Dockerfile

FROM python:3.11-slim

# Set working directory
WORKDIR /app

# Install system dependencies needed by some Python packages
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first (Docker layer caching)
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Download NLTK data at build time so it's baked into the image
RUN python -c "import nltk; nltk.download('punkt'); nltk.download('punkt_tab'); nltk.download('stopwords')"

# Copy application code
COPY app.py .
COPY agent.py .
COPY tools.py .

# Copy dataset (bundled as the default dataset)
COPY dataset.csv .

# Create writable outputs directory
RUN mkdir -p /app/outputs && chmod 777 /app/outputs

# Expose Streamlit port
EXPOSE 8501

# Health check
HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health || exit 1

# Run Streamlit
CMD ["streamlit", "run", "app.py", \
     "--server.port=8501", \
     "--server.address=0.0.0.0", \
     "--server.headless=true", \
     "--browser.gatherUsageStats=false", \
     "--server.fileWatcherType=none"]