AI Agent - Full Stack Application

🇹🇷 Türkçe: Detaylı proje açıklaması için backend/PROJE_OZETI.md dosyasına bakınız.

Full-stack AI-powered platform for real-time audio processing, video conferencing, CRM integrations, and intelligent conversation analysis.

🚀 Features

Backend (FastAPI + Python)

• Real-time Audio Processing: WebSocket-based streaming with OpenAI Realtime API
• LiveKit Integration: Self-hosted WebRTC video conferencing
• Speaker Diarization: Automatic speaker identification and segmentation
• CRM Integrations: HubSpot, Salesforce, Pipedrive connectors
• Intelligent Caching: Redis-based query optimization
• Vector Search: PostgreSQL + pgvector for semantic search
• MCP Service: Natural language to SQL conversion
• Monitoring: Prometheus + Grafana dashboards

Frontend (React + TypeScript)

• Modern UI: Metronic UI theme with Bootstrap
• LiveKit Components: Real-time video/audio conferencing
• Meeting Management: Create, join, and manage meetings
• Real-time Transcripts: Live transcription display
• CRM Dashboard: Integrated CRM data visualization
• Responsive Design: Mobile-friendly interface

📁 Project Structure

ai-agent-fullstack/
├── backend/                 # FastAPI backend
│   ├── api/                # REST API endpoints
│   ├── services/           # Business logic
│   ├── models/             # SQLAlchemy models
│   ├── schemas/            # Pydantic schemas
│   ├── crm/                # CRM integrations
│   ├── docker-compose.yml  # Backend services
│   ├── requirements.txt    # Python dependencies
│   └── README.md           # Backend documentation
│
├── frontend/               # React frontend
│   ├── src/               # Source code
│   │   ├── app/          # Main app components
│   │   ├── _metronic/    # Metronic UI theme
│   │   └── pages/        # Page components
│   ├── public/            # Static files
│   ├── package.json       # Node dependencies
│   └── README.md          # Frontend documentation
│
├── docs/                   # Shared documentation
│   ├── ARCHITECTURE.md    # System architecture
│   ├── DEPLOYMENT.md      # Deployment guide
│   └── DEVELOPMENT.md     # Development guide
│
├── docker-compose.yml      # Full-stack orchestration
├── .gitignore             # Git ignore rules
└── README.md              # This file

🛠️ Quick Start

Prerequisites

• Docker & Docker Compose (recommended)
• Python 3.11+ (for local backend development)
• Node.js 18+ (for local frontend development)
• Git

Option 1: Docker Compose (Full Stack)

# Clone repository
git clone https://github.com/YOUR_USERNAME/ai-agent-fullstack.git
cd ai-agent-fullstack

# Setup environment variables
cp backend/.env.example backend/.env.docker
# Edit backend/.env.docker and backend/.env.secrets with your keys

# Start all services
docker-compose up -d

# Run migrations
docker exec backend alembic upgrade head

# Access services
# Frontend: http://localhost:3000
# Backend API: http://localhost:8001
# API Docs: http://localhost:8001/docs
# Grafana: http://localhost:3000

Option 2: Local Development

Backend Setup

cd backend

# Create virtual environment
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Setup environment
cp .env.example .env.local
# Edit .env.local with your configuration

# Start services (PostgreSQL, Redis, etc.)
docker-compose up -d postgresql redis minio nats livekit

# Run migrations
alembic upgrade head

# Start backend
uvicorn main:app --reload --port 8001

Frontend Setup

cd frontend

# Install dependencies
npm install

# Setup environment
cp .env.example .env.local
# Edit .env.local with backend URL

# Start development server
npm run dev

🔧 Configuration

Backend Environment Variables

Create backend/.env.docker and backend/.env.secrets:

# Required
OPENAI_API_KEY=sk-your-openai-key
DATABASE_URI=postgresql+psycopg://postgres:password@postgresql:5432/ai_agent
REDIS_HOST=redis
REDIS_PORT=6379

# LiveKit
LIVEKIT_API_KEY=your-livekit-key
LIVEKIT_API_SECRET=your-livekit-secret
LIVEKIT_URL=ws://livekit:7880

# Optional CRM
HUBSPOT_CLIENT_ID=
HUBSPOT_CLIENT_SECRET=

Frontend Environment Variables

Create frontend/.env.local:

VITE_API_URL=http://localhost:8001
VITE_LIVEKIT_URL=ws://localhost:7880

📚 Documentation

General

• Architecture - System design and components
• Deployment - Production deployment guide
• Development - Development workflow

Backend

• Backend README - Backend-specific documentation
• Türkçe Özet - Project summary in Turkish
• API Docs - Interactive Swagger UI (when running)

Frontend

• Frontend README - Frontend-specific documentation

🧪 Testing

Backend Tests

cd backend
pytest
pytest --cov=services --cov-report=html

Frontend Tests

cd frontend
npm run test
npm run lint

🚢 Deployment

Docker Production

# Build images
docker-compose build

# Start production stack
docker-compose -f docker-compose.yml -f docker-compose.prod.yml up -d

# Check status
docker-compose ps

See docs/DEPLOYMENT.md for detailed production deployment instructions.

📊 Services & Ports

Service	Port	Description
Frontend	3000	React development server
Backend API	8001	FastAPI backend
PostgreSQL	5432	Database
Redis	6379	Cache & pub/sub
LiveKit	7880-7882	WebRTC server
MinIO	9000, 9001	Object storage
Grafana	3000	Monitoring dashboards
Prometheus	9090	Metrics collection

🤝 Contributing

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

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

🙏 Acknowledgments

• Backend: FastAPI, PostgreSQL, Redis, LiveKit, OpenAI
• Frontend: React, Vite, Metronic UI, Bootstrap
• Infrastructure: Docker, Prometheus, Grafana

---

Made with ❤️ by Umut Baran Çiçek