docs(go): update RAG samples and sections

[hugoaguirre]

• Fixed outdated RAG samples
• Refined Go code blocks

[gemini-code-assist]

Summary of Changes

Hello @hugoaguirre, 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 focuses on enhancing the accuracy and clarity of the Go-based RAG documentation. It addresses outdated code examples and refines existing code blocks to ensure they align with the latest Genkit API practices, making the documentation more reliable and easier to follow for users implementing RAG flows.

Highlights

• RAG Sample Updates: Outdated Go RAG (Retrieval Augmented Generation) samples within the documentation have been fixed to reflect current Genkit API usage.
• Go Code Block Refinements: Go code blocks for RAG examples were refined, including explicit Genkit and vector store initialization, and correct usage of genkit.Retrieve and genkit.GenerateText.
• Documentation Clarity: Improved clarity in the RAG documentation by adding necessary setup steps and clarifying the implementation of custom retrievers.

Changelog

• src/content/docs/docs/rag.mdx
  • Corrected a heading from 'Supported retrievers, and embedders' to 'Supported retrievers and embedders'.
  • Added a new section 'Initialize Genkit and Vector Store' with Go code for setting up the Genkit instance and local vector store.
  • Updated the indexer flow example to correctly use localvec.Index for adding chunks to the vector store.
  • Refactored the RAG flow example by removing redundant initialization code and updating ai.Retrieve to genkit.Retrieve and ai.WithDocs to resp.Documents... for genkit.GenerateText.
  • Modified the custom retriever example to use genkit.DefineRetriever with a simplified path and updated ai.Retrieve to genkit.Retrieve with ai.WithRetriever and ai.WithConfig.
  • Added a note clarifying that the rerank function is a placeholder and not provided by the Genkit framework.

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 provides valuable updates to the Go RAG documentation. The changes effectively fix outdated code samples, correct several bugs, and improve the overall structure and clarity of the document. The updated API calls, such as for genkit.Retrieve, and the completion of the indexing flow make the examples much more practical and easier for developers to follow. The refactoring of initialization code also enhances readability. Overall, these are excellent improvements to the documentation.