Files
DataMate/scripts/images/runtime/Dockerfile
Startalker f86d4fae25 feature: add unstructured formatter operator for doc/docx (#17)
* feature: add UnstructuredFormatter

* feature: add UnstructuredFormatter in db

* feature: add unstructured[docx]==0.18.15

* feature: support doc

---------

Co-authored-by: Startalker <438747480@qq.com>
2025-10-23 16:49:03 +08:00

23 lines
776 B
Docker

FROM python:3.11
COPY runtime/python-executor /opt/runtime
COPY runtime/ops /opt/runtime/datamate/ops
ENV PYTHONPATH=/opt/runtime/datamate/
RUN sed -i 's/deb.debian.org/mirrors.huaweicloud.com/g' /etc/apt/sources.list.d/debian.sources \
&& apt update \
&& apt install -y libgl1 libglib2.0-0 vim poppler-utils tesseract-ocr tesseract-ocr-chi-sim libmagic1t64 libreoffice\
&& apt clean \
&& rm -rf /var/lib/apt/lists/*
WORKDIR /opt/runtime
ENV HF_HUB_DISABLE_XET=1
RUN pip install -e . -i https://mirrors.huaweicloud.com/repository/pypi/simple \
&& pip install -r /opt/runtime/datamate/ops/requirements.txt -i https://mirrors.huaweicloud.com/repository/pypi/simple \
&& pip cache purge
RUN ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime