Backoff when OpenAI returns 5xx #354
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi! Thanks for creating and maintaining async-openai. I noticed during the outtages last weekend that the client is not dealing with server errors as is instructed by OpenAI.
I'm fairly certain these are new instructions, on this page you can see:
https://platform.openai.com/docs/guides/error-codes
That they are now advising to retry (after a delay) on any server error.
It is slightly more involved than that, because I also noticed that it is sometimes (always?) the case that they do not return JSON on server errors, so instead of parsing JSON, we need to create the
ApiErrorourselves by simply inserting the whole response body into the message.