Skip to content

feat: Add a universal OpenAI API #251

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 17 commits into from
Aug 6, 2025
Merged

feat: Add a universal OpenAI API #251

merged 17 commits into from
Aug 6, 2025

Conversation

lu-yg
Copy link
Collaborator

@lu-yg lu-yg commented Aug 6, 2025

English | 简体中文

PR

PR Checklist

Please check if your PR fulfills the following requirements:

  • The commit message follows our Commit Message Guidelines
  • Tests for the changes have been added (for bug fixes / features)
  • Docs have been added / updated (for bug fixes / features)
  • Built its own designer, fully self-validated

PR Type

What kind of change does this PR introduce?

  • Bugfix
  • Feature
  • Code style update (formatting, local variables)
  • Refactoring (no functional changes, no api changes)
  • Build related changes
  • CI related changes
  • Documentation content changes
  • Other... Please describe:

Background and solution

What is the current behavior?

Issue Number: N/A

What is the new behavior?

Does this PR introduce a breaking change?

  • Yes
  • No

Other information

Summary by CodeRabbit

  • New Features

    • Introduced a new AI chat completion API endpoint supporting both standard and streaming responses.
    • Added support for server-sent events (SSE) to enable real-time streaming of AI chat responses.
    • Provided configurable OpenAI-compatible API settings, including API key, base URL, model, and timeout.
    • Added a new data structure for chat requests with customizable parameters.
    • Integrated streaming response handling for efficient delivery of chat completions.
    • Enhanced error reporting with a new message for stream data write failures.
  • Bug Fixes

    • Improved error handling for stream data writing failures with a new error message.

Copy link

coderabbitai bot commented Aug 6, 2025

Walkthrough

This change introduces a new AI chat completion feature with support for streaming responses via server-sent events (SSE). It adds a new REST endpoint, DTO, service interface and implementation, a custom HTTP message converter for streaming, and configuration for OpenAI-compatible APIs. Exception handling and enums are updated to support stream write errors.

Changes

Cohort / File(s) Change Summary
AI Chat Streaming Feature: Controller, Service, DTO
base/src/main/java/com/tinyengine/it/controller/AiChatController.java, base/src/main/java/com/tinyengine/it/model/dto/ChatRequest.java, base/src/main/java/com/tinyengine/it/service/app/v1/AiChatV1Service.java, base/src/main/java/com/tinyengine/it/service/app/impl/v1/AiChatV1ServiceImpl.java
Adds a new REST endpoint /chat/completions for AI chat, with a ChatRequest DTO and a service interface/implementation supporting both standard and streaming (SSE) responses. Handles exceptions and integrates with OpenAI-compatible APIs.
Streaming Response Converter & WebConfig
base/src/main/java/com/tinyengine/it/common/converter/StreamingResponseBodyConverter.java, app/src/main/java/com/tinyengine/it/config/filter/WebConfig.java
Introduces a custom StreamingResponseBodyConverter for handling StreamingResponseBody with text/event-stream and integrates it into Spring MVC via WebConfig.
OpenAI API Configuration
base/src/main/java/com/tinyengine/it/config/OpenAIConfig.java
Adds a configuration class for OpenAI-compatible API settings, including API key, base URL, default model, and timeout.
Exception Enum Update
base/src/main/java/com/tinyengine/it/common/exception/ExceptionEnum.java
Adds a new exception enum value CM326 for stream data write failures.

Sequence Diagram(s)

sequenceDiagram
    participant Client
    participant AiChatController
    participant AiChatV1Service
    participant OpenAI API
    participant StreamingResponseBodyConverter

    Client->>AiChatController: POST /chat/completions (ChatRequest)
    AiChatController->>AiChatV1Service: chatCompletion(request)
    alt request.stream == true
        AiChatV1Service->>OpenAI API: POST chat/completions (stream=true)
        OpenAI API-->>AiChatV1Service: Streaming response (SSE)
        AiChatV1Service-->>AiChatController: StreamingResponseBody
        AiChatController-->>StreamingResponseBodyConverter: StreamingResponseBody
        StreamingResponseBodyConverter-->>Client: SSE data stream
    else request.stream == false
        AiChatV1Service->>OpenAI API: POST chat/completions (stream=false)
        OpenAI API-->>AiChatV1Service: JSON response
        AiChatV1Service-->>AiChatController: JsonNode
        AiChatController-->>Client: JSON response
    end
Loading

Estimated code review effort

🎯 4 (Complex) | ⏱️ ~40 minutes

Poem

In fields of code where rabbits hop,
A streaming chat now will not stop!
With SSE and clever beans,
Configs and DTOs in between,
We chat with AI, swift and neat—
Streaming responses, what a treat!
🐇💬✨

Note

⚡️ Unit Test Generation is now available in beta!

