fix: remove the num_template_per_step param in all notebooks

[want-to-be-relaxed]

Description

Remove the num_template_eval_per_step parameter in all the notebooks.

Thank you for opening a Pull Request!
Before submitting your PR, there are a few things you can do to make sure it goes smoothly:

• Follow the CONTRIBUTING Guide.
• You are listed as the author in your notebook or README file.
  • Your account is listed in CODEOWNERS for the file(s).
• Make your Pull Request title in the https://www.conventionalcommits.org/ specification.
• Ensure the tests and linter pass (Run nox -s format from the repository root to format).
• Appropriate docs were updated (if necessary)

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[code-review-assist]

Hi @want-to-be-relaxed and reviewers,

I'm currently reviewing this pull request and will post my full review in a few minutes. In the meantime, here's a quick summary to help everyone get up to speed:

This PR removes the num_template_eval_per_step parameter from several notebooks within the generative-ai repository. The intent, as stated in the PR description, is to simply remove this parameter.

Here's a breakdown of the changes:

• Files Affected:

  • gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_sdk.ipynb (line 924 removed)
  • gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_sdk_custom_metric.ipynb (line 1167 removed)
  • gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_sdk_long_prompt_optimization.ipynb (line 828 removed)
  • gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_sdk_tool_calling.ipynb (line 1146 removed)
  • gemini/prompts/prompt_optimizer/vertex_ai_prompt_optimizer_ui.ipynb (lines 274, 368 removed; line 297-299 simplified)

• Change Summary: The num_template_eval_per_step parameter, which controlled the number of system instructions evaluated per step in prompt optimization, has been removed from all specified notebooks. The code changes reflect this removal. In vertex_ai_prompt_optimizer_ui.ipynb, some minor code cleanup was also performed around the RESPONSE_MIME_TYPE parameter.

I'll provide a more detailed review shortly, but this should give you a good overview of the changes.

And now, a little haiku to lighten the mood:

Code flows like a stream,
Removing params, clean and bright,
Review's gentle breeze.

Best,
Gemini

[code-review-assist]

Gemini encountered an error creating the review. You can try again by commenting @code-review-assist review.

[inardini]

LGTM