feat(generativeai): Create genai_sdk_supervised_checkpoints_view_chec…

[yishan-pu]

Add an example to view checkpoints from 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_checkpoints_view_checkpoints_example.py, to demonstrate how to view checkpoints from a tuning job using the genai SDK. The example retrieves a tuning job and then iterates through the checkpoints associated with the tuned model, printing the details of each checkpoint.

Highlights

• New Example: A new example script, genai_sdk_supervised_checkpoints_view_checkpoints_example.py, has been added to showcase how to view checkpoints from a tuning job.
• Checkpoint Retrieval: The example demonstrates how to retrieve a tuning job and access its checkpoints using the genai SDK.
• Checkpoint Printing: The example iterates through the checkpoints and prints their details, including checkpoint ID, epoch, step, and endpoint.

Changelog

• generative_ai/model_tuning/genai_sdk_supervised_checkpoints_view_checkpoints_example.py
  • Added a new file containing an example of how to view checkpoints from a tuning job using the genai SDK.
  • The example retrieves a tuning job by its name.
  • The example iterates through the checkpoints associated with the tuning job's tuned model.
  • The example prints the details of each checkpoint, including checkpoint ID, epoch, step, and endpoint.
  • The example includes a TODO comment to remind the user to update the PROJECT_ID variable.

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 checkpoint's gleam,
A step in the tuning stream,
Progress we can see.

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 viewing checkpoints from a tuning job using the genai SDK. The example seems straightforward and helpful for users who want to monitor their tuning jobs. However, there are a few areas that could be improved for clarity and robustness.

Summary of Findings

• Missing Error Handling: The code lacks error handling for the client.tunings.get call. If the tuning job does not exist or there's an issue retrieving it, the program will likely crash. Adding error handling would make the example more robust.
• Hardcoded values: The name variable contains hardcoded project and tuning job IDs. While this is an example, it would be better to either fetch these values dynamically or provide clear instructions on how to replace them with the user's own values.
• TODO comment: The TODO comment on line 27 should be addressed, either by providing a default value or removing the comment if it's no longer relevant.

Merge Readiness

The code is a good starting point, but I recommend addressing the missing error handling and hardcoded values before merging. The TODO comment should also be resolved. I am unable to directly approve this pull request, and recommend that others review and approve this code before merging.

[gemini-code-assist]

It's important to handle potential errors when calling the get method. What happens if the tuning job does not exist, or the user does not have permissions to view it? Consider adding a try-except block to catch exceptions and provide a more informative error message.

  try:
    tuning_job = client.tunings.get(name=name)
  except Exception as e:
    print(f"Error getting tuning job: {e}")
    return None # Or raise the exception, depending on desired behavior

[gemini-code-assist]

Consider providing a default value for PROJECT_ID if it's not found in the environment, or removing this comment if it's no longer needed.

Suggested change

	# TODO(developer): Update and un-comment below lines
	# PROJECT_ID = "your-project-id"
	# PROJECT_ID = os.getenv("GOOGLE_CLOUD_PROJECT", "your-project-id")

[gemini-code-assist]

This name variable is hardcoded. While this is an example, it would be beneficial to provide instructions on how to replace these values with the user's own project and tuning job IDs. Consider adding a comment explaining this.

  # TODO(developer): Replace with your project and tuning job IDs
  name = (
      "projects/123456789012/locations/us-central1/tuningJobs/123456789012345"
  )

[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_checkpoints_view_checkpoints_example.py:24, tag genaisdk_gemini_tuning_checkpoints_view_checkpoints

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_checkpoints_view_checkpoints_example.py:24, tag genaisdk_gemini_tuning_checkpoints_view_checkpoints

---

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