fix(py): fixed broken sample of model-garden and added anthropic to plugin

[MengqinShen]

Added Anthropic Support to Python Model Garden Plugin to Match Go SDK( Previous Python SDK used LIama)

1. Fixed broken sample with an invalid config error reported in the previous bug bash.
2. Plugin Updates: (1)Added anthropic to py/plugins/vertex-ai/pyproject.toml. (2) Created AnthropicModelGarden in
   py/plugins/vertex-ai/src/genkit/plugins/vertex_ai/model_garden/anthropic.py, which uses AsyncAnthropicVertex to communicate with Vertex AI.(3) Updated VertexAIModelGarden._resolve_model in modelgarden_plugin.py to route models starting with anthropic/ to the new handler.
3. Sample Updates: Updated py/samples/model-garden/src/main.py to use the anthropic/claude-3-5-sonnet-v2@20241022 model.

[gemini-code-assist]

Summary of Changes

Hello @MengqinShen, 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 expands the capabilities of the Vertex AI Model Garden plugin by introducing native support for Anthropic models, allowing users to leverage these models within the Genkit framework. It also refines the plugin's configuration, providing more granular control over model deployment locations and improving environment variable integration for region settings. Additionally, a critical bug related to configuration normalization in the compat-oai plugin has been addressed, enhancing overall compatibility and stability.

Highlights

• Bug Fix: Configuration Normalization: Resolved an issue in the compat-oai plugin where GenerationCommonConfig was not correctly converted to OpenAIConfig, ensuring proper handling of common generation parameters.
• Anthropic Model Integration: Added comprehensive support for integrating Anthropic models available through Vertex AI Model Garden, including a new dedicated AnthropicModelGarden class.
• Flexible Model Location Configuration: Enhanced the VertexAIModelGardenPlugin to allow specifying different Google Cloud regions for individual models and improved environment variable-based location discovery.
• Updated Sample Application: Modified the Model Garden sample to demonstrate the usage of an Anthropic model for generating content, replacing previous examples.

🧠 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 adds support for Anthropic models on Vertex AI Model Garden, which is a great addition. The implementation is well-structured, reusing existing components where possible. I've identified a bug in the new sample code where a configuration key is incorrect, and I've also provided a couple of suggestions to improve code readability and maintainability. Overall, the changes look good.