Dockerfile

# Hugging Face Spaces Docker Runtime
FROM python:3.10-slim

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    tesseract-ocr \
    tesseract-ocr-eng \
    poppler-utils \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libgomp1 \
    libgl1 \
    curl \
    && rm -rf /var/lib/apt/lists/*

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

# Install Python dependencies
# Upgrade pip first
RUN pip install --no-cache-dir --upgrade pip setuptools wheel

# Install PyTorch CPU version first (before other packages that might depend on it)
RUN pip install --no-cache-dir --index-url https://download.pytorch.org/whl/cpu \
    torch torchvision

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

# Copy application files
COPY . .

# Create necessary directories
RUN mkdir -p output pdfs uploads

# Expose Hugging Face Spaces default port
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
    CMD curl -f http://localhost:7860/ || exit 1

# Run Flask app
CMD ["python", "app.py"]