[WIP] Add ADK model handler

[damccorm]

Adds model handler capable of running ADK agents mid-pipeline.

---

Thank you for your contribution! Follow this checklist to help us incorporate your contribution quickly and easily:

• Mention the appropriate issue in your description (for example: addresses #123), if applicable. This will automatically add a link to the pull request in the issue. If you would like the issue to automatically close on merging the pull request, comment fixes #<ISSUE NUMBER> instead.
• Update CHANGES.md with noteworthy changes.
• If this contribution is large, please file an Apache Individual Contributor License Agreement.

See the Contributor Guide for more tips on how to make review process smoother.

To check the build health, please visit https://github.com/apache/beam/blob/master/.test-infra/BUILD_STATUS.md

GitHub Actions Tests Status (on master branch)

See CI.md for more information about GitHub Actions CI or the workflows README to see a list of phrases to trigger workflows.

[gemini-code-assist]

Summary of Changes

Hello, 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 introduces a new ModelHandler for Apache Beam's ML Inference library, specifically designed to integrate with the Google Agent Development Kit (ADK). This integration allows users to embed sophisticated AI agents, such as large language model agents, directly into their Beam data processing pipelines. The handler manages agent lifecycle and conversation sessions, providing flexibility for various interaction patterns.

Highlights

• New ADKAgentModelHandler: Introduced ADKAgentModelHandler to enable running Google Agent Development Kit (ADK) agents within Beam pipelines using the RunInference transform.
• Flexible Agent Instantiation: Implemented support for providing ADK agents either as direct instances or as zero-argument factory callables, accommodating unpicklable agent states.
• Session Management: Designed session management within the handler to support both stateless (unique session per element) and stateful (shared session_id for multi-turn conversations) agent interactions.
• Comprehensive Unit Tests: Included comprehensive unit tests for ADKAgentModelHandler covering initialization, model loading, inference execution, and session handling.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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.

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. ↩

[codecov]

Codecov Report

❌ Patch coverage is 0% with 68 lines in your changes missing coverage. Please review.
✅ Project coverage is 54.75%. Comparing base (0afbdf6) to head (633e08a).
⚠️ Report is 7 commits behind head on master.

Files with missing lines	Patch %	Lines
.../apache_beam/ml/inference/agent_development_kit.py	0.00%	68 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             master   #37917    +/-   ##
==========================================
  Coverage     54.75%   54.75%            
  Complexity     1690     1690            
==========================================
  Files          1063     1064     +1     
  Lines        166898   167111   +213     
  Branches       1226     1226            
==========================================
+ Hits          91377    91505   +128     
- Misses        73328    73413    +85     
  Partials       2193     2193            

Flag	Coverage Δ
python	80.02% <0.00%> (-0.06%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.