Skip to content

Conversation

@Jeffwan
Copy link
Collaborator

@Jeffwan Jeffwan commented Oct 25, 2025

Pull Request Description

This PR implements Phase 2 improvements for the batch API, addressing GitHub issues #1651, #1652, #1653, and #1654. All changes maintain full backward compatibility with the OpenAI Batch API specification.

Related Issues

Resolves: part of #1644

Important: Before submitting, please complete the description above and review the checklist below.


Contribution Guidelines (Expand for Details)

We appreciate your contribution to aibrix! To ensure a smooth review process and maintain high code quality, please adhere to the following guidelines:

Pull Request Title Format

Your PR title should start with one of these prefixes to indicate the nature of the change:

  • [Bug]: Corrections to existing functionality
  • [CI]: Changes to build process or CI pipeline
  • [Docs]: Updates or additions to documentation
  • [API]: Modifications to aibrix's API or interface
  • [CLI]: Changes or additions to the Command Line Interface
  • [Misc]: For changes not covered above (use sparingly)

Note: For changes spanning multiple categories, use multiple prefixes in order of importance.

Submission Checklist

  • PR title includes appropriate prefix(es)
  • Changes are clearly explained in the PR description
  • New and existing tests pass successfully
  • Code adheres to project style and best practices
  • Documentation updated to reflect changes (if applicable)
  • Thorough testing completed, no regressions introduced

By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.

@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @Jeffwan, 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 delivers Phase 2 improvements to the batch API, focusing on enhancing file management, job execution control, and API endpoint coverage. It introduces a new file listing API for better visibility into uploaded data, allows for dynamic configuration of batch job concurrency, and refines error handling by providing dedicated output files for failed requests. Additionally, the batch API's capabilities are expanded to support more OpenAI-compatible endpoints, all while maintaining backward compatibility.

Highlights

  • File List API: Introduced a new API endpoint (/v1/files) to list uploaded files with filtering by purpose, pagination, and limit capabilities, enhancing file management and discoverability.
  • Configurable Job Pool Size: The batch job scheduler's concurrency can now be configured via the AIBRIX_BATCH_JOB_POOL_SIZE environment variable, allowing administrators to fine-tune resource utilization and performance.
  • Dedicated Error File Handling: Batch jobs now explicitly prepare separate output and error files for results, improving the clarity and handling of failed requests by segregating successful and unsuccessful responses.
  • Expanded Batch API Endpoints: The batch API now supports /v1/completions and /v1/embeddings in addition to /v1/chat/completions, broadening its utility and compatibility with OpenAI specifications.
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.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request introduces several enhancements to the batch API, including support for file listing, configurable job pool size, and error file handling. The changes include modifications to documentation, constants, storage adapters, and API endpoints. I have provided comments addressing a potential issue with exception handling in the list_files function.

Comment on lines +311 to +313
except Exception as e:
logger.error("Failed to list files", error=str(e)) # type: ignore[call-arg]
raise HTTPException(status_code=500, detail="Failed to list files")
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

The current implementation catches all exceptions but raises an HTTPException with a generic message. This obscures the original error, making debugging difficult. It would be better to either re-raise the original exception or include the original error message in the HTTPException.

Consider logging the full exception traceback for better debugging.

logger.exception("Failed to list files", error=str(e))
Suggested change
except Exception as e:
logger.error("Failed to list files", error=str(e)) # type: ignore[call-arg]
raise HTTPException(status_code=500, detail="Failed to list files")
logger.exception("Failed to list files", error=str(e)) # Log the full exception with traceback
raise HTTPException(status_code=500, detail=f"Failed to list files: {str(e)}")

@Jeffwan Jeffwan merged commit 43b4b9a into vllm-project:main Oct 25, 2025
11 checks passed
@Jeffwan Jeffwan deleted the jiaxin/batch-api-phase-2 branch October 25, 2025 08:56
xvoron pushed a commit to xvoron/aibrix that referenced this pull request Oct 29, 2025
…ile handling (vllm-project#1700)

* Make DEFAULT_JOB_POOL_SIZE configurable
* Implement the file listing API
* Added comprehensive docstring to prepare_job_ouput_files()
* Create tests to cover batch API supported endpoints
* Update the batch api docs

Signed-off-by: Jiaxin Shan <[email protected]>
Signed-off-by: Artyom Voronin <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant