An AI-powered research tool that fuses knowledge from Wikipedia, web search, and Claude AI to generate comprehensive research summaries.
- 🤖 AI-powered research summaries (300-500 words)
- 🔍 Multi-source integration (Wikipedia + Web Search + Claude AI)
- ⚡ Fast results (7-10 seconds)
- 🎨 Modern dark-themed UI
- 📊 Structured output with sources
Frontend: React, Vite, Axios
Backend: Python, Flask, LangChain, Claude AI (Anthropic)
APIs: Anthropic, Wikipedia, DuckDuckGo
- Python 3.8+
- Node.js 16+
- Anthropic API key (Get one here)
cd backend
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
# Create .env file
cp .env.example .env
# Add your API key to .env: ANTHROPIC_API_KEY=your_key_here
python app.pyBackend runs on http://localhost:5001
cd frontend
npm install
npm run devFrontend runs on http://localhost:3000
FusionAI/
├── backend/
│ ├── app.py # Flask API
│ ├── tools.py # LangChain tools
│ ├── requirements.txt # Python dependencies
│ └── .env # API keys (DO NOT COMMIT)
├── frontend/
│ ├── src/
│ │ ├── App.jsx # Main component
│ │ └── App.css # Styles
│ ├── package.json # Node dependencies
│ └── vite.config.js # Vite config
└── README.md
Health Check:
GET /api/healthResearch:
POST /api/research
Content-Type: application/json
{
"query": "artificial intelligence"
}Create backend/.env:
ANTHROPIC_API_KEY=your_api_key_here
PORT=5001.env file to GitHub!
Backend: Deploy to Render/Heroku (set ANTHROPIC_API_KEY in environment variables)
Frontend: Deploy to Vercel/Netlify (build command: npm run build, output: dist)
Claude Sonnet 4 costs approximately $0.03-0.05 per query. New users get free trial credits.
Port in use: Change PORT in .env or port in vite.config.js
API errors: Verify API key in .env file
Module errors: Reinstall dependencies with pip install -r requirements.txt or npm install
Bao Tran - George Mason University