FROM python:3.11-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    build-essential \
    libreoffice \
    wget \
    && rm -rf /var/lib/apt/lists/*


# Copy requirements first to leverage Docker cache
COPY requirements.txt .
RUN pip install huggingface_hub
RUN wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py
RUN python download_models_hf.py


RUN pip install --no-cache-dir -r requirements.txt
RUN pip install -U magic-pdf[full]


# Copy the rest of the application
COPY . .

# Create storage directories
RUN mkdir -p storage/uploads storage/processed

# Expose the port the app runs on
EXPOSE 8000

# Command to run the application
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]