A production-ready Retrieval Augmented Generation system built with Next.js, FastAPI, and AWS.

• 📝 Document processing and chunking
• 🔍 Semantic search with pgvector
• 💬 Streaming chat interface
• 🚀 High-performance vector search
• 🔒 Built-in authentication
• 📊 Advanced monitoring

• FastAPI
• PostgreSQL + pgvector
• AWS Bedrock
• Docker + ECS

• Next.js 14 (App Router)
• shadcn/ui components
• Tailwind CSS
• TypeScript

• AWS (ECS, RDS, S3, Lambda)
• Terraform

• Python 3.11+
• Node.js 18+
• Docker
• AWS CLI configured
• Terraform

1. Clone the repository

git clone https://github.com/yourusername/rag-system.git
cd rag-system

2. Backend Setup

cd backend
python -m venv venv
source venv/bin/activate  # or `venv\Scripts\activate` on Windows
pip install -r requirements.txt

3. Frontend Setup

cd frontend
npm install

4. Environment Setup

Create .env files:

backend/.env:

DATABASE_URL=postgresql://user:pass@localhost:5432/rag
AWS_REGION=us-west-2
BEDROCK_MODEL_ID=anthropic.claude-v2
S3_BUCKET=your-rag-documents-bucket

frontend/.env.local:

NEXT_PUBLIC_API_URL=http://localhost:8000
NEXT_PUBLIC_UPLOAD_BUCKET=your-rag-documents-bucket

5. Run Development Servers

Backend:

cd backend
uvicorn api.main:app --reload

Frontend:

cd frontend
npm run dev

1. Infrastructure Setup

cd infrastructure
terraform init
terraform apply

2. Backend Deployment

docker build -f docker/backend.Dockerfile -t rag-backend .
docker push <ECR_REPO>/rag-backend:latest

3. Frontend Deployment

cd frontend
npm run build
vercel deploy  # or your preferred hosting

├── Document Upload
│   └── S3 Storage
├── Processing Pipeline
│   ├── Lambda Trigger
│   ├── Unstructured-IO
│   └── Embedding Generation
├── Vector Storage
│   └── PostgreSQL + pgvector
└── Query Pipeline
    ├── Semantic Search
    ├── Context Retrieval
    └── LLM Response

rag-system/
├── backend/
│   ├── api/
│   ├── indexer/
│   └── retriever/
├── frontend/
│   ├── app/
│   ├── components/
│   └── lib/
└── infrastructure/
    └── modules/

Key configurations in backend/config.py:

• Database settings
• AWS credentials
• Model parameters
• Processing pipeline

Key configurations in frontend/config.ts:

• API endpoints
• Authentication
• UI theming
• Feature flags

1. Fork the repository
2. Create your feature branch
3. Commit your changes
4. Push to the branch
5. Create a new Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• Built with Next.js
• UI components from shadcn/ui
• Vector search by pgvector