fix: include doc_type for image hit-testing

[LukaErnestini]

Summary

• include doc_type in default vector attributes for image hit-testing
• ensure image results map back to segments for retrieval

I've been facing the issue of not being able to do a retrieval by passing an image. I found this to be the reason.

[gemini-code-assist]

Summary of Changes

Hello @LukaErnestini, 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 addresses an issue in image hit-testing by incorporating the doc_type into the default vector attributes. This crucial addition facilitates the accurate mapping of image search results back to their originating segments, thereby enhancing the precision of retrieval-augmented generation (RAG) processes involving visual data.

Highlights

• Vector Attributes: Included doc_type in the default vector attributes for image hit-testing.
• Image Retrieval: Ensured image results map back to segments for retrieval, improving accuracy in RAG systems.

🧠 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

The pull request effectively addresses the requirement to include doc_type for image hit-testing by adding it to the default vector attributes. This change directly supports multimodal capabilities and enhances the accuracy of document retrieval based on type.

[gemini-code-assist]

The addition of doc_type to the default attributes list is a good improvement for multimodal support. To make this more precise and potentially avoid indexing doc_type for datasets that are not multimodal, consider making its inclusion conditional based on the dataset.is_multimodal property. This ensures that doc_type is only added when it's relevant, optimizing metadata storage and indexing for text-only datasets.

Suggested change

	attributes = ["doc_id", "dataset_id", "document_id", "doc_hash", "doc_type"]
	attributes = ["doc_id", "dataset_id", "document_id", "doc_hash"] + (["doc_type"] if dataset.is_multimodal else [])