feat(py): Implemented deepseek plugin

[zarinn3pal]

Implemented Deepseek plugin with tests and samples

[gemini-code-assist]

Summary of Changes

Hello @zarinn3pal, 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 delivers a new Python plugin for integrating DeepSeek models into the Genkit ecosystem. The implementation meticulously mirrors the existing JavaScript plugin, ensuring a consistent developer experience and feature set. By utilizing Genkit's OpenAI-compatible model infrastructure, the plugin efficiently wraps DeepSeek's API, providing capabilities such as multi-turn conversations, tool calling, streaming responses, and configurable model parameters. The inclusion of comprehensive tests and a practical sample application facilitates quick adoption and validation of the new integration.

Highlights

• DeepSeek Plugin: Introduces a new Python plugin for DeepSeek models, enabling their use within the Genkit framework.
• Feature Parity: Achieves full feature parity with the existing JavaScript DeepSeek plugin, ensuring consistent functionality across platforms.
• OpenAI Compatibility: Leverages Genkit's OpenAI-compatible model infrastructure (OpenAIModel and OpenAIConfig) for seamless integration with DeepSeek's API, promoting code reuse.
• Comprehensive Support: Includes support for deepseek-reasoner and deepseek-chat models, dynamic model resolution, tool usage, streaming, and custom configuration.
• Testing and Samples: Comes with dedicated unit tests for model information and plugin functionality, along with a sample application (deepseek-hello) demonstrating various use cases.

🧠 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 a new Deepseek plugin for Python, complete with tests and a sample application. The implementation is comprehensive and follows the provided plan for the most part. I've identified a few areas for improvement, primarily focusing on fixing a bug in the plugin initialization, correcting some type hints and docstrings for clarity, and improving the sample application to better demonstrate streaming and multi-turn chat functionalities. These changes will enhance the plugin's correctness and usability.

[yesudeep]

Please fix the comments added by Gemini Code Assist.

[MengqinShen]

@zarinn3pal I can not run the sample successfully on my end. I shared the error message with you via chat. On top of that, please refer to model plugin in JS SDK to have the same model Config and Tool in the picture I shared with you.

[MengqinShen]

@zarinn3pal please also add run.sh file to be consistent with other sample flows.