Dockerfile

# Use Python 3.11 slim image as base
FROM python:3.11-slim

# Set working directory
WORKDIR /app

# Install system dependencies required for PDF processing and OCR
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    tesseract-ocr-hin \
    tesseract-ocr-ben \
    tesseract-ocr-tam \
    tesseract-ocr-tel \
    tesseract-ocr-guj \
    tesseract-ocr-mar \
    tesseract-ocr-pan \
    tesseract-ocr-ori \
    tesseract-ocr-asm \
    tesseract-ocr-mal \
    tesseract-ocr-kan \
    libgl1-mesa-dri \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    libgcc-s1 \
    poppler-utils \
    && rm -rf /var/lib/apt/lists/*

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

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

# Copy application code
COPY app/ ./app/

# Create a non-root user for security
RUN useradd --create-home --shell /bin/bash app \
    && chown -R app:app /app
USER app

# Expose port 8000
EXPOSE 7860

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

# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
    CMD curl -f http://localhost:7860/health || exit 1

# Run the application
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]