[Firebase AI] Implement new public API surface and tests

[andrewheard]

Updated the FirebaseAI API surface to allow a Backend to be specified:

public static func firebaseAI(app: FirebaseApp? = nil, backend: Backend = .googleAI()) -> FirebaseAI

public struct Backend {
  public static func vertexAI(location: String = "us-central1") -> Backend
  public static func googleAI() -> Backend
}

#no-changelog

[gemini-code-assist]

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

[google-oss-bot]

	1 Warning
⚠️	New public headers were added, did you remember to add them to the umbrella header?

Generated by 🚫 Danger

[andrewheard]

/gemini review

[gemini-code-assist]

Code Review

This pull request introduces a new public API surface for the FirebaseAI SDK, allowing developers to specify a Backend for the AI models. The changes include the addition of a Backend struct with options for Vertex AI and Google AI, and updates to the FirebaseAI class to utilize this new backend configuration. The tests have also been updated to reflect these changes. Overall, the changes look good and introduce a valuable feature.

Summary of Findings

• Assertion Usage: The assertions in FirebaseAI.swift verify that the instance is configured with the production endpoint and the correct version. While these are good for development, consider if they should be removed or modified for production code to avoid unexpected crashes.
• Naming Consistency: The naming of the internal initializer firebaseAI(app:location:apiConfig:) in FirebaseAI.swift is a bit confusing, as it shares the same name as the public API. Consider renaming the internal initializer to something more descriptive, like createFirebaseAIInstance.
• Documentation Improvements: The documentation for the Backend struct and its methods could be expanded to provide more clarity on when to use each backend option and the implications of choosing one over the other.

Merge Readiness

The pull request is almost ready for merging. I recommend addressing the naming consistency issue and considering the assertion usage in production code. Expanding the documentation for the Backend struct would also be beneficial. I am unable to approve this pull request, and other reviewers should review and approve this code before merging.