Dockerfile

FROM python:3.10-slim

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

# 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

# Copy application code
COPY . .

# Create models directory for persistent storage
RUN mkdir -p /data/models

# Set environment variables
ENV MODEL_CACHE_DIR=/data/models
ENV HOST=0.0.0.0
ENV PORT=8501
ENV STREAMLIT_SERVER_PORT=8501
ENV STREAMLIT_SERVER_HEADLESS=true
ENV STREAMLIT_BROWSER_GATHER_USAGE_STATS=false

# Expose port
EXPOSE 8501

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

# Download a small model during build (TinyLlama is lightweight)
RUN python scripts/download_models.py --model tiny-llama --cache-dir /data/models

# Command to run the Streamlit app
CMD ["streamlit", "run", "src/streamlit_app.py"]