Commit Graph

60 Commits

Author SHA1 Message Date
merwanehamadi
101ffdbce0 Integrate with gpt engineer (#47) 2023-07-03 14:53:28 -04:00
merwanehamadi
07133fb041 Run regression tests on push to master and stable (#46) 2023-07-03 14:42:24 -04:00
merwanehamadi
838f72097c Add static linters ci (#45) 2023-07-02 16:14:49 -04:00
merwanehamadi
2062844fa6 Integrate one challenge to auto gpt (#44) 2023-07-02 10:38:30 -04:00
merwanehamadi
0f33416b0e Merge pull request #42 from Significant-Gravitas/feat/kill
adding hook to integrate agnostically
2023-06-30 09:45:45 -07:00
Silen Naihin
7c352b745e integrate config, agent_interface just func, hook 2023-06-30 11:55:43 -04:00
Silen Naihin
2987d71264 moving run agent to tests & agnostic run working 2023-06-30 10:50:54 -04:00
Silen Naihin
fce421fb33 moving logic to benchmark.py file 2023-06-29 20:51:23 -04:00
Silen Naihin
ac5af73696 trying to get kill process 2023-06-28 21:28:46 -04:00
Silen Naihin
0c81585a53 Update README.md (#41) 2023-06-27 22:17:42 -04:00
merwanehamadi
11303e2ef7 Merge pull request #40 from Significant-Gravitas/feat/basics
addition of basic challenges, easier challenge creation, --mock flag, adding mini-agi
2023-06-27 18:50:23 -07:00
Silen Naihin
76ee994d2c read mes, remove port and host from config, etc 2023-06-27 19:19:14 -04:00
Silen Naihin
f933717d8b mini-agi, simple challenge creation, --mock flag 2023-06-27 18:17:54 -04:00
Silen Naihin
36ef54340f Merge branch 'feat/basics' of https://github.com/Significant-Gravitas/Auto-GPT-Benchmarks into feat/basics 2023-06-27 13:26:39 -04:00
Silen Naihin
fa0df12439 mini agi attempt 2023-06-27 13:26:28 -04:00
Silen Naihin
d6a6e69f2e can now put file extensions or names in files data 2023-06-27 13:26:28 -04:00
Silen Naihin
2411c35d0e update regression tests info 2023-06-27 13:26:28 -04:00
Silen Naihin
a2f79760ce other was non solution, solution is pytest-depends 2023-06-27 13:26:28 -04:00
Silen Naihin
06a6f08054 finally figured out right way to do dependencies 2023-06-27 13:26:28 -04:00
Silen Naihin
2f28a66591 more elegant marking & dependency solution 2023-06-27 13:26:28 -04:00
Silen Naihin
60a7ac2343 adding dependencies on other challenges 2023-06-27 13:26:28 -04:00
Silen Naihin
22458a04e8 file creation from within file before server :) 2023-06-27 13:26:28 -04:00
Silen Naihin
8c44b9eddf basic challenges, more ChallengeData structure 2023-06-27 13:26:28 -04:00
Silen Naihin
a7972ad873 regression test creation 2023-06-27 13:25:47 -04:00
Silen Naihin
84f170c9e0 fixing relative imports 2023-06-26 09:36:13 -04:00
Silen Naihin
4be22ae5ab mini agi attempt 2023-06-26 09:27:20 -04:00
Silen Naihin
7604ae07bb can now put file extensions or names in files data 2023-06-25 19:30:04 -04:00
Silen Naihin
adc6b225a6 update regression tests info 2023-06-25 11:12:33 -04:00
Silen Naihin
31c1192719 other was non solution, solution is pytest-depends 2023-06-25 08:48:16 -04:00
Silen Naihin
d1c5e0a91a finally figured out right way to do dependencies 2023-06-25 00:22:53 -04:00
Silen Naihin
f895d54e02 more elegant marking & dependency solution 2023-06-24 14:42:35 -04:00
Silen Naihin
4fa9f72083 adding dependencies on other challenges 2023-06-24 12:24:17 -04:00
Silen Naihin
66c9e68b04 file creation from within file before server :) 2023-06-24 12:15:53 -04:00
Silen Naihin
a5073ab577 basic challenges, more ChallengeData structure 2023-06-24 09:42:36 -04:00
Silen Naihin
b6562f3420 Update README.md 2023-06-23 09:31:21 -04:00
Silen Naihin
ffd1d15a0e MockManager, mock_func in data.json (#39) 2023-06-23 07:53:57 -04:00
Silen Naihin
15c5469bb1 Add automatic regression markers (#38) 2023-06-22 08:18:22 -04:00
Silen Naihin
e5974ca3ea Delete file_to_check.txt 2023-06-21 11:44:59 -04:00
Silen Naihin
b7deb984f7 start click, fixtures, types, challenge creation, mock run -stable (#37) 2023-06-21 11:43:18 -04:00
Silen Naihin
04536e92a5 Merge pull request #34 from Significant-Gravitas/dsl 2023-06-20 18:32:58 -04:00
Silen Naihin
1eb278f3cc Update README.md 2023-06-19 09:53:30 -04:00
scarletpan
f37981c388 init first challenge template 2023-06-19 12:39:34 +00:00
Silen Naihin
51f2295971 init agbenchmark 2023-06-18 11:14:54 -04:00
Douglas Schonholtz
dfb73204bf Update readme to suggest people check out challenges 2023-05-05 16:33:39 -04:00
Douglas Schonholtz
04722e7fc5 EvalNames with dates for the eval run filename and compatibility with 0.3.0 (#26)
* EvalNames with dates and the eval run

* Ignore .idea files, update readme to use 3.10, updates for 0.3.0
2023-05-03 10:14:44 -04:00
Douglas Schonholtz
b8c7c05dd5 windows docs make workspace if not there (#25)
* windows docs make workspace if not there

* small fixes
2023-04-22 19:17:28 -04:00
Media
ef5c4f8a11 Graphs for evals (#20)
* Update README.md

* Jupyter Notebook for evaluating eval results

---------

Co-authored-by: Douglas Schonholtz <15002691+dschonholtz@users.noreply.github.com>
2023-04-20 19:04:34 -04:00
Douglas Schonholtz
011ed2f2b9 Update README.md (#17)
remove -m
2023-04-20 15:47:15 -04:00
Douglas Schonholtz
625d6e72ec Remove the submodule, reference OpenAI directly rather than running it on the command line, fix logging (#16)
* Removed submodule, refactor, docker on pip, async docker logging, running our own tool on CLI rather than OpenAIs
2023-04-20 15:41:29 -04:00
Douglas Schonholtz
f00ced6612 Update README.md 2023-04-18 11:59:42 -04:00