[VertexAI] Add HarmBlockThreshold Off

[a-maurice]

Description

Provide details of the change, and generalize the change in the PR title above.

Add new option HarmBlockThreshold Off, which is similar to None, but also sets the response to not include the metadata about the HarmCategory as well.

---

Testing

Describe how you've tested these changes.

Running tests locally

---

Type of Change

Place an x the applicable box:

• Bug fix. Add the issue # below if applicable.
• New feature. A non-breaking change which adds functionality.
• Other, such as a build process or documentation change.

---

[gemini-code-assist]

Hello @a-maurice, 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!

Summary of Changes

This pull request introduces a new HarmBlockThreshold option called Off to the vertexai library. This new option allows all content, regardless of harm, and also prevents the response from including metadata about the HarmCategory. The changes involve adding the Off enum value to the HarmBlockThreshold enum in Safety.cs and updating the ConvertThreshold method to handle the new Off value, mapping it to the string "OFF".

Highlights

• New Feature: Introduces a new HarmBlockThreshold.Off option to disable harm category metadata in the response.
• Enum Extension: Extends the HarmBlockThreshold enum with the Off value.
• Code Modification: Modifies the ConvertThreshold method to correctly convert the new HarmBlockThreshold.Off value to its string representation.

Changelog

• vertexai/src/Safety.cs
  • Added HarmBlockThreshold.Off enum value.
  • Modified ConvertThreshold method to handle the new Off value, mapping it to the string "OFF".

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 is currently in preview and 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 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.

---

A new threshold appears,
'Off' removes all the fears,
No harm to be found,
Metadata unbound,
A cleaner response nears.

Footnotes

1. 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. ↩

[gemini-code-assist]

Code Review

This pull request introduces a new HarmBlockThreshold.Off option to the VertexAI SDK, which allows content to be generated regardless of harm, and also excludes metadata about the HarmCategory in the response. The code changes are straightforward and seem to implement the intended functionality. However, there are a few points to consider before merging.

Merge Readiness

The code introduces a new feature, and the implementation appears correct. However, it would be beneficial to add a unit test to verify the new functionality. I am unable to directly approve this pull request, and recommend that others review and approve this code before merging. Given the absence of unit tests, I recommend that the pull request not be merged until this is addressed.