-
Notifications
You must be signed in to change notification settings - Fork 4.1k
feat(firebaseai): add responseJsonSchema
to GenerationConfig
#17564
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 our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
base: main
Are you sure you want to change the base?
Conversation
responseJsonSchema
to GenerationConfig
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
responseJsonSchema
to GenerationConfig
responseJsonSchema
to GenerationConfig
Thanks for the PR, would like to check if it has been tested under both vertexAI and googleAI backend. |
Yes, I've tested it on both backends. |
… use in GenerationConfig (firebase#17599) Expose ThinkingConfig class so that it can be used in GenerationConfig
The Developer API was missing support for parts, which was already implemented in the Vertex AI API. This change copies the parsing logic from the Vertex AI function to the function in the Developer API. An existing test file, , has been updated to include a test case for parsing parts, ensuring the functionality is working as expected.
…irebase#17607) * [Infra] Move FirebaseAuth imports to implementation files * Add module import
…17503) * add developer api to live * make the whole process going through * feat(firebase_ai): handle unknown parts when parsing content * tweak the content test * remove the extra exception * Make Live API sending tool response for function calling * update bidi model for googleAI in example * fix analyzer and test * more test fixing --------- Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
…ests (firebase#17612) * ci(firestore): add `--ignore-timeouts` flag for cloud firestore e2e tests * chore: set timeout-minutes value to 60 * remove --ignore-timeouts flag * revert change * chore: apply --ignore-timeouts to all iOS e2e tests * chore: apply --ignore-timeouts to android and macos e2e tests * chore: fix macos ci
* chore(release): publish packages - [email protected] - [email protected] - [email protected] - [email protected] - [email protected]+1 - [email protected] * chore: BoM Version 4.1.0
Okay, @cynthiajoan I added an example here that uses I also formatted the output a little better in the "chat" of the example, and updated the regular schema example to match. I also bumped the Gemini model versions in the example's main, since they were pretty old, but I'm happy to revert that if you wanted them to stay that way. |
Description
This adds the
responseJsonSchema
field to the GenerationConfig class, which enables more JSON schema features like$def
and$ref
along with other advanced JSON schema features that Gemini 2.5 supports.See the Gemini docs for more information about what is supported.
Related Issues
Checklist
Before you create this PR confirm that it meets all requirements listed below by checking the relevant checkboxes (
[x]
).This will ensure a smooth and quick review process. Updating the
pubspec.yaml
and changelogs is not required.///
).melos run analyze
) does not report any problems on my PR.Breaking Change
Does your PR require plugin users to manually update their apps to accommodate your change?