[feat] embedding config

[suluyana]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello, 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 significantly enhances the configurability of the application's embedding model. By externalizing the embedding model ID and cache directory into environment variables, users gain greater flexibility in customizing the underlying embedding technology. This change streamlines deployment, simplifies model management, and improves the overall adaptability of the system to different embedding requirements.

Highlights

• Externalized Embedding Configuration: Introduced EMBEDDING_MODEL_ID and EMBEDDING_CACHE_DIR environment variables to allow users to specify their preferred embedding model and cache location.
• API Integration: Integrated the new embedding configuration variables into the API settings, making them discoverable and manageable via the application's settings endpoint.
• CLI Enhancements: Updated the command-line interface to include the new embedding configuration in the generated env.example file and to dynamically use these settings when preloading embedding models.
• Flexible Embedding Initialization: Refactored the AgenticSearch class to support injecting an EmbeddingUtil instance or initializing it dynamically based on the new environment variables, improving modularity and testability.
• Environment-Aware Embedding Utility: Modified the EmbeddingUtil class to automatically read model_id and cache_dir from environment variables if not explicitly provided during instantiation.

🧠 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.

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 configurability for the embedding model via environment variables (EMBEDDING_MODEL_ID and EMBEDDING_CACHE_DIR). The changes are well-implemented across the CLI, API, and core search logic. I've found two areas for improvement: one is a minor bug in the settings API where it reports an incorrect value for the embedding cache directory, and the other is a maintainability improvement to use a defined constant instead of a hardcoded string for the default model ID.