Conversation
There was a problem hiding this comment.
Summary of Changes
Hello @abhijitjavelin, 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!
I've updated the SDK's guardrails service methods to align with a new expected input structure. This change involves nesting the 'text' parameter within an 'input' dictionary for apply_trustsafety, apply_promptinjectiondetection, and apply_guardrails. Additionally, I've added an optional config parameter to the apply_guardrails method to provide more flexibility.
Highlights
- Input Structure Update: Modified apply_trustsafety and apply_promptinjectiondetection methods to wrap the text parameter within an input dictionary.
- Guardrails Input and Config: Updated apply_guardrails to also wrap the text parameter within an input dictionary and introduced an optional config parameter to allow for additional configuration.
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 PR correctly fixes the payload structure for guardrail service calls. The changes are consistent and address the issue.
A key point to consider: the new config parameter in GuardrailsService.apply_guardrails is not exposed in JavelinClient.apply_guardrails. This prevents SDK users from accessing the new functionality. It would be beneficial to update the client method accordingly.
I've also included a suggestion to improve type hinting for better code clarity.
|
|
||
| def apply_guardrails(self, text: str, guardrails: list) -> Dict[str, Any]: | ||
| data = {"text": text, "guardrails": guardrails} | ||
| def apply_guardrails( |
There was a problem hiding this comment.
For better type safety and code clarity, it's recommended to use a more specific type for the guardrails parameter instead of the generic list. Based on its usage, List[Dict[str, Any]] would be more appropriate.
You'll need to add List to your imports from the typing module.
| def apply_guardrails( | |
| def apply_guardrails(self, text: str, guardrails: "List[Dict[str, Any]]", config: Optional[Dict[str, Any]] = None) -> Dict[str, Any]: |
No description provided.