Dockerfile

# Use Python 3.12 slim image
FROM python:3.12-slim

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    poppler-utils \
    && 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

# Copy the application code
COPY . .

# Create necessary directories
RUN mkdir -p data/uploads data/vector_db

# Set environment variables
ENV PYTHONPATH=/app
ENV PYTHONUNBUFFERED=1

# Expose port
EXPOSE 8000

# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:8000/health || exit 1

# Command to run the application
CMD ["python", "-m", "src.api.main", "--host", "0.0.0.0", "--port", "8000"]