fix(py): add mistral to model-garden and add llama back #4185
Conversation
Summary of ChangesHello @MengqinShen, 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 expands the 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 Mistral model in Model Garden and re-enables sample code for Llama models. The changes involve updating model information, adjusting model lookup logic, and uncommenting example flows. My review focuses on improving code readability and adhering to style conventions. I've suggested a more idiomatic way to look up models from multiple dictionaries and recommended reverting a formatting change that reduces code clarity.
|
|
||
| model = SUPPORTED_OPENAI_MODELS[self._model] | ||
| if SupportedOutputFormat.JSON_MODE in model.supports.output: | ||
| model = SUPPORTED_OPENAI_MODELS.get(self._model, SUPPORTED_OPENAI_COMPAT_MODELS.get(self._model)) |
There was a problem hiding this comment.
For improved readability and to make the logic clearer, you could simplify this line. Using or to chain the dictionary lookups is a more common and idiomatic Python pattern for this scenario. It also has the minor benefit of short-circuiting, so the second lookup is only performed if the first one fails.
| model = SUPPORTED_OPENAI_MODELS.get(self._model, SUPPORTED_OPENAI_COMPAT_MODELS.get(self._model)) | |
| model = SUPPORTED_OPENAI_MODELS.get(self._model) or SUPPORTED_OPENAI_COMPAT_MODELS.get(self._model) |
| or os.getenv('GOOGLE_CLOUD_LOCATION') | ||
| or os.getenv('GOOGLE_CLOUD_REGION') | ||
| or const.DEFAULT_REGION | ||
| location or os.getenv('GOOGLE_CLOUD_LOCATION') or os.getenv('GOOGLE_CLOUD_REGION') or const.DEFAULT_REGION |
There was a problem hiding this comment.
This line is quite long (over 100 characters) and can be difficult to read. The previous multi-line formatting was more readable and aligned better with Python style guides like PEP 8, which recommend limiting line length. I'd suggest reverting to the multi-line format for better maintainability.
location
or os.getenv('GOOGLE_CLOUD_LOCATION')
or os.getenv('GOOGLE_CLOUD_REGION')
or const.DEFAULT_REGION2 participants
Description here... Help the reviewer by:
Checklist (if applicable):