---
title: RAG Chatbot Backend
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
---

# RAG Chatbot Backend API

Backend API for the Humanoid AI Robotics Book Chatbot using RAG (Retrieval-Augmented Generation).

## 🚀 Features

- FastAPI-based REST API
- OpenAI Agents SDK for intelligent responses
- Qdrant vector database for semantic search
- Cohere embeddings for document retrieval
- CORS enabled for frontend integration

## 📋 API Endpoints

### Health Check

```
GET /health
```

### Chat

```
POST /chat
Content-Type: application/json

{
  "question": "Your question here"
}
```

## ⚙️ Environment Variables

Set these in Space Settings → Variables and secrets:

- `COHERE_API_KEY` - Cohere API key
- `QDRANT_URL` - Qdrant Cloud URL
- `QDRANT_API_KEY` - Qdrant API key
- `QDRANT_COLLECTION` - Collection name
- `OPENAI_API_KEY` - OpenAI API key
- `AGENT_MODEL` - Model name (e.g., gpt-4o-mini)

## 🔗 Frontend

Frontend deployed at: https://hackathon-1-humanoid-ai-robotics.vercel.app

## 📝 License

Part of the Humanoid AI Robotics Book Chatbot project.