This repository provides a hands-on workshop for developers to learn how to build applications using Google's Gemini API and Python SDK. It covers text prompting, multimodal understanding, and agentic capabilities, targeting developers looking to integrate advanced AI features into their projects.

How It Works

The workshop is structured into three parts, guiding users through Gemini's capabilities. It emphasizes practical application via notebooks and exercises, progressing from basic text prompting and streaming to complex multimodal inputs (image, video, audio, documents, code) and agentic features like tool usage and function calling.

Quick Start & Requirements

• Install: No specific installation commands are provided, but the project relies on the Gemini API Python SDK.
• Prerequisites: A Google AI Studio API key is required. All functionalities are accessible via the free tier.
• Resources: The workshop is designed to be run locally with standard Python environments.
• Documentation: Notebooks and Solutions are available within the repository.

Highlighted Details

• Covers text, multimodal (image, video, audio, docs, code), and agentic capabilities.
• Includes practical exercises and solutions for each topic.
• Demonstrates advanced features like streaming responses, system prompts, and tool usage.
• Features final exercises integrating learned concepts, such as "Chat with book" and "Analyze supermarket invoice."

Maintenance & Community

The repository is maintained by Patrick Loeber. Further resources and related projects are linked in the README, including Gemini 2.0 features and a Live API cookbook.

Licensing & Compatibility

The repository's license is not specified in the README. Compatibility for commercial use or closed-source linking is not detailed.

Limitations & Caveats

The README does not specify the exact Python version requirements or provide explicit installation instructions beyond needing the Gemini API SDK. The project appears to be a workshop guide rather than a runnable application with a defined setup process.