FROM python:3.11-slim

WORKDIR /app

# Install system dependencies and Poetry
RUN apt-get update && apt-get install -y \
    gcc \
    g++ \
    && rm -rf /var/lib/apt/lists/* \
    && pip install --no-cache-dir poetry==1.7.1

# Copy dependency files
COPY pyproject.toml ./

# Configure Poetry and install dependencies
RUN poetry config virtualenvs.create false \
    && poetry install --no-dev --no-interaction --no-ansi

# Copy source code
COPY src/ ./src/

# Download embedding model during build (cache it) and create data directory
# Note: This downloads ~1.1GB for multilingual support
RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('paraphrase-multilingual-mpnet-base-v2')" \
    && mkdir -p /app/data

# Expose port
EXPOSE 8080

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
    CMD python -c "import requests; requests.get('http://localhost:8080/health')" || exit 1

# Run application
CMD ["python", "-m", "uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8080"]