Learn more here, or try it out under "Finishing Touches" below.


📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 75d535e and 55af856.

📒 Files selected for processing (2)
  • base/src/main/java/com/tinyengine/it/config/OpenAIConfig.java (1 hunks)
  • base/src/main/java/com/tinyengine/it/controller/AiChatController.java (4 hunks)
🚧 Files skipped from review as they are similar to previous changes (2)
  • base/src/main/java/com/tinyengine/it/config/OpenAIConfig.java
  • base/src/main/java/com/tinyengine/it/controller/AiChatController.java
✨ Finishing Touches
  • 📝 Generate Docstrings
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share
🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

  • Review comments: Directly reply to a review comment made by CodeRabbit. Example:
    • I pushed a fix in commit <commit_id>, please review it.
    • Explain this complex logic.
    • Open a follow-up GitHub issue for this discussion.
  • Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
    • @coderabbitai explain this code block.
  • PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
    • @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
    • @coderabbitai read src/utils.ts and explain its main purpose.
    • @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Support

Need help? Create a ticket on our support page for assistance with any issues or questions.

CodeRabbit Commands (Invoked using PR comments)

  • @coderabbitai pause to pause the reviews on a PR.
  • @coderabbitai resume to resume the paused reviews.
  • @coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
  • @coderabbitai full review to do a full review from scratch and review all the files again.
  • @coderabbitai summary to regenerate the summary of the PR.
  • @coderabbitai generate docstrings to generate docstrings for this PR.
  • @coderabbitai generate sequence diagram to generate a sequence diagram of the changes in this PR.
  • @coderabbitai generate unit tests to generate unit tests for this PR.
  • @coderabbitai resolve resolve all the CodeRabbit review comments.
  • @coderabbitai configuration to show the current CodeRabbit configuration for the repository.
  • @coderabbitai help to get help.

Other keywords and placeholders

  • Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
  • Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
  • Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (.coderabbit.yaml)

  • You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
  • Please see the configuration documentation for more information.
  • If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

  • Visit our Documentation for detailed information on how to use CodeRabbit.
  • Join our Discord Community to get help, request features, and share feedback.
  • Follow us on X/Twitter for updates and announcements.

Copy link

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 13

🧹 Nitpick comments (3)
app/src/main/java/com/tinyengine/it/config/filter/WebConfig.java (2)

40-41: Use English for code comments to maintain consistency.

The Chinese comment should be in English to match the codebase's language standards.

-        // 添加自定义的 StreamingResponseBody 转换器
+        // Add custom StreamingResponseBody converter

34-36: Add defensive null check for the injected converter.

While Spring should handle this, adding a null check would make the code more robust.

 public WebConfig(StreamingResponseBodyConverter streamingResponseBodyConverter) {
+    this.streamingResponseBodyConverter = Objects.requireNonNull(
+        streamingResponseBodyConverter, "StreamingResponseBodyConverter cannot be null");
-    this.streamingResponseBodyConverter = streamingResponseBodyConverter;
 }

Add the import:

+import java.util.Objects;
base/src/main/java/com/tinyengine/it/common/converter/StreamingResponseBodyConverter.java (1)

55-55: Use English for code comments.

For consistency and international collaboration, use English for inline comments.

-        responseBody.writeTo(outputStream); // 使用 StreamingResponseBody 的 writeTo 方法
+        responseBody.writeTo(outputStream); // Use StreamingResponseBody's writeTo method
📜 Review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between aaf776b and 75d535e.

📒 Files selected for processing (8)
  • app/src/main/java/com/tinyengine/it/config/filter/WebConfig.java (2 hunks)
  • base/src/main/java/com/tinyengine/it/common/converter/StreamingResponseBodyConverter.java (1 hunks)
  • base/src/main/java/com/tinyengine/it/common/exception/ExceptionEnum.java (1 hunks)
  • base/src/main/java/com/tinyengine/it/config/OpenAIConfig.java (1 hunks)
  • base/src/main/java/com/tinyengine/it/controller/AiChatController.java (4 hunks)
  • base/src/main/java/com/tinyengine/it/model/dto/ChatRequest.java (1 hunks)
  • base/src/main/java/com/tinyengine/it/service/app/impl/v1/AiChatV1ServiceImpl.java (1 hunks)
  • base/src/main/java/com/tinyengine/it/service/app/v1/AiChatV1Service.java (1 hunks)
🔇 Additional comments (1)
app/src/main/java/com/tinyengine/it/config/filter/WebConfig.java (1)

34-36: LGTM! Clean dependency injection implementation.

The constructor injection and field assignment follow Spring best practices correctly.

@hexqi hexqi merged commit 0fd760c into opentiny:develop Aug 6, 2025
1 check passed
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.

2 participants