Dockerfile

# Use Python 3.11 slim image for smaller size
FROM python:3.11-slim

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    gcc \
    g++ \
    && rm -rf /var/lib/apt/lists/*

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

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

# Install additional dependencies for Hugging Face datasets
RUN pip install --no-cache-dir datasets huggingface_hub

# Copy all application files
COPY . .

# Expose port
EXPOSE 8501

# Set environment variables
ENV PYTHONPATH=/app
ENV STREAMLIT_SERVER_PORT=8501
ENV STREAMLIT_SERVER_ADDRESS=0.0.0.0

# Health check
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health

# Run the app + background scheduler
CMD ["bash", "start.sh"]