Jordan Henkel

This is awesome! It'd be great to support more of these parameters --- I know, personally, I'd love to see support for multiple completions from the model and support for...

One last request here if we're going to move forward with adding more parameters (ignoring the issues of somethings like `n` and `logits` not really being possible right now based...

Ahh I see, this is helpful thank you! The good news is, that w/ the Chat API PR I opened today, you should be able to cover this use case...

@Codie-Petersen sounds good! Thanks for the discussion and examples --- do checkout the Chat support when it gets merged, I think it covers your use case well (and shouldn't require...

I can reproduce this now! (I run an ubuntu desktop and WSL normally, but setup on regular Windows to reproduce this.) This issue seems to be the culprit: [https://github.com/microsoft/debugpy/issues/1246](https://github.com/microsoft/debugpy/issues/1246) For...

Okay, branch surgery done, feedback addressed, and I threw in a linter/formatter pass at the end as some of the files got out of sync with our formatting rules. @dluc...

This would be awesome to have! Looks great! (@alexchaomander and @dluc how do we want to do reviews on the Python side of things? Are there designated folks from the...

@AdityaGudimella I was able to run this locally via `act` to test things out, but only after a few small tweaks to the workflow. I'm not sure if they're necessary,...

@AdityaGudimella when I refer to testing here I just mean testing the workflow yml you wrote (not tests for the code). I was using this tool: https://github.com/nektos/act to verify things...

I want to chime in here and say that, based on other open source projects in the LLM space I've seen, using something like `pydantic` would align us more closely...