FROM python:3.10

ARG PIP_NO_CACHE_DIR=1

RUN apt-get update \
    && apt-get install -y tesseract-ocr \
    && rm -rf /var/lib/apt/lists/*

# libssl1.1 for PaddlePaddle
RUN wget http://security.ubuntu.com/ubuntu/pool/main/o/openssl/libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb \
    && dpkg -i libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb \
    && rm libssl1.1_1.1.1f-1ubuntu2.20_amd64.deb

RUN pip install torch==2.1.1 -i https://download.pytorch.org/whl/cpu
RUN pip install paddlepaddle==2.5.1 -i https://mirror.baidu.com/pypi/simple
RUN pip install transformers pytesseract gradio Pillow
RUN pip install paddleocr==2.7.0.3 \
    && pip uninstall -y opencv-python opencv-contrib-python \
    && pip install opencv-python-headless

RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user
WORKDIR $HOME/app
COPY --chown=user . $HOME/app

CMD ["python", "app.py"]