-17 19:41:58 -07:00
merwanehamadi 2d8fa5ca6f
Use report location (#165) 2023-07-17 20:15:10 -04:00
Silen Naihin 8aa6452cc4
file naming when --test (#164) 2023-07-17 11:24:16 -04:00
Silen Naihin dffc1dfd51
internal_info.json dynamic changes (#163) 2023-07-17 09:39:24 -04:00
Silen Naihin ce4cefe7e7
Dynamic home path for runs (#119) 2023-07-16 18:24:06 -07:00
merwanehamadi 2704bcee5e
Allow change location of reports (#115)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-16 07:26:36 -07:00
Silen Naihin 9f3a2d4f05
Dynamic cutoff and other quality of life (#101) 2023-07-15 22:10:20 -04:00
merwanehamadi 5886d75059
Add three sum challenge (#108)
Co-authored-by: Silen Naihin <silen.naihin@gmail.com>
2023-07-15 19:52:42 -04:00
Erik Peterson cbd2e49d97
Clean up workspace between each test (#109) 2023-07-15 16:23:49 -07:00
merwanehamadi 7bc7d9213d
Replace hidden files with custom python (#99)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-14 14:39:47 -07:00
merwanehamadi a9702e4629
Add basic code generation challenge (#98) 2023-07-14 13:27:48 -04:00
merwanehamadi 78df4915cf
Remove dependencies if a specific test is asked by the user (#95)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-12 14:35:12 -07:00
Silen Naihin 8d0c5179ed
fixing backslashes, adding basic metrics (#89) 2023-07-12 01:37:59 -04:00
merwanehamadi b3c506cd94
Fix Auto-GPT looping forever (#87) 2023-07-11 20:02:29 -04:00
merwanehamadi 4ecb70c5e3
Fix Auto-GPT integration by adding python module as entrypoint (#86)
Co-authored-by: Silen Naihin <silen.naihin@gmail.com>
2023-07-11 15:11:24 -04:00
merwanehamadi 0799be7e28
Fix tests ci (#82) 2023-07-10 21:54:25 -07:00
Silen Naihin 8df82909b2
Added --test, consolidate files, reports working (#83) 2023-07-10 19:25:19 -07:00
merwanehamadi 437e066a66
Add "Simple web server" challenge (#74)
Co-authored-by: Silen Naihin <silen.naihin@gmail.com>
2023-07-10 20:46:03 -04:00
merwanehamadi 30ba51593f
Add Helicone (#81) 2023-07-10 12:19:12 -04:00
Silen Naihin b8830f8625
Adding search interface challenge and cleaning repo (#80) 2023-07-09 18:33:08 -07:00
Silen Naihin 3d43117554
Just json, no test files (#77) 2023-07-09 17:27:21 -07:00
merwanehamadi 573130549f
Add gpt engineer to ci (#78) 2023-07-09 13:31:31 -07:00
merwanehamadi d89264998d
Fix debug code challenge (#76)
Co-authored-by: Silen Naihin <silen.naihin@gmail.com>
2023-07-08 21:46:37 -04:00
Silen Naihin 69bd41f741
Quality of life improvements & fixes (#75) 2023-07-08 18:43:38 -07:00
Silen Naihin e56b112aab
i/o workspace, adding superagi (#60) 2023-07-08 03:27:31 -04:00
merwanehamadi 487f99f8f2
Use artifacts out insted of python code (#72) 2023-07-07 15:49:37 -07:00
merwanehamadi f0f7d2be90
Fix memory challenge 2 (#71) 2023-07-07 15:38:50 -07:00
merwanehamadi e34c83ca1c
Add .txt to memory challenges (#70) 2023-07-07 15:34:57 -07:00
Erik Peterson 3defe044bd
Print out all of stdout on each process poll. (#69) 2023-07-07 15:02:08 -07:00
Silen Naihin 4562bc6caf
Update data.json remove text 2023-07-07 17:54:09 -04:00
merwanehamadi e61523e59e
Get rid of get file path by using the data.json convention to store the challenge information (#67)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-07-07 13:58:17 -07:00