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

Create a new AsyncOpenai client for each request #434

Merged
merged 1 commit into from
Dec 14, 2023

Conversation

rlouf
Copy link
Member

@rlouf rlouf commented Dec 14, 2023

The client currently returns a TimeOutError after many requests. This seems to be a problem on the OpenAI side, but we provide this temporary fix so the OpenAI integration works fine in Outlines. Fixes #428

The client currently returns a `TimeOutError` after many requests. This
seems to be a problem on the OpenAI side, but we provide this temporary
fix so the OpenAI integration works fine in Outlines.
Copy link
Contributor

@HerrIvan HerrIvan left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Very big improvement in performance. I cannot say that it recovers after a timeout, because it doesn't timeout anymore. Workflows where before there was a 100% chance of throwing a timeout are now completed.

@rlouf
Copy link
Member Author

rlouf commented Dec 14, 2023

Good news, I'm merging and cutting a new release!

@rlouf rlouf merged commit ec94e7a into main Dec 14, 2023
5 checks passed
@rlouf rlouf deleted the temp-fix-openai-timeouts branch December 14, 2023 10:39
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

openai models do not complete any further requests after throwing an APITimeoutError
2 participants