feat(py): implement Genkit class methods and registry for feature parity

[yesudeep]

This commit enhances the Genkit Python SDK by implementing several core
methods in the Genkit class and expanding registry capabilities to
better align with the canonical JavaScript implementation.

ISSUE: N/A

CHANGELOG:

• Added Genkit.current_context(), Genkit.run(), Genkit.flush_tracing(),
  and Genkit.check_operation() to the Genkit class.
• Implemented define_simple_retriever supporting flexible content and
  metadata mapping for easy integration of existing data sources.
• Added Genkit.dynamic_tool() for creating unregistered tool actions
  passed directly to generation calls.
• Updated GoogleAI and VertexAI plugins to support optional api_version
  and base_url configuration.
• Enhanced registry management and action resolution logic within the
  Genkit instance.
• Added comprehensive unit tests for the updated Genkit API, including
  retriever mapping and tracing flush logic.

[gemini-code-assist]

Summary of Changes

Hello @yesudeep, 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 significantly advances the Genkit Python SDK by bringing its core Genkit class and registry capabilities closer to feature parity with its JavaScript counterpart. It introduces several new methods for managing execution context, dynamic tool creation, tracing, and long-running operations, alongside a more flexible mechanism for defining data retrievers. These changes aim to improve the SDK's extensibility, observability, and ease of integration with various data sources and AI models.

Highlights

• New Genkit Class Methods: Implemented Genkit.current_context(), Genkit.run(), Genkit.flush_tracing(), Genkit.check_operation(), and Genkit.dynamic_tool() to enhance core functionality and align with the JavaScript SDK.
• Flexible Retriever Definition: Introduced define_simple_retriever supporting flexible content and metadata mapping, simplifying the integration of existing data sources into Genkit flows.
• Plugin Configuration Enhancements: Updated GoogleAI and VertexAI plugins to support optional api_version and base_url configuration, providing more control over API endpoints.
• Registry and Action Resolution: Enhanced internal registry management and action resolution logic within the Genkit instance for improved extensibility.
• Comprehensive Unit Tests: Added extensive unit tests for the newly implemented Genkit API methods, including retriever mapping and tracing flush logic, ensuring reliability and correctness.

🧠 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.

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 introduces several core methods to the Genkit class and expands registry capabilities, bringing the Python SDK closer to feature parity with the JavaScript implementation. Key additions include Genkit.current_context(), Genkit.run(), Genkit.flush_tracing(), Genkit.check_operation(), and define_simple_retriever. The GoogleAI and VertexAI plugins have also been updated to support optional api_version and base_url configurations. The changes are well-tested with comprehensive unit tests for the new APIs. Overall, the changes are well-structured and enhance the SDK's functionality significantly.

[yesudeep]

/gemini review

[yesudeep]

/gemini review