feat(modelarmor): Added snippets for sanitization user prompt

[tirthrajsinh-zala-crest]

Description

Added code snippets for modelarmor sanitization user prompt

Checklist

• I have followed Contributing Guidelines from CONTRIBUTING.MD
• Tests pass: go test -v ./.. (see Testing)
• Code formatted: gofmt (see Formatting)
• Vetting pass: go vet (see Formatting)
• These samples need a new API enabled in testing projects to pass (let us know which ones)
• These samples need a new/updated env vars in testing projects set to pass (let us know which ones)
• This sample adds a new sample directory, and I updated the CODEOWNERS file with the codeowners for this sample
• This sample adds a new Product API, and I updated the Blunderbuss issue/PR auto-assigner with the codeowners for this sample
• Please merge this PR for me once it is approved

[gemini-code-assist]

Hello @tirthrajsinh-zala-crest, 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 code snippets for ModelArmor sanitization, focusing on user prompt handling. It adds a new directory modelarmor with necessary files including create_template.go, go.mod, go.sum, modelarmor_test.go, sanitize_user_prompt.go, and a test environment file. The changes include creating a Model Armor template and sanitizing user prompts using that template.

Highlights

• New Module: A new modelarmor module is added to the go.work file, integrating it with the existing modules.
• Template Creation: The create_template.go file provides a function to create a new Model Armor template with specified filters for PI, jailbreak attempts, and malicious URIs.
• User Prompt Sanitization: The sanitize_user_prompt.go file includes a function to sanitize user prompts using a specified Model Armor template, helping to filter out harmful content.
• Testing: The modelarmor_test.go file contains a test case, TestSanitizeUserPrompt, which validates the sanitization of user prompts using the created template.

Changelog

Click here to see the changelog

• go.work
  • Added the modelarmor module to the workspace.
• modelarmor/create_template.go
  • Created a new file with code to create a Model Armor template.
  • Implements the createModelArmorTemplate function to create a template with specified filters.
• modelarmor/go.mod
  • Created a new go module for modelarmor.
  • Added dependencies for cloud.google.com/go/modelarmor, github.com/GoogleCloudPlatform/golang-samples, github.com/google/uuid, github.com/joho/godotenv, google.golang.org/api, and google.golang.org/grpc.
• modelarmor/go.sum
  • Generated go sum file for the modelarmor module
• modelarmor/modelarmor_test.go
  • Created a new test file for Model Armor functionality.
  • Includes a test case TestSanitizeUserPrompt to validate user prompt sanitization.
• modelarmor/sanitize_user_prompt.go
  • Created a new file with code to sanitize user prompts.
  • Implements the sanitizeUserPrompt function to sanitize user prompts using a specified template.
• modelarmor/testdata/env/test.env
  • Created a test environment file to store the location of the test

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 template's born,
Armor shields the user's words,
Safety now takes hold.

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

The pull request introduces code snippets for ModelArmor sanitization, including template creation and user prompt sanitization. The code appears well-structured and includes necessary error handling and documentation. However, there are a few areas that could be improved for clarity and robustness.

Summary of Findings

• Error Handling Consistency: In createModelArmorTemplate, the error message in case of client creation failure includes the location, but the error message in case of template creation failure does not. Maintaining consistency in error messages improves debuggability.
• Test Environment Loading: The testLocation function loads the test environment file using a relative path. This can be fragile if the test is run from a different directory. Using an absolute path or a path relative to the project root would be more robust.
• Missing Input Validation: The functions createModelArmorTemplate and sanitizeUserPrompt do not validate the input parameters such as projectID, locationID, and templateID. Adding validation would prevent unexpected behavior due to invalid inputs.

Merge Readiness

The pull request is almost ready for merging. Addressing the inconsistencies in error handling and improving the robustness of the test environment loading would enhance the overall quality of the code. I am unable to approve this pull request, and recommend that others review and approve this code before merging. At a minimum, the high severity issues should be addressed before merging.

[snippet-bot]

Here is the summary of changes.

You are about to add 1 region tag.

• modelarmor/sanitize_user_prompt.go:19, tag modelarmor_sanitize_user_prompt

---

This comment is generated by snippet-bot.
If you find problems with this result, please file an issue at:
https://github.com/googleapis/repo-automation-bots/issues.
To update this comment, add snippet-bot:force-run label or use the checkbox below:

• Refresh this comment

[telpirion]

This PR has the same global issues as #5273 .

Also, this PR contains content that we can't publish to our GitHub repo.

[harshnasitcrest]

LGTM, user prompts used in the tests have been updated as per python code snippets.

[telpirion]

Please resolve the merge conflicts and we can get this merged!