feat(generativeai): Create genai_sdk_supervised_example.py

[yishan-pu]

Add a Gen AI SDK example to create a tuning job.

[gemini-code-assist]

Hello @yishan-pu, 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 example, genai_sdk_supervised_example.py, demonstrating how to create a tuning job using the Gen AI SDK. The example showcases the basic steps involved in tuning a Gemini model, including setting up the client, specifying the base model and training dataset, configuring the tuning job, and monitoring its progress. It also prints information about the tuned model, its endpoint, the associated experiment, and any checkpoints that were created.

Highlights

• New Example: Introduces genai_sdk_supervised_example.py to illustrate the creation of a tuning job with the Gen AI SDK.
• Tuning Job Configuration: Demonstrates how to configure a tuning job, including specifying the base model, training dataset, and display name.
• Monitoring and Output: Shows how to monitor the tuning job's progress and print information about the tuned model, endpoint, experiment, and checkpoints.

Changelog

• generative_ai/model_tuning/genai_sdk_supervised_example.py
  • Created a new file containing an example of how to create a tuning job using the Gen AI SDK.
  • The example uses the gemini-2.0-flash-lite-001 base model and a sample training dataset from Google Cloud Storage.
  • The example includes code to monitor the tuning job's state and print information about the tuned model and its checkpoints.

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 model to tune,
A dataset to refine,
AI's gentle art.

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 code introduces a new example for creating a tuning job using the Gen AI SDK. The example is well-structured and provides a basic implementation for tuning a Gemini model. However, there are a few areas that could be improved for clarity and robustness.

Summary of Findings

• Missing Error Handling: The code lacks proper error handling. The example should include error handling for API calls and other potential failures to ensure the application is robust.
• TODO Comment: The TODO comment should be addressed by providing a default value or a clear instruction on how to set the PROJECT_ID environment variable.
• Hardcoded Values: The example uses hardcoded values for the base model and training dataset. These values should be configurable or clearly documented to allow users to easily adapt the example to their own use cases.

Merge Readiness

The code is a good starting point for demonstrating the Gen AI SDK's tuning capabilities. However, the missing error handling and the TODO comment should be addressed before merging. Additionally, consider making the hardcoded values configurable to improve the example's usability. I am unable to directly approve the pull request, and users should have others review and approve this code before merging. Given the medium severity issues, I recommend addressing them before merging.

[gemini-code-assist]

The PROJECT_ID should be explicitly set if the environment variable is not found, or the program should exit with an error message. Consider using a default value or raising an exception if the environment variable is not set. This will prevent unexpected behavior if the environment variable is missing.

  PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT")
  if not PROJECT_ID:
    raise ValueError("GOOGLE_CLOUD_PROJECT environment variable must be set.")

[gemini-code-assist]

Consider adding a try-except block to handle potential exceptions during the API call. This will make the example more robust and prevent it from crashing if the API call fails.

    try:
      tuning_job = client.tunings.get(name=tuning_job.name)
    except Exception as e:
      print(f"Error getting tuning job: {e}")
      break # Exit the loop if there's an error

[snippet-bot]

Here is the summary of possible violations 😱

There is a possible violation for not having product prefix.

• generative_ai/model_tuning/genai_sdk_supervised_example.py:23, tag genaisdk_gemini_tuning_basic

The end of the violation section. All the stuff below is FYI purposes only.

---

Here is the summary of changes.

You are about to add 1 region tag.

• generative_ai/model_tuning/genai_sdk_supervised_example.py:23, tag genaisdk_gemini_tuning_basic

---

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