[Frontend] OpenAI Responses API supports input image

[chaunceyjiang]

Essential Elements of an Effective PR Description Checklist

• The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
• The test plan, such as providing test command.
• The test results, such as pasting the results comparison before and after, or e2e results
• (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

Purpose

Follow up #20504

https://platform.openai.com/docs/guides/images-vision?api-mode=responses

OpenAI Responses API supports input image

Test Plan

Added test cases.

[gemini-code-assist]

Summary of Changes

Hello @chaunceyjiang, 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 introduces support for image inputs within the OpenAI Responses API, allowing users to send images via URLs or base64 encoding. This enhancement expands the API's multimodal capabilities, enabling it to process visual information alongside text.

Highlights

• OpenAI Responses API Image Support: The API now accepts image inputs through a new input_image type, aligning with OpenAI's vision capabilities for multimodal models.
• Flexible Image Input Handling: Images can be provided either as direct URLs or as base64 encoded strings, offering versatility for different use cases.
• Robust Parsing Logic: New parsing mechanisms have been implemented in chat_utils.py to correctly interpret and process the ResponseInputImageParam type for multimodal content.
• Comprehensive Test Coverage: A new test suite has been added to validate the functionality for single and multiple image inputs, including adherence to configured image limits per prompt.

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. ↩

[github-actions]

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

🚀

[gemini-code-assist]

Code Review

This pull request adds support for image inputs to the OpenAI-compatible responses API. The changes in vllm/entrypoints/chat_utils.py correctly introduce a new parser for input_image and integrate it into the existing multi-modal content parsing logic. A new test file is added to verify the functionality with single and multiple images, both as URLs and base64 encoded data. I've found a critical issue in one of the new tests where an incorrect parameter name is used, which prevents the test from validating the intended success path.

[DarkLight1337]

LGTM, thanks!

[DarkLight1337]

The tests are failing, PTAL

[chaunceyjiang]

The tests are failing, PTAL

From the logs, it appears that vllm encountered an OOM (Out of Memory) error.
I’ve added some parameters to reduce GPU memory usage.

Could you help retry the e2e test?
@DarkLight1337

[mgoin]

LGTM, thanks for the tests