T3C-433 Evaluate GPT-5-mini #283
Conversation
| {"role": "system", "content": req.llm.system_prompt}, | ||
| {"role": "user", "content": full_prompt}, | ||
| ], | ||
| temperature=0.0, |
There was a problem hiding this comment.
This parameter is no longer supported by gpt-5
| HEADERS_TIMEOUT: 120000, | ||
| BODY_TIMEOUT: 120000, | ||
| KEEP_ALIVE_TIMEOUT: 30000, | ||
| REQUEST_TIMEOUT: 12000000, |
There was a problem hiding this comment.
These are just placeholders to get the thing to work, I didn't do any profiling or anything to get to these numbers.
|
🚀 Ephemeral Environment Deployed Frontend: https://dev-t3c-next-client-pr-283-6hx7a5impq-uc.a.run.app This environment will be automatically cleaned up when the PR is closed or merged. |
|
🚀 Ephemeral Environment Deployed Frontend: https://dev-t3c-next-client-pr-283-6hx7a5impq-uc.a.run.app This environment will be automatically cleaned up when the PR is closed or merged. |
|
🚀 Ephemeral Environment Deployed Frontend: https://dev-t3c-next-client-pr-283-6hx7a5impq-uc.a.run.app This environment will be automatically cleaned up when the PR is closed or merged. |
3 similar comments
|
🚀 Ephemeral Environment Deployed Frontend: https://dev-t3c-next-client-pr-283-6hx7a5impq-uc.a.run.app This environment will be automatically cleaned up when the PR is closed or merged. |
|
🚀 Ephemeral Environment Deployed Frontend: https://dev-t3c-next-client-pr-283-6hx7a5impq-uc.a.run.app This environment will be automatically cleaned up when the PR is closed or merged. |
|
🚀 Ephemeral Environment Deployed Frontend: https://dev-t3c-next-client-pr-283-6hx7a5impq-uc.a.run.app This environment will be automatically cleaned up when the PR is closed or merged. |
|
🚀 Ephemeral Environment Deployed Frontend: https://dev-t3c-next-client-pr-283-6hx7a5impq-uc.a.run.app This environment will be automatically cleaned up when the PR is closed or merged. |
1. What is the goal of this PR?
This PR updates code to use GPT-5-mini model
2. What specific parts of T3C are you changing and how?
Pyserver and Express-Server to make requests with the gpt-5-mini model
3. How did you test these changes?
Local/ephemeral report generation
Please add one or more reviewer(s) and tag them in a new post in the Slack dev channel :)