feat(genai): add provisioned throughput and controlled generation samples

[jdomingr]

Add new samples:

• Provisioned throughput with text input.
• Controlled generation with enum schema.

Also, I fixed some comments in TextGenWithPdf.cs and TextGenWithPdf.cs.

All local tests have passed

[snippet-bot]

Here is the summary of changes.

You are about to add 2 region tags.

• genai/api/GenAI.Samples/ControlledGeneration/ControlledGenWithEnumSchema.cs:17, tag googlegenaisdk_ctrlgen_with_enum_schema
• genai/api/GenAI.Samples/ProvisionedThroughput/ProvisionedThroughputWithTxt.cs:17, tag googlegenaisdk_provisionedthroughput_with_txt

---

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]

Summary of Changes

Hello @jdomingr, 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 expands the Generative AI C# samples by introducing two new functionalities: controlled generation, which guides model output to specific enum values, and provisioned throughput, which optimizes performance for text generation. Additionally, it includes minor documentation improvements by fixing typos in existing sample comments.

Highlights

• New Sample: Controlled Generation with Enum Schema: A new C# sample has been added to demonstrate controlled generation using an enum schema, ensuring model responses adhere to a predefined set of string values.
• New Sample: Provisioned Throughput for Text Generation: A new C# sample showcases how to utilize provisioned throughput for text input, allowing for dedicated capacity for generative AI models.
• Comment Fixes: Minor typographical errors in comments within existing text generation samples (TextGenWithPdf.cs and TextGenWithTxt.cs) have been corrected.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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

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 adds two new C# samples for the GenAI library, demonstrating provisioned throughput and controlled generation, along with their corresponding tests. It also includes minor typo fixes in existing files. The new samples are a good addition. My review focuses on improving the correctness and robustness of these new samples. I've pointed out that the provisioned throughput sample is misleadingly configured for the pay-as-you-go model. Additionally, I've suggested changes to make the response handling safer in both new samples to avoid potential runtime exceptions.

[Alan5142]

Some of the samples have a try-catch to catch the errors. I think that we should aim for that here as well just to 1. showcase some simple error handling, and 2. keep consistency with other languages that have a try-catch as well.

[jdomingr]

Thanks for the suggestion, but as far as I know, it is not necessary to implement exception handling in the samples, unless there are specific error handling cases that we need to show, which, in my opinion, does not apply in this case.

[iennae]

in general, we recommend it so that if there is some kind of issue with the service that you can print that out rather than the user assuming something is broken with the sample. This reduces frustration and gives the user a path to move forward.