Token counter regression #83
Merged
Conversation
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
gaya3-zipstack
requested review from
a team,
Deepak-Kesavan,
chandrasekharan-zipstack and
jaseemjaskp
and removed request for
a team
gaya3-zipstack
commented
Aug 6, 2024
chandrasekharan-zipstack
approved these changes
Aug 6, 2024
jaseemjaskp
approved these changes
Aug 6, 2024
Deepak-Kesavan
approved these changes
Aug 6, 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Outdated suggestions cannot be applied.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.
What
Token counter was broken aftre latest llama-index upgrade.
Why
Llama index has overhauled the token counting objects internally causing us to make compatible changes.. The same was pushed with SDK 0.41.0. However, that had some regressions where in it was failing for non OpenAI models.
How
Changed the token counting functions in accordance with latest class attributes and functions.
Relevant Docs
Related Issues or PRs
Dependencies Versions / Env Variables
Notes on Testing
Tested for a bunch of models of Open AI, VertexAI, Anthropic, Mistral.
Ollama was not tested due to some setup issues and lack of time.
AnyScal also is not tested as the set up is no longer working. Need to migrate to the latest AnyScale infra
Screenshots
From token_usage table
Checklist
I have read and understood the Contribution Guidelines.