Do not cache fully empty completion responses or those with empty contents#465
Draft
caufieldjh wants to merge 2 commits into
Draft
Do not cache fully empty completion responses or those with empty contents#465caufieldjh wants to merge 2 commits into
caufieldjh wants to merge 2 commits into
Conversation
Member
Author
|
Need a newer litellm version to be able to do more cache manipulation - see https://github.com/BerriAI/litellm/blob/81157aa13593a02e8d34ec1ef47a777f347a5b68/litellm/caching/caching.py#L722C15-L722C32 |
caufieldjh
changed the title
Member
Author
|
This is being actively changed in litellm so I'm actually going to hold off on further updates to this PR |
This file contains hidden or 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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Caching empty responses can be an issue when we're running numerous documents.
This adds two cases where an error may be raised after prompt completion:
result: