feat(genai): Add GenAI SDK samples (2)

[gericdong]

Description

Fixes b/415995543 - Add GenAI SDK samples (2)

• Count tokens with video
• Controlled generation - enum

[snippet-bot]

Here is the summary of changes.

You are about to add 2 region tags.

• genai/controlled-generation/ctrlgen-with-enum-schema.js:17, tag googlegenaisdk_ctrlgen_with_enum_schema
• genai/count-tokens/counttoken-with-txt-vid.js:17, tag googlegenaisdk_counttoken_with_txt_vid

---

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

[gemini-code-assist]

Hello @gericdong, 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 adds a new sample to the GenAI SDK demonstrating how to count tokens when using a video file as part of the input. It includes the code for counting tokens with a video and accompanying text prompt, as well as a test case to verify the functionality.

Highlights

• New Sample: Count Tokens with Video: Introduces a new sample demonstrating how to count tokens when the input includes a video file and a text prompt using the GenAI SDK.
• Code Implementation: The sample code utilizes the GoogleGenAI class to count tokens for a given video file (hosted on Google Cloud Storage) and a descriptive text prompt.
• Test Case: A test case is included to ensure that the countTokens function returns a token count greater than zero, verifying the basic functionality of the sample.

Changelog

• genai/count-tokens/counttoken-with-txt-vid.js
  • Added a new file containing the sample code for counting tokens with a video and text prompt.
  • The code uses GoogleGenAI to interact with the GenAI service.
  • It defines a function countTokens that takes project ID and location as parameters and returns the total token count.
  • The video file is specified using a Google Cloud Storage URI.
• genai/test/counttoken-with-txt-vid.test.js
  • Added a new test file for the count tokens with video sample.
  • The test case asserts that the countTokens function returns a value greater than 0.

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 video's worth,
In tokens, we now discern,
AI's keen insight.

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 adds a new sample for counting tokens with text and video using the GenAI SDK. The code includes the sample itself and a corresponding test case. Overall, the code is well-structured and easy to understand. However, there are a few minor points that could be improved.

Merge Readiness

The pull request is ready to be merged as there are no critical or high severity issues. I am unable to directly approve the pull request, and recommend that others review and approve this code before merging.

[holtskinner]

Not sure what the issue is on the tests, might just need another run.