start.sh

#!/bin/bash

# Start Ollama in background
ollama serve &

# Wait for Ollama to be ready
echo "Waiting for Ollama to start..."
until curl -s http://localhost:11434/api/tags > /dev/null 2>&1; do
  sleep 2
done

echo "Ollama ready. Pulling Qwen2.5-Coder-7B..."
ollama pull qwen2.5-coder:7b

echo "Model ready. Kodingo inference service is live."

# Keep container running
wait