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 \
    MPLCONFIGDIR=/app/.cache/matplotlib \
    YOLO_CONFIG_DIR=/app/.config/Ultralytics \
    PIP_NO_CACHE_DIR=off \
    PIP_DISABLE_PIP_VERSION_CHECK=on \
    # Ensure pip uses the official PyTorch CPU index for torch related packages
    PIP_EXTRA_INDEX_URL=https://download.pytorch.org/whl/cpu

# Set the working directory in the container
WORKDIR /app

# System libs
RUN apt-get update && apt-get install -y --no-install-recommends \
    libgl1-mesa-glx \
    libglib2.0-0 \
    libopenblas0-pthread \
    libgomp1 \
    libxext6 \
    libxrender-dev \
    libfreetype6-dev && \
    rm -rf /var/lib/apt/lists/*

# Upgrade pip first
RUN python -m pip install --upgrade pip

# --- MODIFIED AND MORE AGGRESSIVE PYTORCH INSTALLATION ---
RUN python -m pip uninstall -y torch torchvision torchaudio

# 2. Install the specific CPU-only PyTorch version using the --index-url for PyTorch's CPU wheelhouse.
RUN python -m pip install --no-cache-dir torch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 --index-url https://download.pytorch.org/whl/cpu


# 3. Verify PyTorch installation during build (same as before)
RUN python -c "import torch; print('PyTorch version during build: ' + torch.__version__); print('Has get_default_device: ' + str(hasattr(torch, 'get_default_device')))"
# --- END MODIFICATION ---

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

# Install other Python dependencies from requirements.txt
RUN python -m pip install --no-cache-dir -r requirements.txt

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

# Create directories
RUN mkdir -p ${MDR_MODEL_DIR} /app/temp_uploads /app/.cache/matplotlib /app/.config/Ultralytics && \
    chmod -R 777 ${MDR_MODEL_DIR} /app/temp_uploads /app/.cache /app/.config

ENV PORT 7860
EXPOSE 7860
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]
VOLUME ${MDR_MODEL_DIR}