run.sh

#!/bin/bash
set -e

# Cleanup on exit (Ctrl+C, terminal close, etc.)
cleanup() {
    echo "Shutting down..."
    kill $BACKEND_PID 2>/dev/null
    wait $BACKEND_PID 2>/dev/null
}
trap cleanup EXIT INT TERM

# Start Ollama if not already running
if ! pgrep -x "ollama" > /dev/null; then
    echo "Starting Ollama..."
    ollama serve &
    sleep 3
fi

# Pull model if not already present
echo "Pulling model (llama3.2:latest)..."
ollama pull llama3.2:latest

# Start backend
echo "Starting FastAPI backend on port 8000..."
uvicorn backend.main:app --host 0.0.0.0 --port 8000 &
BACKEND_PID=$!
echo "Waiting for backend to be ready..."
MAX_WAIT=120
WAITED=0
until curl -sf http://localhost:8000/health > /dev/null 2>&1; do
    if [ $WAITED -ge $MAX_WAIT ]; then
        echo "ERROR: Backend failed to start within ${MAX_WAIT}s"
        exit 1
    fi
    sleep 1
    WAITED=$((WAITED + 1))
done
echo "Backend is ready (took ~${WAITED}s)"

# Start frontend (blocks until user exits)
echo "Starting Streamlit frontend on port 8501..."
streamlit run frontend/app.py --server.port 8501