change Gemini model #150
change Gemini model #150
Conversation
|
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA). View this failed invocation of the CLA check for more information. For the most up to date status, view the checks section at the bottom of the pull request. |
![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 @JeffLi1993, 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 updates the Gemini AI model versions used in both the backend CLI example and the frontend input form. The changes involve moving from preview versions of gemini-2.5-pro and gemini-2.5-flash to their stable, non-preview counterparts. This ensures that the application utilizes the most current and stable iterations of these models.
Highlights
- Backend Model Update: The default reasoning model in
cli_research.pyhas been updated fromgemini-2.5-pro-preview-05-06togemini-2.5-pro. - Frontend Model Update (Flash): The default
gemini-2.5-flashmodel and its corresponding selectable option inInputForm.tsxhave been updated fromgemini-2.5-flash-preview-04-17togemini-2.5-flash. - Frontend Model Update (Pro): The
gemini-2.5-proselectable option inInputForm.tsxhas been updated fromgemini-2.5-pro-preview-05-06togemini-2.5-pro.
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 or fill out our survey 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
-
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 updates the Gemini model names from preview versions to stable versions across the backend example script and the frontend component. The changes are straightforward. My review focuses on improving maintainability by suggesting the use of constants or a centralized data structure for the model names to avoid hardcoded strings in multiple places. This will make the code more robust and easier to update in the future.
| @@ -21,7 +21,7 @@ def main() -> None: | |||
| ) | |||
| parser.add_argument( | |||
| "--reasoning-model", | |||
| default="gemini-2.5-pro-preview-05-06", | |||
| default="gemini-2.5-pro", | |||
There was a problem hiding this comment.
This model name is hardcoded. While this is an example script, it's a good practice to define such values as constants to improve readability and maintainability, especially if the value might be used elsewhere or change in the future.
| @@ -26,7 +26,7 @@ export const InputForm: React.FC<InputFormProps> = ({ | |||
| }) => { | |||
| const [internalInputValue, setInternalInputValue] = useState(""); | |||
| const [effort, setEffort] = useState("medium"); | |||
| const [model, setModel] = useState("gemini-2.5-flash-preview-04-17"); | |||
| const [model, setModel] = useState("gemini-2.5-flash"); | |||
There was a problem hiding this comment.
The default model is hardcoded here. This string must exactly match one of the SelectItem values below. Using a constant for the default model that is derived from a centralized list of models would make this more robust and prevent potential bugs caused by typos or inconsistencies.
| <SelectItem | ||
| value="gemini-2.5-flash-preview-04-17" | ||
| value="gemini-2.5-flash" | ||
| className="hover:bg-neutral-600 focus:bg-neutral-600 cursor-pointer" | ||
| > | ||
| <div className="flex items-center"> | ||
| <Zap className="h-4 w-4 mr-2 text-orange-400" /> 2.5 Flash | ||
| </div> | ||
| </SelectItem> | ||
| <SelectItem | ||
| value="gemini-2.5-pro-preview-05-06" | ||
| value="gemini-2.5-pro" | ||
| className="hover:bg-neutral-600 focus:bg-neutral-600 cursor-pointer" | ||
| > |
There was a problem hiding this comment.
Hardcoding model names as string literals here and for the default model state on line 29 can lead to inconsistencies and makes maintenance difficult. If a model name changes, it needs to be updated in multiple places, which is error-prone.
Consider defining the available models as a data structure, like an array of objects, and then dynamically generating these SelectItem components by mapping over this array. The default state could also be derived from this single source of truth. This would centralize the model definitions, making them easier to update and ensuring consistency.
No description provided.