Dockerfile

FROM python:3.12-slim

# Set working directory
WORKDIR /app

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

# Create non-root user (required by HF Spaces)
RUN useradd -m -u 1000 user
ENV HOME=/home/user
ENV PATH=/home/user/.local/bin:$PATH

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

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

# Download sentence-transformers model at build time to avoid runtime delays
RUN python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')"

# Copy application code
COPY . .

# Create necessary directories and set ownership
RUN mkdir -p data/vectordb data/raw data/processed evals/results \
    && chown -R user:user /app

# Switch to non-root user
USER user

# Expose port
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
    CMD curl -f http://localhost:7860/health || exit 1

# Set environment variables
ENV PYTHONUNBUFFERED=1
ENV GRADIO_SERVER_NAME=0.0.0.0
ENV GRADIO_SERVER_PORT=7860

# Run the application
CMD ["python", "app.py"]