FROM python:3.11-slim

ENV PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1 \
    DEBIAN_FRONTEND=noninteractive \
    MODEL_CACHE_DIR=/models \
    TORCH_CUDA_ARCH_LIST=""

# Install system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    git \
    curl \
    wget \
    libsndfile1 \
    portaudio19-dev \
    ffmpeg \
    && rm -rf /var/lib/apt/lists/*

# Install torch CPU-only first (before other deps that might pull CUDA)
RUN pip install --no-cache-dir torch torchaudio --index-url https://download.pytorch.org/whl/cpu

# Set up Python virtual environment
WORKDIR /app

# Copy requirements and install Python deps
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application code
COPY . .

# Create model cache directory
RUN mkdir -p ${MODEL_CACHE_DIR}

# Set environment variables for models
ENV TRANSFORMERS_CACHE=${MODEL_CACHE_DIR} \
    HF_HOME=${MODEL_CACHE_DIR}

# Expose WebSocket port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD curl -f http://localhost:8000/docs || exit 1

# Run the application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]