Munich-news/OLLAMA_INTEGRATION.md

Ollama Integration Complete ✅

What Was Added

1. Ollama Service in Docker Compose

   • Runs Ollama server on port 11434
   • Persists models in ollama_data volume
   • Health check ensures service is ready

2. Automatic Model Download

   • ollama-setup service automatically pulls phi3:latest (2.2GB)
   • Runs once on first startup
   • Model is cached in volume for future use

3. Configuration Files

   • docs/OLLAMA_SETUP.md - Comprehensive setup guide
   • configure-ollama.sh - Helper script to switch between Docker/external Ollama
   • Updated README.md with Ollama setup instructions

4. Environment Configuration

   • Updated backend/.env to use http://ollama:11434 (internal Docker network)
   • All services can now communicate with Ollama via Docker network

Current Status

✅ Ollama service running and healthy ✅ phi3:latest model downloaded (2.2GB) ✅ Translation feature working with integrated Ollama ✅ Summarization feature working with integrated Ollama

Quick Start

# Start all services (including Ollama)
docker-compose up -d

# Wait for model download (first time only, ~2-5 minutes)
docker-compose logs -f ollama-setup

# Verify Ollama is ready
docker-compose exec ollama ollama list

# Test the system
docker-compose exec crawler python crawler_service.py 1

Switching Between Docker and External Ollama

# Use integrated Docker Ollama (recommended)
./configure-ollama.sh
# Select option 1

# Use external Ollama server
./configure-ollama.sh
# Select option 2

Performance Notes

• First request: ~6 seconds (model loading)
• Subsequent requests: 0.5-2 seconds (cached)
• Translation: 0.5-6 seconds per title
• Summarization: 5-90 seconds per article (depends on length)

Resource Requirements

• RAM: 4GB minimum for phi3:latest
• Disk: 2.2GB for model storage
• CPU: Works on CPU, GPU optional

Alternative Models

To use a different model:

1. Update OLLAMA_MODEL in backend/.env
2. Pull the model:

   docker-compose exec ollama ollama pull <model-name>
   

Popular alternatives:

• gemma2:2b - Smaller, faster (1.6GB)
• llama3.2:latest - Larger, more capable (2GB)
• mistral:latest - Good balance (4.1GB)