FROM nvidia/cuda:11.8-runtime-ubuntu22.04

# Set environment variables
ENV DEBIAN_FRONTEND=noninteractive
ENV PYTHONUNBUFFERED=1

# Install system dependencies
RUN apt-get update && apt-get install -y \
    python3 \
    python3-pip \
    python3-dev \
    ffmpeg \
    git \
    wget \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Copy requirements first for better Docker layer caching
COPY requirements.txt .

# Install Python dependencies
RUN pip3 install --no-cache-dir -r requirements.txt

# Copy source code
COPY src/ ./src/

# Create necessary directories
RUN mkdir -p /app/audio/processed /app/models /app/logs

# Download Whisper model cache (optional - will download on first use if not present)
# RUN python3 -c "from faster_whisper import WhisperModel; WhisperModel('large-v2', device='cpu')"

# Run as non-root user
RUN useradd -m -u 1001 whisper
RUN chown -R whisper:whisper /app
USER whisper

# Health check
HEALTHCHECK --interval=30s --timeout=15s --start-period=60s --retries=3 \
    CMD python3 src/healthcheck.py || exit 1

# Expose port
EXPOSE 8000

# Start the service
CMD ["python3", "src/api.py"]