Add openai client support for tinker backend #475
Conversation
Summary of ChangesHello @chenyushuo, 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 preliminary support for using the OpenAI client with the Tinker backend. It addresses the current incompleteness of Tinker's native OpenAI-compatible API by implementing a custom routing mechanism that directs OpenAI client chat completion requests to Tinker's internal chat method. This allows for immediate integration and testing of Tinker models via an OpenAI-like interface, with a clear path to transition to Tinker's official API once it becomes stable. Highlights
🧠 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 AssistThe 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
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 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
|
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request adds support for the Tinker backend, including a custom implementation to work around Tinker's incomplete OpenAI-compatible API. The changes are extensive, touching model wrappers, configurations, and tests. The refactoring of the test setup is a good improvement for extensibility. However, I've identified a critical issue in the OpenAI client patching logic, significant code duplication, and a few other areas for improvement, such as removing leftover debug code and avoiding in-place modification of arguments. Addressing these points will enhance the code's robustness and maintainability.
|
/unittest-module-common |
Summary
Skipped
Tests
Github Test Reporter by CTRF 💚 |
2 participants
Description
As the title says.
Currently, Tinker's OpenAI-compatible API implementation is still incomplete. Instead, we're using our custom
self.chat()method to replicate the functionality ofopenai.OpenAI.chat.completions.create().Once Tinker's API is fully implemented and stable, we plan to switch to using this official endpoint directly.
Checklist
Please check the following items before code is ready to be reviewed.