Commit Graph

39 Commits

Author SHA1 Message Date
merwanehamadi
0e804e27dd Add more data challenges (#5390)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-28 19:30:08 -07:00
SwiftyOS
4f15b1c582 Fix pathing issues 2023-09-28 12:29:03 +02:00
SwiftyOS
f0087ab80a fix artifact bug 2023-09-28 12:01:02 +02:00
SwiftyOS
5360313271 Fixed CORS and proxy timeout issues 2023-09-28 11:39:15 +02:00
merwanehamadi
37fbb52d19 Add more challenges + cleanup (#5368)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-27 17:58:58 -07:00
merwanehamadi
793ff1c163 Add data challenges (#5361)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-27 10:47:34 -07:00
merwanehamadi
e0aa11f4d7 Duplicate tasks created (#5358)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-27 07:41:51 -07:00
merwanehamadi
fa9fc18e22 Validate skill tree so the UI never breaks (#5306)
Validate skill tree to prevent it from breaking the UI

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-22 17:32:05 -07:00
merwanehamadi
a0e383f4d9 Fix skill tree (#5303)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-22 13:09:57 -07:00
merwanehamadi
18e576cb53 Structure challenges (#5296) 2023-09-21 20:06:37 -07:00
merwanehamadi
f67a352937 Add categories skill tree (#5295)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-21 17:39:16 -07:00
merwanehamadi
f4e7b1c61c Add eval_id and sync Skill Tree with Frontend(#5287)
Add eval_id to skill tree

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-21 13:36:17 -07:00
merwanehamadi
ff4c76ba00 Make agbenchmark a proxy of the evaluated agent (#5279)
Make agbenchmark a Proxy of the evaluated agent

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-20 16:06:00 -07:00
merwanehamadi
c09a0e7afa Implement old polling mechanism (#5248)
Implement old polling mechanism

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-18 16:23:06 -07:00
merwanehamadi
2cf350b783 Agent Protocol v1 (#5254)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-18 11:09:55 -07:00
merwanehamadi
f4d319cee4 Refactor benchmark (#5247)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-17 06:55:20 -07:00
merwanehamadi
f76d45cd9e Remove start from agbenchmark (#5241)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-16 17:22:49 -07:00
merwanehamadi
ece9e85b41 Add agent protocol within agbenchmark (#5239)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-16 15:31:12 -07:00
merwanehamadi
b101fec16b Add ability to run multiple tests (#5233)
Add multiple tests

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-16 13:01:11 -07:00
merwanehamadi
991e816ea2 Fix CORS issue (#5232)
* Allow Cors

* Update app.py
2023-09-16 10:56:21 -07:00
merwanehamadi
295702867a Ability to run by categories (#5229)
* Ability to run by categories

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

* always use Path.cwd()

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>

---------

Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-15 20:04:12 -07:00
merwanehamadi
b4401cd409 add benchmark endpoints mock (#5221)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-15 08:48:12 -07:00
merwanehamadi
6342a77037 Fix SDK client (#5214) 2023-09-13 20:25:58 -07:00
merwanehamadi
4bb86c0cb5 Support agent protocol in benchmark (#5213)
Benchmark/Forge/Agent Protocol
2023-09-13 18:50:39 -07:00
merwanehamadi
52c8b53122 Fix API Mode (#5209) 2023-09-13 07:30:46 -07:00
Luke
d319473e3c Fix TestUrlShortener to prevent conflicting test.py file and clarify instructions (#5177) 2023-09-13 06:11:40 -07:00
SwiftyOS
ed172dec19 fixed datetime and changed benchmark defaults for autogpt 2023-09-13 13:47:26 +02:00
SwiftyOS
9eb01d85a3 fixed multiple report folder bug 2023-09-13 12:18:04 +02:00
SwiftyOS
d44a4f591d Added ability to keep answers 2023-09-13 11:56:31 +02:00
SwiftyOS
bacd0e5e4e Added answers to the report 2023-09-13 10:40:55 +02:00
merwanehamadi
b2fc8f2a06 Integrate benchmark and autogpt (#5208)
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-12 19:30:45 -07:00
Merwane Hamadi
1b14d304d4 Benchmark changes
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-12 12:13:39 -07:00
Merwane Hamadi
c7550ba845 benchmark-fix 2023-09-11 21:37:23 -07:00
SwiftyOS
c73e90c4e6 Fixing benchmarks 2023-09-11 17:41:27 -07:00
Merwane Hamadi
fa888bfafa Add back api mode
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-06 22:51:45 -07:00
Merwane Hamadi
bc14028294 Add benchmark CI
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-06 19:50:24 -07:00
Merwane Hamadi
81bdcb9477 Fix forge and benchmark 2023-09-05 16:58:09 -07:00
Merwane Hamadi
66719e4c78 Cleanup 2023-09-05 16:34:55 -07:00
Auto-GPT-Bot
45c15e370f Auto-GPT-20230905085638
Signed-off-by: Merwane Hamadi <merwanehamadi@gmail.com>
2023-09-05 10:10:03 -07:00