Dockerfile

# Video Transcription with AI Persona - Docker Image
FROM python:3.11-slim

# Install system dependencies
RUN apt-get update && apt-get install -y \
    ffmpeg \
    libsndfile1 \
    git \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Create non-root user
RUN useradd -m -u 1000 appuser

# Set working directory
WORKDIR /app

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

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

# Download Whisper model during build (base model for balance of speed/accuracy)
RUN python -c "import whisper; whisper.load_model('base')"

# Copy application code
COPY . .

# Create data directory for persistent storage
RUN mkdir -p /app/data && chown -R appuser:appuser /app

# Switch to non-root user
USER appuser

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV STREAMLIT_SERVER_PORT=8501
ENV STREAMLIT_SERVER_ADDRESS=0.0.0.0

# Expose Streamlit port
EXPOSE 8501

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:8501/_stcore/health || exit 1

# Run the application
CMD ["streamlit", "run", "main.py", "--server.port=8501", "--server.address=0.0.0.0"]