Munich-news/QUICKSTART.md

⚡ Quick Start Guide

Get Munich News Daily running in 5 minutes!

📋 Prerequisites

• Docker & Docker Compose installed
• 4GB+ RAM (for AI models)
• (Optional) NVIDIA GPU for faster processing

🚀 Setup Steps

1. Configure Environment

cp backend/.env.example backend/.env
nano backend/.env

Required: Update SMTP_SERVER, EMAIL_USER, and EMAIL_PASSWORD.

2. Start the System

# Auto-detects GPU capabilities and starts services
./start-with-gpu.sh

# Watch installation progress (first time model download ~2GB)
docker-compose logs -f ollama-setup

3. Add News Sources

# Connect to database
docker-compose exec mongodb mongosh munich_news

# Paste this into the mongo shell:
db.rss_feeds.insertMany([
  {
    name: "Süddeutsche Zeitung München",
    url: "https://www.sueddeutsche.de/muenchen/rss",
    active: true
  },
  {
    name: "Merkur München",
    url: "https://www.merkur.de/lokales/muenchen/rss/feed.rss",
    active: true
  }
])

4. Add Yourself as Subscriber

# Still in mongo shell:
db.subscribers.insertOne({
  email: "your-email@example.com",
  active: true,
  tracking_enabled: true,
  subscribed_at: new Date()
})

5. Verify Installation

# 1. Run the crawler manually to fetch news
docker-compose exec crawler python crawler_service.py 5

# 2. Send a test email to yourself
docker-compose exec sender python sender_service.py test your-email@example.com

🎮 Dashboard Access

Once running, access the services:

• Dashboard: http://localhost:3000
• API: http://localhost:5001

⏭️ What's Next?

The system is now fully automated:

1. 6:00 AM: Crawls news and generates AI summaries.
2. 7:00 AM: Sends the daily newsletter.

Useful Commands

# Stop everything
docker-compose down

# View logs for a service
docker-compose logs -f crawler

# Update code & rebuild
docker-compose up -d --build