add ray support for accelerating document information extraction

[alcholiclg]

Change Summary

1. Add ray support for accelerating hierarchical keyInformation information extraction.
2. Add conditional Ray import with serial fallback when Ray is unavailable.
3. Add multi-level fallback to serial logic when actor execution fails.
4. Support CPU allocation and worker count control.

Related issue number

Checklist

• The pull request title is a good summary of the changes - it will be used in the changelog
• Unit tests for the changes exist
• Run pre-commit install and pre-commit run --all-files before git commit, and passed lint check.
• Documentation reflects the changes where applicable

[gemini-code-assist]

Summary of Changes

Hello @alcholiclg, 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 enhances the document information extraction process by integrating the Ray distributed computing framework. The primary goal is to boost performance, especially when processing numerous files, through parallel execution. The changes introduce a new, optimized extraction mechanism that intelligently leverages Ray while providing robust fallback options to sequential processing, ensuring the system remains functional even if Ray is not available or encounters issues. This significantly improves the efficiency and scalability of key information extraction without compromising reliability.

Highlights

• Ray Integration for Acceleration: Introduced Ray support to significantly accelerate hierarchical key information extraction, enabling parallel processing of multiple documents.
• Robust Fallback Mechanism: Implemented conditional Ray import and multi-level fallbacks to sequential processing if Ray is unavailable or if Ray actor execution encounters failures, ensuring stability and graceful degradation.
• Configurable Resource Allocation: Added controls for CPU allocation per task and the number of Ray workers, allowing for optimized resource utilization based on system capabilities and workload.
• Optimized Extraction API: Created a new OptimizedKeyInformationExtraction class and a high-level extract_key_information function to encapsulate the Ray-accelerated logic and manage the fallback to sequential extraction.

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 support for accelerating document information extraction using Ray. The implementation includes a new OptimizedKeyInformationExtraction class that conditionally uses Ray for parallel processing and falls back to sequential execution if Ray is unavailable or fails. The changes are well-structured, providing a robust fallback mechanism. My review includes suggestions to correct some type hints and simplify the result-merging logic in the new Ray implementation for better clarity and efficiency. I also recommend refactoring the integration in the research workflow to reduce redundant logic and make better use of the new abstraction.