Files
DataMate/scripts/images/runtime/Dockerfile
Jerry Yan 8fdc7d99b8 feat(docker): 优化 Dockerfile 支持弱网环境缓存
- 使用缓存挂载 DataX 源码,避免重复克隆提高构建效率
- 添加 NLTK 数据缓存挂载并增加失败检查机制
- 实现 PaddleOCR 模型下载缓存,支持离线重用
- 集成 spaCy 模型缓存机制,提升安装稳定性
- 优化构建流程适配弱网环境下的依赖下载
2026-01-31 14:31:47 +08:00

59 lines
2.6 KiB
Docker

FROM ghcr.nju.edu.cn/astral-sh/uv:python3.11-bookworm
# 配置 apt 阿里云镜像源
RUN --mount=type=cache,target=/var/cache/apt \
--mount=type=cache,target=/var/lib/apt \
if [ -f /etc/apt/sources.list.d/debian.sources ]; then \
sed -i 's/deb.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list.d/debian.sources; \
elif [ -f /etc/apt/sources.list ]; then \
sed -i 's/deb.debian.org/mirrors.aliyun.com/g' /etc/apt/sources.list; \
fi \
&& apt update \
&& apt install -y libgl1 libglib2.0-0 vim libmagic1 libreoffice dos2unix swig poppler-utils tesseract-ocr
# 使用缓存挂载下载 PaddleOCR 模型,支持弱网环境
RUN --mount=type=cache,target=/tmp/models \
mkdir -p /home/models \
&& if [ ! -f /tmp/models/ch_ppocr_mobile_v2.0_cls_infer.tar ]; then \
echo "Downloading PaddleOCR model..."; \
wget -O /tmp/models/ch_ppocr_mobile_v2.0_cls_infer.tar https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar || exit 1; \
else \
echo "Using cached PaddleOCR model"; \
fi \
&& tar -xf /tmp/models/ch_ppocr_mobile_v2.0_cls_infer.tar -C /home/models
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
# 配置 uv 使用阿里云 PyPI 镜像
ENV UV_INDEX_URL="https://mirrors.aliyun.com/pypi/simple/"
WORKDIR /opt/runtime
# 使用缓存挂载 spaCy 模型,支持弱网环境
RUN --mount=type=cache,target=/root/.cache/uv \
--mount=type=cache,target=/tmp/spacy-models \
uv pip install -e .[all] --system \
&& uv pip install -r /opt/runtime/datamate/ops/pyproject.toml --system \
&& if [ ! -f /tmp/spacy-models/zh_core_web_sm-3.8.0-py3-none-any.whl ]; then \
echo "Downloading spaCy model..."; \
wget -O /tmp/spacy-models/zh_core_web_sm-3.8.0-py3-none-any.whl https://ghproxy.net/https://github.com/explosion/spacy-models/releases/download/zh_core_web_sm-3.8.0/zh_core_web_sm-3.8.0-py3-none-any.whl || exit 1; \
else \
echo "Using cached spaCy model"; \
fi \
&& uv pip install /tmp/spacy-models/zh_core_web_sm-3.8.0-py3-none-any.whl --system \
&& 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"]