You've already forked DataMate
* feature: 增加data-juicer算子 * feat: 支持运行data-juicer算子 * feat: 支持data-juicer任务下发 * feat: 支持data-juicer结果数据集归档 * feat: 支持data-juicer结果数据集归档
38 lines
1.4 KiB
Docker
38 lines
1.4 KiB
Docker
FROM ghcr.io/astral-sh/uv:python3.11-bookworm
|
|
|
|
RUN --mount=type=cache,target=/var/cache/apt \
|
|
--mount=type=cache,target=/var/lib/apt \
|
|
apt update \
|
|
&& apt install -y libgl1 libglib2.0-0 vim libmagic1 libreoffice dos2unix swig poppler-utils tesseract-ocr
|
|
|
|
RUN mkdir -p /home/models \
|
|
&& wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar \
|
|
&& tar -xf ch_ppocr_mobile_v2.0_cls_infer.tar -C /home/models \
|
|
&& rm -f ch_*.tar
|
|
|
|
COPY runtime/python-executor /opt/runtime
|
|
COPY runtime/ops /opt/runtime/datamate/ops
|
|
COPY runtime/ops/user /opt/runtime/user
|
|
COPY scripts/images/runtime/start.sh /opt/runtime/start.sh
|
|
|
|
ENV PYTHONPATH=/opt/runtime/datamate/
|
|
ENV UV_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu"
|
|
ENV UV_INDEX_STRATEGY=unsafe-best-match
|
|
|
|
WORKDIR /opt/runtime
|
|
|
|
RUN --mount=type=cache,target=/root/.cache/uv \
|
|
uv pip install -e .[all] --system \
|
|
&& uv pip install -r /opt/runtime/datamate/ops/pyproject.toml --system \
|
|
&& uv pip uninstall torch torchvision --system \
|
|
&& python -m spacy download zh_core_web_sm \
|
|
&& echo "/usr/local/lib/ops/site-packages" > /usr/local/lib/python3.11/site-packages/ops.pth
|
|
|
|
RUN ln -sf /usr/share/zoneinfo/Asia/Shanghai /etc/localtime \
|
|
&& chmod +x /opt/runtime/start.sh \
|
|
&& dos2unix /opt/runtime/start.sh
|
|
|
|
EXPOSE 8081
|
|
|
|
ENTRYPOINT ["/opt/runtime/start.sh"]
|