genkit: support for upcoming unified plugin #8957
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @ifielker, 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 introduces support for an upcoming unified Genkit plugin, primarily focusing on how Genkit projects are initialized and configured. It updates versioning logic to recognize and utilize the new plugin, refactors internal data structures for handling models and plugins, and introduces a new Firebase template that aligns with the unified plugin's capabilities and modern Firebase Functions practices. The changes ensure that new Genkit projects can seamlessly integrate with the unified Google AI and Vertex AI plugin, simplifying setup and improving consistency.
Highlights
- Genkit Versioning Updates: The
GenkitInfointerface now includes agenaiVersionfield, and thegetGenkitInfofunction has been updated to fetch and populate this version, indicating support for the new unified plugin. - Template Versioning and Unified Plugin Activation: The minimum supported Genkit version (
MIN_VERSION) has been updated to "1.0.0-rc.1". Crucially, new logic has been added to detect Genkit versions 1.17.0 and above, along withgenaiVersion0.0.2-rc.1, to activate the new "1.17.0" template for unified plugin support. - Refactored Plugin and Model Configuration: The internal structures for handling plugins and models (
PluginInfo,ModelOption) have been refactored. A newgetPluginInfohelper function simplifies retrieving plugin details. ThepluginToInfoconstant now includes specific configurations for the unified@genkit-ai/google-genaiplugin, differentiating between Vertex AI and Google AI providers. - Improved Sample File Generation: The
generateSampleFilefunction, responsible for creating the initialindex.tsfile, has been updated to use the newModelOptionandPluginInfostructures. This streamlines the generation of model imports, comments, and plugin configurations in the sample code. - Updated Firebase Template: The old
firebase.0.9.0.templatehas been removed and replaced withfirebase.1.17.0.template. The new template reflects modern Firebase Functions practices, includingonCallGenkitfor callable functions,defineSecretfor API key management, and a refactored flow definition usingai.defineFlowandai.generateStreamfor streaming responses.
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 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.
You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.
Footnotes
-
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. ↩
There was a problem hiding this comment.
Code Review
This pull request adds support for the new unified Genkit plugin (@genkit-ai/google-genai). The changes correctly detect the new plugin and select the appropriate template version. The logic for handling plugin information has been refactored to be more centralized, which improves code clarity. I've found one critical issue that could lead to a crash during initialization when no model provider is selected. Please see my detailed comment.
github-project-automation
bot
moved this to Approved [PR]
in [Cloud] Extensions + Functions
No description provided.