🐰 Rabbit Hole

The infinite, adaptive encyclopedia of curiosity

An AI-powered platform that celebrates neurodivergent learning patterns - turning every question into an endless journey of discovery. Built for those who love to dive deep and explore the fascinating connections between ideas.

✨ Features

• 🎯 Dynamic Topic Suggestions - Fresh, intriguing topics regenerated every visit
• 🎛️ 5-Level Depth Control - From 5-year-old explanations to PhD-level research
• 🔄 Real-time Streaming - Watch content generate live with Qwen2.5:7b
• 🎨 Smart Text Selection - Highlight any text to create new rabbit holes
• 🌊 Infinite Exploration - Every concept becomes a doorway to new discoveries
• ⚡ Local AI - Powered by Ollama for privacy and speed

🚀 Quick Start

Prerequisites

• Node.js (v18+)
• Python (v3.8+)
• Ollama with Qwen2.5:7b model

Installation

1. Install Ollama and pull the model:

   # Install Ollama from https://ollama.ai/
   ollama pull qwen2.5:7b
   

2. Clone and setup the project:

   git clone https://github.com/yourusername/rabbit-hole
   cd rabbit-hole
   

3. Start the backend:

   cd backend
   pip install fastapi uvicorn httpx
   python test_server.py
   

4. Start the frontend:

   cd frontend
   npm install
   npm run dev
   

5. Open http://localhost:5174 and start exploring!

🎮 How to Use

1. Start Your Journey - Try one of the dynamic suggestions or search for anything
2. Adjust Depth - Use the slider to match your learning preference
3. Explore Mode - Choose fact-based, story-driven, or hands-on content
4. Dive Deeper - Highlight any text and click "Dive into the Rabbit Hole"
5. Follow Connections - Click [[bracketed]] terms for related exploration

🏗️ Architecture

rabbit-hole/
├── frontend/          # SvelteKit + Tailwind CSS
│   ├── src/routes/    # Main application pages
│   ├── src/lib/       # Components and utilities
│   └── src/app.html   # Base HTML template
├── backend/           # FastAPI + Ollama integration
│   └── test_server.py # AI content generation server
└── README.md         # You are here!

🤖 AI Model

This project uses Qwen2.5:7b via Ollama:

• 7 billion parameter model optimized for reasoning
• Runs locally for privacy and speed
• Supports streaming for real-time content generation
• Dramatically different outputs per depth level

🎨 Design Philosophy

Built for neurodivergent learning patterns:

• Non-linear exploration over rigid curricula
• Multiple depth levels for different cognitive states
• Visual rabbit hole tracking
• Infinite curiosity-driven discovery
• No judgment, just pure exploration

🛠️ Tech Stack

• Frontend: SvelteKit, Tailwind CSS, JavaScript
• Backend: FastAPI, Python, HTTP streaming
• AI: Ollama, Qwen2.5:7b local model
• Deployment: Static frontend, Python backend

🤝 Contributing

This is an open-source celebration of neurodivergent curiosity! Contributions welcome:

1. Fork the repository
2. Create a feature branch (git checkout -b amazing-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin amazing-feature)
5. Open a Pull Request

Ideas for Contribution

• Additional AI models support
• Mobile app version
• Voice interaction
• Visual knowledge graphs
• Collaborative exploration
• Multi-language support

📝 License

MIT License - feel free to fork, modify, and use in your own projects!

🙏 Acknowledgments

• Built with love for the neurodivergent community
• Powered by the amazing Ollama project
• Inspired by everyone who's ever fallen down a Wikipedia rabbit hole

Happy exploring! 🐰✨

Remember: There are no wrong questions, only fascinating journeys waiting to begin.