Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Bug]: Remove support for openai.chat.completions.create(..., n>1) everywhere #821

Open
1 task done
creatorrr opened this issue Nov 9, 2024 · 1 comment
Open
1 task done
Assignees

Comments

@creatorrr
Copy link
Contributor

creatorrr commented Nov 9, 2024

📜 Description

So the problem is that if you use n>1, api will return more than one result in the {"choices": [...]} but then:

  1. how do you unwrap?
  2. if there's a tool-call, how do you handle it as in which choice's tool-call should you use?
  3. no one really uses choices anymore (reasoning models don't support it either)

Possible solutions

  1. Remove support from typespec and rewrite (simplify) the prompt step logic
  2. Just consider tool-calls with n>1 as wait for input

👀 Have you spent some time to check if this bug has been raised before?

  • I checked and didn't find similar issue
@creatorrr creatorrr added the bug Something isn't working label Nov 9, 2024
@creatorrr creatorrr removed the bug Something isn't working label Jan 20, 2025
@creatorrr creatorrr changed the title [Bug]: Remove support for n>1 everywhere [Bug]: Remove support for openai.chat.completions.create(..., n>1) everywhere Feb 15, 2025
@creatorrr
Copy link
Contributor Author

@whiterabbit1983 thoughts?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants