# BreakPilot Transcription Worker
# GPU-optimized container for faster-whisper + pyannote.audio
#
# Build: docker build -f Dockerfile.worker -t breakpilot-transcription-worker .
# Run:   docker run --gpus all breakpilot-transcription-worker

FROM python:3.11-slim

# Set environment variables
ENV PYTHONDONTWRITEBYTECODE=1 \
    PYTHONUNBUFFERED=1 \
    PIP_NO_CACHE_DIR=1 \
    PIP_DISABLE_PIP_VERSION_CHECK=1

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

# Create app user (non-root)
RUN useradd --create-home --shell /bin/bash worker
WORKDIR /app

# Install Python dependencies for transcription
COPY requirements-worker.txt .
RUN pip install --no-cache-dir -r requirements-worker.txt

# Copy worker package
COPY transcription_worker/ ./transcription_worker/

# Change ownership
RUN chown -R worker:worker /app

# Switch to non-root user
USER worker

# Create cache directories
RUN mkdir -p /home/worker/.cache/huggingface \
    && mkdir -p /tmp/transcriptions

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD python -c "from transcription_worker.transcriber import WhisperTranscriber; print('OK')" || exit 1

# Entry point - RQ worker
CMD ["python", "-m", "transcription_worker.worker"]