[OAI refactor] Add rerank and score serving

[woodx9]

Motivation

update score and rerank serving due to serving_base update
base on #7351

Modifications

Checklist

• Format your code according to the Code Formatting with Pre-Commit.
• Add unit tests as outlined in the Running Unit Tests.
• Update documentation / docstrings / example tutorials as needed, according to Writing Documentation.
• Provide throughput / latency benchmark results and accuracy evaluation results as needed, according to Benchmark and Profiling and Accuracy Results.
• For reviewers: If you haven't made any contributions to this PR and are only assisting with merging the main branch, please remove yourself as a co-author when merging the PR.
• Please feel free to join our Slack channel at https://slack.sglang.ai to discuss your PR.

[gemini-code-assist]

Summary of Changes

Hello @woodx9, 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 dedicated serving capabilities for "rerank" and "score" functionalities, integrating them into the existing OpenAI-like serving framework. It defines the necessary request and response protocols for reranking and establishes new service handlers to manage the lifecycle of these requests, from validation and internal conversion to processing and response formatting. This work refactors and expands the serving infrastructure to support these new types of requests, building upon a recent serving_base update.

Highlights

• New Rerank and Score Serving: Introduces new, dedicated serving handlers (OpenAIServingRerank and OpenAIServingScore) to manage reranking and scoring requests, respectively, integrating them into the existing OpenAI-like serving framework.
• Rerank Protocol Definition: Defines new protocol models (V1RerankReqInput and RerankResponse) in protocol.py for handling rerank requests and their corresponding responses, including query, documents, scores, and metadata.
• Internal Request Conversion Logic: Implements specific _convert_to_internal_request logic for both rerank (adapting to EmbeddingReqInput for cross-encoder processing) and score (passing requests directly to a specialized scoring method).
• Request Validation and Response Formatting: Each new serving handler includes logic for validating incoming requests and formatting the processed results into the appropriate OpenAI-like response structure, including sorting rerank results by score.
• Alignment with Serving Base: The changes align the rerank and score serving implementations with a common serving_base pattern, as indicated by the PR's motivation to update serving due to serving_base changes.

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 PR refactors the serving layer to add support for rerank and score endpoints. The changes introduce new serving handlers and update the protocol definitions. The method signatures and return types of the new handlers do not match the OpenAIServingBase abstract class, which will lead to runtime errors. A new request protocol model should inherit from Pydantic's BaseModel for consistency and to leverage FastAPI's features.