This project implements a PDF document processing system with vector embeddings for semantic search capabilities. It consists of a client-server architecture where users can upload PDFs and perform semantic searches through their content.

pdf-rag/
├── client/          # Next.js frontend
├── server/          # Node.js backend
└── docker-compose.yml  # Docker configuration

• Node.js (v18 or higher)
• Docker and Docker Compose
• pnpm (Package Manager)

1. Clone the repository:

git clone <your-repo-url>
cd pdf-rag

1. Install dependencies:

# Install server dependencies
cd server
pnpm install

# Install client dependencies
cd ../client
pnpm install

1. Set up environment variables:

   • Copy .env.example to .env in both client and server directories
   • Fill in the required environment variables

2. Start the services:

# Start Docker containers (Redis and Qdrant)
docker-compose up -d

# Start the server
cd server
pnpm dev

# Start the client (in a new terminal)
cd client
pnpm dev

• PDF document upload
• Vector embeddings generation using Google AI
• Document storage in Qdrant vector database
• Semantic search capabilities
• Real-time processing with Redis queue

• Frontend: Next.js
• Backend: Node.js
• Vector Database: Qdrant
• Queue: BullMQ with Redis
• Embeddings: Google AI
• Container: Docker