Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up
Appearance settings

Remove the abstraction for token counting from the main evaluation API#6320

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 ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Merged
shyamnamboodiripad merged 2 commits intodotnet:mainfromshyamnamboodiripad:counter
Apr 23, 2025

Conversation

@shyamnamboodiripad
Copy link
Contributor

@shyamnamboodiripadshyamnamboodiripad commentedApr 18, 2025
edited
Loading

This change is being made because there is still some uncertainty around what a general-purpose token counting abstraction (that supports all kinds of future models, and all kinds of input modalities) should look like at the moment. We do not want to bake in an API that only supports text-based inputs for the models and use cases that are prevalent today, since it would be a potential breaking change to change this API after we release a stable version of the evaluation APIs.

We can always reintroduce the token counting support in a non-breaking fashion in the future if and when there is more clarity on what a general-purpose token counting abstraction should look like, or if and when a general-purpose token counting abstraction is introduced in a lower layer (Microsoft.Extensions.AI) in the future.

In the meanwhile, callers should still be able to use theMicrosoft.ML.Tokenizers library directly to count tokens in text-based content and trim down the conversation history before callingEvaluateAsync() if needed.

Fixes#6234

Microsoft Reviewers:Open in CodeFlow

@shyamnamboodiripadshyamnamboodiripad requested a review froma team as acode ownerApril 18, 2025 08:55
@github-actionsgithub-actionsbot added the area-ai-evalMicrosoft.Extensions.AI.Evaluation and related labelApr 18, 2025
@shyamnamboodiripadshyamnamboodiripadforce-pushed thecounter branch 2 times, most recently from7511ebe tof93c418CompareApril 18, 2025 21:35
@shyamnamboodiripadshyamnamboodiripadforce-pushed thecounter branch 2 times, most recently frombd3f9b0 to987b057CompareApril 22, 2025 21:05
This change is being made because there is still some uncertainty around what a general purpose token counting abstraction (that supports all kinds of future models, and all kinds of input modalities) should look like at the moment. We do not want to bake in an API that only supports text based inputs for the models and use cases that are prevalent today, since it would be a potential breaking change to change this API after we release a stable version of the evaluation APIs.We can always reintroduce the token counting support in a non-breaking fashion in the future if and when there is more clarity on what a general purpose token counting abstraction should look like, or if and when a general purpose token counting abstraction is introduced in a lower layer (Microsoft.Extensions.AI) in the future.In the meanwhile, callers should still be able to use the Microsoft.ML.Tokenizers library directly to count tokens in text-based content and trim down the conversation history before calling EvaluateAsync() if needed.
@shyamnamboodiripadshyamnamboodiripad merged commit44eaa2e intodotnet:mainApr 23, 2025
6 checks passed
@shyamnamboodiripadshyamnamboodiripad deleted the counter branchApril 23, 2025 17:44
@github-actionsgithub-actionsbot locked and limited conversation to collaboratorsMay 24, 2025
Sign up for freeto subscribe to this conversation on GitHub. Already have an account?Sign in.

Reviewers

@peterwaldpeterwaldpeterwald approved these changes

Labels

area-ai-evalMicrosoft.Extensions.AI.Evaluation and related

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

[AI Evaluation] Rationalize IEvaluationTokenCounter interface

2 participants

@shyamnamboodiripad@peterwald

[8]ページ先頭

©2009-2025 Movatter.jp