# DocuMente - Agentic Retrieval System

Powered by [datapizza-ai](https://github.com/datapizza-labs/datapizza-ai)

## Quick Start

```bash
# Install dependencies
pip install datapizza-ai datapizza-ai-clients-openai datapizza-ai-embedders-openai datapizza-ai-vectorstores-qdrant

# Start Qdrant (vector store)
docker run -p 6333:6333 qdrant/qdrant

# Run the API
python -m agentic_rag.api.main
```

## Features

- 🌐 **Web Interface** - User-friendly UI for document upload and chat
- 🔌 **REST API** - Full API with Swagger documentation at `/api/docs`
- 🤖 **Agentic RAG** - Powered by datapizza-ai framework
- 📄 **Document Processing** - PDF, DOCX, TXT, MD support
- 🔍 **Semantic Search** - Vector-based retrieval with Qdrant
- 💬 **Chat Interface** - Conversational AI with context

## API Endpoints

- `POST /api/v1/documents` - Upload document
- `GET /api/v1/documents` - List documents
- `POST /api/v1/query` - Query knowledge base
- `POST /api/v1/chat` - Chat endpoint
- `GET /api/health` - Health check
- `GET /api/docs` - Swagger UI

## Architecture

```
Web UI (React/Vanilla JS)
    ↓
FastAPI REST API
    ↓
datapizza-ai RAG Pipeline
    ↓
Qdrant Vector Store
```