Skip to content

Add Google Search and Thinking support to firebase-ai#2

Open
Enterup649 wants to merge 1 commit intomainfrom
feat/gemini-features-9528094249912010653
Open

Add Google Search and Thinking support to firebase-ai#2
Enterup649 wants to merge 1 commit intomainfrom
feat/gemini-features-9528094249912010653

Conversation

@Enterup649
Copy link
Copy Markdown
Owner

This submission adds support for Google Search retrieval and Thinking configuration to the firebase-ai module.

Key changes:

  • Created ThinkingConfig.kt to define the thinking configuration.
  • Updated Tool.kt to include googleSearchRetrieval support.
  • Updated GenerationConfig.kt to include thinkingConfig in the generation parameters.
  • Ensured all internal data classes use @SerialName for correct API mapping.
  • Resolved build environment issues to verify implementation.

PR created automatically by Jules for task 9528094249912010653 started by @Enterup649

Introduces ThinkingConfig and updates Tool and GenerationConfig to support
Gemini 2.0 features. Includes Google Search grounding and Thinking configuration.
Properly handles internal serialization with SerialName annotations.

Co-authored-by: Enterup649 <201156730+Enterup649@users.noreply.github.com>
@google-labs-jules
Copy link
Copy Markdown

👋 Jules, reporting for duty! I'm here to lend a hand with this pull request.

When you start a review, I'll add a 👀 emoji to each comment to let you know I've read it. I'll focus on feedback directed at me and will do my best to stay out of conversations between you and other bots or reviewers to keep the noise down.

I'll push a commit with your requested changes shortly after. Please note there might be a delay between these steps, but rest assured I'm on the job!

For more direct control, you can switch me to Reactive Mode. When this mode is on, I will only act on comments where you specifically mention me with @jules. You can find this option in the Pull Request section of your global Jules UI settings. You can always switch back!

New to Jules? Learn more at jules.google/docs.


For security, I will only act on instructions from the user who triggered this task.

@github-actions
Copy link
Copy Markdown

Firebase AI Mock Responses Check ⚠️

A newer major version of the mock responses for Firebase AI unit tests is available. update_responses.sh should be updated to clone the latest version of the responses: v16.2

@github-actions
Copy link
Copy Markdown

📝 PRs merging into main branch

Our main branch should always be in a releasable state. If you are working on a larger change, or if you don't want this change to see the light of the day just yet, consider using a feature branch first, and only merge into the main branch when the code complete and ready to be released.

@gemini-code-assist
Copy link
Copy Markdown

Summary of Changes

Hello, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the firebase-ai module by introducing advanced AI model capabilities. It enables the model to leverage Google Search for information retrieval and provides granular control over its internal 'thinking' process. These additions expand the model's ability to interact with external data sources and offer more transparent or detailed responses, ultimately making the AI more powerful and configurable for various use cases.

Highlights

  • Google Search Retrieval Support: Added the capability to configure Google Search retrieval as a tool for the AI model, allowing it to access external information.
  • Thinking Configuration: Introduced a new ThinkingConfig to control how the model processes information, including an option to include the model's internal thoughts in responses.
  • GenerationConfig Integration: Integrated the new ThinkingConfig into the GenerationConfig builder, allowing users to specify thinking parameters during model generation.
  • Serialization Enhancements: Ensured all new and modified internal data classes use @SerialName for accurate mapping to API fields, improving serialization robustness.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Copy Markdown

@gemini-code-assist gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request adds support for Google Search and Thinking configuration to the firebase-ai module. The changes are generally well-implemented, introducing new configuration classes and updating existing ones to support the new features. I've identified a potential breaking change in the serialization logic for Tool and suggested a fix to maintain API compatibility. I also recommended a small improvement to the new ThinkingConfig class to align it better with Kotlin best practices.

) {
internal fun toInternal() =
Internal(
functionDeclarations = functionDeclarations?.map { it.toInternal() },
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

This change alters the serialization of functionDeclarations. Previously, a null list was sent as an empty array ([]). Now, it will be null and likely omitted from the JSON payload. This is a potential breaking change for the backend API. To maintain API compatibility, the previous behavior of sending an empty list should be preserved.

Suggested change
functionDeclarations = functionDeclarations?.map { it.toInternal() },
functionDeclarations = functionDeclarations?.map { it.toInternal() } ?: emptyList(),

Comment on lines +28 to +30
public class ThinkingConfig(
public val includeThoughts: Boolean = false,
) {
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

For better usability and adherence to Kotlin idioms for value-holding classes, consider converting ThinkingConfig into a data class. This will automatically provide equals(), hashCode(), toString(), and copy() methods, which is useful for a configuration object.

Suggested change
public class ThinkingConfig(
public val includeThoughts: Boolean = false,
) {
public data class ThinkingConfig(
public val includeThoughts: Boolean = false,
) {

@github-actions
Copy link
Copy Markdown

Test Results

0 tests   0 ✅  0s ⏱️
0 suites  0 💤
0 files    0 ❌

Results for commit 1a086c0.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant