Fix incorrect import path in batch processor initialization

[keyuchen21]

Summary

Fixes #766

This PR corrects an incorrect import path that prevented the batch API feature from working.

Problem

When users tried to enable the batch API with the --enable_batch_api flag, the router would crash with a ModuleNotFoundError because the import statement was referencing a non-existent module path.

Incorrect import (line 9):

from vllm_router.batch.local_processor import LocalBatchProcessor

The directory vllm_router/batch/ does not exist in the codebase.

Solution

Changed the import to use the correct path where LocalBatchProcessor actually exists:

from vllm_router.services.batch_service.local_processor import LocalBatchProcessor

Impact

• Unblocks the batch API functionality which was completely unusable due to this import error
• Users can now successfully use the --enable_batch_api flag
• No breaking changes or API modifications
• Single-line fix with zero risk

Testing

• Verified that src/vllm_router/services/batch_service/local_processor.py exists and contains the LocalBatchProcessor class
• Searched the entire codebase to confirm no other files reference the incorrect import path
• Confirmed the import statement follows Python module structure conventions

[gemini-code-assist]

Summary of Changes

Hello @keyuchen21, 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 a critical issue where the batch API feature was completely unusable due to an incorrect module import path. By correcting a single line of code, the PR enables the batch API to function as intended, resolving a ModuleNotFoundError and ensuring the feature is accessible without any adverse effects on the existing system.

Highlights

• Critical Bug Fix: This pull request resolves a ModuleNotFoundError that was preventing the batch API feature from being enabled and used.
• Import Path Correction: The fix involves correcting an incorrect import path for LocalBatchProcessor from vllm_router.batch.local_processor to the correct vllm_router.services.batch_service.local_processor.
• Batch API Unblocked: The change unblocks the batch API functionality, making it fully usable for users who enable it with the --enable_batch_api flag.
• Minimal Impact: This is a single-line fix with no breaking changes or API modifications, ensuring zero risk to existing functionality.

🧠 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

This pull request correctly fixes a ModuleNotFoundError by updating an incorrect import path for LocalBatchProcessor. The change is direct and effectively resolves the bug that was crashing the router when the batch API was enabled. I have one suggestion to improve the maintainability of the code by using a relative import, since the imported module is within the same package.

[keyuchen21]

@zerofishnoodles i think now it should be good to go now

previous code:
from vllm_router.services.batch_service.local_processor import LocalBatchProcessor

change to:
from vllm_router.services.batch_service.local_processor import (
LocalBatchProcessor,
)

[zerofishnoodles]

LGTM! Thanks for the contribution!