[perf] Batch rpyc calls in multimodal path

[SangChengC]

No description provided.

[gemini-code-assist]

Summary of Changes

Hello @SangChengC, 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 robustness and performance of inter-process communication, specifically with RPyC, within the system's multimodal embedding cache. It resolves potential serialization problems by configuring RPyC to allow pickle and introduces significant performance gains by converting numerous single-item cache interactions into efficient batch operations, thereby optimizing the processing of multimodal data.

Highlights

• RPyC Configuration: Enabled allow_pickle for all RPyC connections to ensure proper serialization and deserialization of complex Python objects, addressing potential communication issues.
• Cache System Optimization: Refactored the embedding cache manager to support batch operations for allocating, retrieving, and setting the status of multiple items simultaneously. This includes new alloc_batch, get_items_data, set_items_data, get_items_embed, and set_items_embed methods.
• Multimodal Data Processing Efficiency: Updated various client components (HTTP, Audio, Visual servers, and model RPCs) to leverage the new batch RPyC cache operations, significantly reducing network round trips and improving performance when handling multiple multimodal inputs like images and audio.

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 in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

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 issue 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 is currently in preview and 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 to provide feedback.

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 addresses an issue with rpyc and refactors the embedding cache logic to use batch operations. A critical bug was identified where audio embedding logic incorrectly uses data caching functions. Additionally, medium-severity issues were found, including an incorrect type hint and performance improvement opportunities in the cache implementation. The security implications of enabling pickle in rpyc were also noted.