Dockerfile

# Use a lightweight Python base image
FROM python:3.10-slim

# Install system dependencies for OCR and Chromium
RUN apt-get update && apt-get install -y \
    libgl1 \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    wget \
    gnupg \
    chromium \
    chromium-driver \
    libreoffice \
    ghostscript \
    tesseract-ocr \
    poppler-utils \
    default-jre \
    && rm -rf /var/lib/apt/lists/*

# Set environment variables for DrissionPage/Chromium
ENV CHROME_BIN=/usr/bin/chromium
ENV CHROMEDRIVER_PATH=/usr/bin/chromedriver

# Create application directory
WORKDIR /app

# Copy requirements and install
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Pre-download models to avoid startup timeouts in Hugging Face Spaces
# This ensures rembg and easyocr models are ready
RUN python -c "import rembg; rembg.new_session('isnet-general-use')"
RUN python -c "import easyocr; easyocr.Reader(['en', 'de'], gpu=False)"

# Copy application code
COPY . .

# Expose the default Hugging Face port
EXPOSE 7860

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