Refactor workflow to async workflow#276
Conversation
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Summary of Changes
Hello @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 a significant refactoring effort to transition various core workflows and model interaction methods to an asynchronous programming paradigm. By converting synchronous operations to async functions and utilizing await for model calls, the change aims to improve the overall efficiency and responsiveness of the system, particularly in scenarios involving I/O-bound tasks like model inference. This refactor lays the groundwork for more scalable and non-blocking execution of workflows.
Highlights
- Asynchronous Workflow Execution: Many
runmethods across various workflow classes (e.g.,customized_math_workflows,customized_toolcall_workflows,RAFT_alfworld_workflow,RAFT_reflect_alfworld_workflow,alfworld_workflow,sciworld_workflow,webshop_workflow,eval_workflow,math_rm_workflow,math_ruler_workflow,simple_mm_workflow,workflow) have been refactored torun_asyncand marked asasync def. - Asynchronous Model Interactions: All synchronous calls to
self.model.chat(),self.model.generate(), andself.model.chat_mm()within the refactored workflows have been updated to their asynchronous counterparts,await self.model.chat_async(),await self.model.generate_async(), andawait self.model.chat_mm_async()respectively. - New Asynchronous Property for Workflows: A new
@property asynchronoushas been added to numerous workflow classes, returningTrue, indicating their support for asynchronous operation. - Asynchronous Model Version Retrieval: A new
model_version_asyncasynchronous property has been added toModelWrapperintrinity/common/models/model.pyto retrieve the model version asynchronously, which is then utilized inworkflow_runner.py. - Documentation Updates: Help text in
buffer_config_manager.pyhas been updated to reflect the transition frommodel.chat()tomodel.chat_async()in workflow descriptions.
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 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
-
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. ↩
There was a problem hiding this comment.
Code Review
This pull request refactors synchronous workflows to be asynchronous, which is a great improvement for performance. The changes are largely correct, converting run methods to async def run_async and using await for model calls. However, I've identified a few critical issues and a minor one. There's a recurring SyntaxError in get_model_response_text methods across several workflow files due to incorrect await usage, which will cause these workflows to fail. Additionally, there's an incorrect return type hint for an async property in model.py. Addressing these issues will ensure the refactoring is successful.
|
/unittest-module-common |
Summary
Tests
Github Test Reporter by CTRF 💚 |
|
/unittest-module-explorer |
Summary
Tests
Github Test Reporter by CTRF 💚 |
|
/unittest-module-explorer |
Summary
Failed Tests
Tests
Github Test Reporter by CTRF 💚 |
|
/unittest-module-explorer |
Summary
Tests
Github Test Reporter by CTRF 💚 |
2 participants
Description
Checklist
Please check the following items before code is ready to be reviewed.