Making the token count check do both max_tokens and context_window ch… #1008
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
…ecks to ensure an error is thrown even when max_tokens is below context window
gecBurton
reviewed
Sep 2, 2024
|
|
||
| if total_tokens > max_tokens_allowed: | ||
| return "max_exceeded" | ||
| elif total_tokens > token_budget_remaining_in_context: |
There was a problem hiding this comment.
Suggested change
| elif total_tokens > token_budget_remaining_in_context: | |
| if total_tokens > token_budget_remaining_in_context: |
gecBurton
reviewed
Sep 2, 2024
| return "max_exceeded" | ||
| elif total_tokens > token_budget_remaining_in_context: | ||
| return "context_exceeded" | ||
| else: |
gecBurton
approved these changes
Sep 2, 2024
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Outdated suggestions cannot be applied.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.
We were previously only check max_tokens when the request total tokens exceeded the context window. To avoid confusing situations with the interaction of these env vars both are now always checked so that an error is thrown when the total tokens exceeds the max regardless of whether it's more or less than the context window
Changes proposed in this pull request
A new decision node returns a request handler name from 'max_exceeded'/'context_exceeded'/'pass' rather than two boolean checks in serial. This allows moving to the correct next node in all situationss
Guidance to review
Ignore the reformatting in django-app. Must have missed a Ruff pass on a previous PR
Things to check