feat(py/genkit): initial implementation of reranker

[yesudeep]

CHANGELOG:

• Adds ai.define_reranker
• Adds tests.

[gemini-code-assist]

Summary of Changes

Hello @yesudeep, 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 delivers the initial implementation of reranker functionality for the genkit library. It provides the necessary infrastructure and API methods to integrate reranking models, which are crucial for enhancing the quality of Retrieval-Augmented Generation (RAG) pipelines by reordering retrieved documents based on their relevance to a given query. The changes include new type definitions, core logic, and user-facing methods, along with examples and tests to ensure proper functionality and demonstrate usage.

Highlights

• New Reranker Functionality: Introduced the core reranker capabilities, allowing users to define and use reranking models to reorder documents based on relevance to a query within RAG pipelines.
• New API Methods: Added ai.define_reranker for registering custom reranker functions and ai.rerank for executing reranking operations against a query and a list of documents.
• Comprehensive Testing: Included a new test file with extensive unit tests covering the RankedDocument class, reranker definition, and the rerank function, including examples of custom rerankers and two-stage retrieval patterns.

🧠 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.

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 the initial implementation for rerankers in Genkit, a valuable addition for RAG pipelines. The changes include the core reranker block logic, registration with the AI registry, and comprehensive tests. The code is well-structured, but I've identified a few areas for improvement, mainly concerning potential side effects from in-place dictionary modifications and some opportunities for code cleanup. My detailed comments are below.