- Notifications
You must be signed in to change notification settings - Fork845
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
Uh oh!
There was an error while loading.Please reload this page.
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
7511ebe tof93c418Comparesrc/Libraries/Microsoft.Extensions.AI.Evaluation/Microsoft.Extensions.AI.Evaluation.csproj OutdatedShow resolvedHide resolved
Uh oh!
There was an error while loading.Please reload this page.
src/Libraries/Microsoft.Extensions.AI.Evaluation/ChatMessageExtensions.cs OutdatedShow resolvedHide resolved
Uh oh!
There was an error while loading.Please reload this page.
test/Libraries/Microsoft.Extensions.AI.Evaluation.Tests/ConversationTrimmingTests.cs OutdatedShow resolvedHide resolved
Uh oh!
There was an error while loading.Please reload this page.
bd3f9b0 to987b057CompareThis 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.
peterwald approved these changesApr 23, 2025
44eaa2e intodotnet:main 6 checks passed
Uh oh!
There was an error while loading.Please reload this page.
Sign up for freeto subscribe to this conversation on GitHub. Already have an account?Sign in.
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.
Uh oh!
There was an error while loading.Please reload this page.
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.Tokenizerslibrary 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