feat(batch prediction): Adds tuned model support comments to samples.

[br1mendez]

Description

Adds a comment that shows how to use tuned models in a batch prediction job.

Internal: b/417300996

Checklist

• I have followed Sample Guidelines from AUTHORING_GUIDE.MD
• README is updated to include all relevant information
• Tests pass: nox -s py-3.9 (see Test Environment Setup)
• Lint pass: nox -s lint (see Test Environment Setup)
• 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 @br1mendez, 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

Hello team, Gemini here to provide a quick summary of this pull request by @br1mendez. The primary goal of this PR, as indicated by the title, is to enhance the existing batch prediction samples by adding comments that guide users on how to specify a tuned model instead of the default base model. This change aims to make the samples more versatile and informative for users who have trained their own models.

Highlights

• Documentation via Comments: Adds inline comments to the batch prediction sample code to demonstrate the format required for using a tuned model resource path.
• Batch Prediction Samples: Specifically targets the Python samples for batch prediction using both BigQuery and Google Cloud Storage as input/output sources.

Changelog

• genai/batch_prediction/batchpredict_with_bq.py
  • Added comments explaining how to use a tuned model by providing the full resource path (projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}) for the model parameter in the client.batches.create call.
• genai/batch_prediction/batchpredict_with_gcs.py
  • Added comments explaining how to use a tuned model by providing the full resource path (projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}) for the model parameter in the client.batches.create call.

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.

---

Code comments appear,
Guiding users, making clear,
Tuned models can run.

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 helpful comments to the batch prediction samples, guiding users on how to specify a tuned model. The changes are straightforward and improve the clarity of the code for this specific use case. Based on the review settings, I was instructed to only provide comments for issues of medium, high, or critical severity. My review found no issues meeting these criteria.

Summary of Findings

• No issues found at specified severity levels: My review found no issues of medium, high, or critical severity in the code changes. The added comments are clear, correctly formatted, and provide valuable guidance for users wanting to utilize tuned models in the batch prediction samples.

Merge Readiness

Based on my review, which found no issues of medium, high, or critical severity, the code appears to be in good shape and ready for merging. Please note that I am unable to approve this pull request directly; another reviewer will need to provide approval.