Dockerfile

FROM ubuntu:24.04

ENV DEBIAN_FRONTEND=noninteractive

# 1. Install Python 3.10 + system deps required by Docling (libglib2.0-0, libgl1)
RUN apt-get update && apt-get install -y \
    software-properties-common \
    curl \
    && add-apt-repository ppa:deadsnakes/ppa \
    && apt-get update && apt-get install -y \
    python3.10 \
    python3.10-dev \
    python3.10-distutils \
    build-essential \
    libmagic-dev \
    libglib2.0-0 \
    libgl1 \
    && rm -rf /var/lib/apt/lists/*

# 2. Install pip for Python 3.10
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.10
RUN python3.10 -m pip install --no-cache-dir --upgrade pip

# 3. Install Python requirements
WORKDIR /app
COPY requirements.txt /app/requirements.txt
RUN python3.10 -m pip install --no-cache-dir -r requirements.txt

# 4. FIX: RapidOCR downloads weights at runtime into the system python dir.
# By making the rapidocr directory globally writable, the non-root 'ubuntu' 
# user can successfully save the weights there on the first request.
RUN mkdir -p /usr/local/lib/python3.10/dist-packages/rapidocr/models && \
    chmod -R 777 /usr/local/lib/python3.10/dist-packages/rapidocr

# 5. Ubuntu 24.04 already has UID 1000 as user "ubuntu" — use it directly
RUN chown -R ubuntu:ubuntu /app
USER ubuntu
ENV HOME=/home/ubuntu \
    PATH=/home/ubuntu/.local/bin:$PATH

# 6. Copy application code
COPY --chown=ubuntu . /app

# 7. Block HF persistent user cache interference
ENV PYTHONNOUSERSITE=1

EXPOSE 7860

CMD ["python3.10", "-m", "uvicorn", "app.app:app", "--host", "0.0.0.0", "--port", "7860"]