feat(py): Add fastAPI plugin and sample

[huangjeff5]

Plugin exposes:

• genkit_fastapi_handler - Decorator for serving Genkit flows via FastAPI.
• genkit_lifespan - For serving dev UI + FastAPI server together.

[gemini-code-assist]

Summary of Changes

Hello @huangjeff5, 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 adds a FastAPI plugin to Genkit, allowing developers to easily expose Genkit flows as HTTP endpoints within FastAPI applications. It also provides a sample application called BugBot, which showcases how to use the plugin for AI-powered code reviews, including security, bug, and style analysis. The changes include the plugin code, a sample application, and necessary configurations to integrate with Genkit's Dev UI.

Highlights

• FastAPI Plugin: Introduces a new plugin for Genkit that enables serving Genkit flows as FastAPI endpoints.
• Sample Application: Includes a sample FastAPI application (BugBot) demonstrating the plugin's usage for AI-powered code reviews.
• Dev UI Integration: The plugin and sample application are designed to integrate with Genkit's Dev UI for debugging and development.

🧠 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.

Changelog

• py/plugins/fastapi/init.py
  • Exposes the genkit_fastapi_handler and genkit_lifespan functions for easy import.
  • Defines the package_name function to return the package name.
• py/plugins/fastapi/handler.py
  • Introduces the genkit_fastapi_handler decorator for serving Genkit flows via FastAPI.
  • Defines the _FastAPIRequestData class to wrap FastAPI request data for Genkit context.
• py/plugins/fastapi/lifespan.py
  • Adds the genkit_lifespan function to create a FastAPI lifespan that registers with Genkit Dev UI.
  • Includes a function to find a free port for the reflection server.
• py/samples/fastapi-hello/prompts/analyze_bugs.prompt
  • Adds a prompt for analyzing code for bugs and logical errors.
  • Specifies the model and output format (JSON).
• py/samples/fastapi-hello/prompts/analyze_diff.prompt
  • Adds a prompt for reviewing code diffs for security, bugs, and style issues.
  • Includes logic for handling additional context.
• py/samples/fastapi-hello/prompts/analyze_security.prompt
  • Adds a prompt for analyzing code for security vulnerabilities.
  • Specifies the model and output format (JSON).
• py/samples/fastapi-hello/prompts/analyze_style.prompt
  • Adds a prompt for analyzing code for style and best practice issues.
  • Specifies the model and output format (JSON).
• py/samples/fastapi-hello/src/main.py
  • Implements a FastAPI application (BugBot) that uses Genkit flows for code review.
  • Defines API endpoints for code review, security analysis, and diff analysis.
  • Integrates with genkit_fastapi_handler to expose flows directly.

Activity

• huangjeff5 added a FastAPI plugin and sample application for Genkit.

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.

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

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. ↩

[gemini-code-assist]

Code Review

This pull request introduces a new FastAPI plugin for Genkit, along with a sample application demonstrating its usage. The implementation is well-structured and provides a good foundation for integrating Genkit flows with FastAPI. I've identified a few areas for improvement, including a potential race condition in development mode, some API inconsistencies, and a bug in the sample application's request handling. The suggested changes aim to improve robustness, API consistency, and correctness of the provided example.