This repository provides starter applications demonstrating Google Gemini's capabilities for interactive experiences, targeting developers looking to integrate AI into web applications. The apps showcase Gemini's spatial understanding, video analysis via function calling, and map exploration using the Google Maps API.

How It Works

The starter apps leverage Gemini's multimodal reasoning and function calling features. Spatial Understanding uses Gemini to parse 2D and 3D bounding boxes, while Video Analyzer demonstrates event exploration within videos through defined functions. Map Explorer integrates with the Google Maps API, also utilizing function calling for interactive map interactions. These examples are built with React and Lit, providing clear patterns for developers.

Quick Start & Requirements

• Install: Clone the repository and install dependencies using npm install.
• Prerequisites: A Gemini API key is required.
• Local Development: Insert your Gemini API key into the .env file (for Spatial Understanding and Video Analyzer) or directly into script.js (for Map Explorer).
• Demos: Live demos are available via links in the README.

Highlighted Details

• Demonstrates Gemini's 2D and 3D spatial understanding and reasoning.
• Showcases function calling for video analysis and Google Maps API integration.
• Built with modern web technologies (React, Lit).

Maintenance & Community

Contributors include @bencobley, @dmotz, @grantcuster, and @hapticdata. Further community or roadmap information is not detailed in the README.

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 starter apps are intended as demonstrations and may require further development for production use. Specific licensing details and potential compatibility restrictions are not provided.