Dockerfile

# Use official Python image
FROM python:3.10

# Set working directory
WORKDIR /app

# Copy project files
COPY . /app

# Install system dependencies required for OCR
RUN apt-get update && apt-get install -y \
    poppler-utils \
    tesseract-ocr \
    libgl1 \
    && rm -rf /var/lib/apt/lists/*

# Upgrade pip
RUN pip install --upgrade pip

# Install Python dependencies
RUN pip install -r requirements.txt

# Download spacy dependency
RUN python -m spacy download en_core_web_sm

# Expose port used by HuggingFace Spaces
EXPOSE 7860

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