feat(genai): samples for batch predict

[Valeriy-Burlaka]

Description

Add samples for batch prediction with genai SDK.

Checklist

• I have followed Sample Guidelines from AUTHORING_GUIDE.MD
• Tests pass: nox -s py-3.12 (see Test Environment Setup)
• Lint pass: nox -s lint (see Test Environment Setup)
• This sample adds a new sample directory, and I updated the CODEOWNERS file with the codeowners for this sample

[snippet-bot]

Here is the summary of changes.

You are about to add 2 region tags.

• genai/batch_prediction/submit_with_bq.py:17, tag googlegenaisdk_batchpredict_with_bq
• genai/batch_prediction/submit_with_gcs.py:17, tag googlegenaisdk_batchpredict_with_gcs

---

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

[code-review-assist]

Hi team,

I'm currently reviewing this pull request and will provide my feedback shortly. In the meantime, here's a summary for you and other reviewers to quickly get up to speed:

This pull request, submitted by Valeriy-Burlaka, adds the ability to perform batch predictions using Google Cloud Storage (GCS). Let's break down the changes:

Intent:

The primary goal is to enhance the existing functionality by enabling users to leverage GCS for batch prediction tasks. This likely improves efficiency and scalability for large-scale prediction jobs.

Changes:

• A new Python file, genai/batch_predict/batch_prediction_with_gcs.py, was added. This file contains the core logic for initiating and monitoring batch prediction jobs using the Google GenAI API. The code uses the google-genai library to interact with the GenAI service, specifically using the client.batches.create and client.batches.get methods to manage the job lifecycle. The job's state is polled until it reaches a terminal state (succeeded, failed, cancelled, or paused).
• genai/batch_predict/requirements.txt and genai/batch_predict/requirements-test.txt were updated to include necessary dependencies, such as google-genai, google-api-core, google-cloud-storage, and pytest.
• A new test file, genai/batch_predict/test_batch_predict.py, was added to ensure the functionality works as expected. This test uses a pytest fixture to manage a temporary GCS bucket for output, and asserts that the job completes successfully and the output is written to the specified GCS location.

Activity:

The PR description mentions that it addresses issue # and includes a checklist for ensuring code quality and compliance. The author has also indicated that they've followed the sample guidelines and updated relevant files such as the README and CODEOWNERS.

I'll provide a more detailed review shortly. In the meantime, please let me know if you have any questions.

And now, a little haiku to lighten the mood:

Batch jobs now fly high,
GCS wings them to the clouds,
Data's swift descent.

[code-review-assist]

This pull request introduces batch prediction using Google Cloud Storage (GCS). The implementation looks good overall. However, there are a few minor points to address and some suggestions for improvement.

I've summarized the style guide elements referenced below:

• Descriptive Function Names: Function names should clearly describe their purpose.
• Docstrings: All functions and methods should have docstrings explaining their purpose, arguments, and return values.
• Type Hinting: Use type hints to improve code readability and maintainability.
• Error Handling: Handle potential errors gracefully and provide informative error messages.
• Testing: Ensure sufficient test coverage, including edge cases and error scenarios.

[msampathkumar]

Need minor updates. PTAL.

[Valeriy-Burlaka]

Hi @msampathkumar! I updated the PR, — please take another look.

[msampathkumar]

LGTM. Passing all the tests. Nice work.