Include full GenerateContentRequest for countTokens #169
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
This will make the counted tokens aligned with what the model will count if the same request were made to `generateContent`. Extract the JSON conversion to a separate method and call it from `generateContent`, `generateContentStream`, and `countTokens`.
This is a member of the proto, but the backend reports an error if it is used in `countTokens`. Soften the changelog entry - since we are not sending the _exact_ same JSON to the backend I'm less confident making the promise that the behavior is aligned.
This reverts commit 3b7003a.
This reverts commit 0be8786.
Also add `model` to the general `GenerateContentRequest`. It is required when using that pattern for counting tokens.
devoncarew
approved these changes
May 22, 2024
Co-authored-by: Devon Carew <devoncarew@google.com>
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Outdated suggestions cannot be applied.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.
This will make the counted tokens aligned with what the model will count
if the same request were made to
generateContent.Extract the JSON conversion to a separate method and call it from
generateContent,generateContentStream, andcountTokens.