Remove adk kernel & updated ADK version

[takumiohym]

• Updated ADK version to 1.14.1 (Chose this version since >=1.15.0 updates other dependencies including protobuf.)
• Removed ADK kernel

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[gemini-code-assist]

Summary of Changes

Hello @takumiohym, 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!

This pull request streamlines the development environment by updating the Agent Development Kit (ADK) to version 1.14.1 and eliminating the need for a separate ADK-specific Jupyter kernel. This change simplifies setup for users by consolidating dependencies within the base Python environment and updating relevant notebook configurations and requirements.txt to reflect the new ADK version and associated google-genai dependency.

Highlights

• ADK Version Update: The Agent Development Kit (ADK) has been updated to version 1.14.1, specifically chosen to avoid broader dependency changes that would occur with versions 1.15.0 and above.
• ADK Kernel Removal: The dedicated ADK kernel and its associated setup script (kernels/adk.sh) have been removed, simplifying the environment configuration.
• Notebook Environment Streamlining: Jupyter notebooks have been updated to remove references to the custom ADK kernel, now relying on the base Python environment and adjusting PATH for ADK commands.
• Dependency Pinning: The google-genai dependency has been pinned to version 1.23.0 in the notebooks, and google-adk to 1.14.1 in requirements.txt and notebooks.
• Python Version Update: The Python version referenced in the notebook metadata has been updated from 3.10.16 (or 3.10.14) to 3.10.18.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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.

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 removes the custom ADK kernel and updates the ADK version to 1.14.1, simplifying the notebook setup. The changes rely on a standard pip installation of google-adk and adjust the PATH environment variable accordingly. The updates are consistent with the description and improve the overall user experience. I have one suggestion to enhance portability.

[gemini-code-assist]

Hardcoding the path with /home/jupyter makes the notebook less portable across different environments. It's better to programmatically retrieve the user's home directory using os.path.expanduser('~') to ensure the code runs correctly for any user.

Suggested change

	"%env PATH=/home/jupyter/.local/bin:{PATH}"
	"%env PATH={os.path.expanduser('~')}/.local/bin:{PATH}"

[sanjanalreddy]

@takumiohym Was this meant to be added to the keras3-dev branch?

[takumiohym]

@sanjanalreddy Yes, because ADK lib is added to requirements.txt along with the keras 3 update in the keras3-dev branch.