Dockerfile

FROM python:3.11-slim

# Set environment variables
ENV PYTHONUNBUFFERED=1 \
    MDR_MODEL_DIR=/models \
    MDR_DEVICE=cpu \
    MDR_TABLE_FORMAT=MARKDOWN \
    LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH

# Set the working directory in the container
WORKDIR /app

# Install system dependencies required by OpenCV and potentially others
RUN apt-get update && apt-get install -y --no-install-recommends \
    libgl1-mesa-glx \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libfreetype6-dev \
    && rm -rf /var/lib/apt/lists/*

# Copy the requirements file into the container
COPY requirements.txt .

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

# Copy the application code into the container
COPY mdr_pdf_parser.py .
COPY main.py .

# Create the default model directory and a temp directory
RUN mkdir -p ${MDR_MODEL_DIR} /app/temp_uploads && \
    chmod -R 777 ${MDR_MODEL_DIR} /app/temp_uploads

# Expose the port the app runs on
EXPOSE 8000

CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

# This allows mounting a host directory for persistent models
VOLUME ${MDR_MODEL_DIR}