Namespace
datajuicer
Image / Tag
data-juicer:v1.4.1
Content Digest
sha256:f3108f2999bf17a018d4beeee1ac4202dd24bfab89fd2c4d7784c4b9a851550f
Details
Created

2025-07-17 01:23:00 UTC

Size

11.8 GB

Content Digest
Labels
  • com.nvidia.cudnn.version
    9.1.0.70-1
  • maintainer
    NVIDIA CORPORATION <cudatools@nvidia.com>
  • org.opencontainers.image.created
    2025-07-17T00:59:43.478Z
  • org.opencontainers.image.description
    Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷
  • org.opencontainers.image.licenses
    Apache-2.0
  • org.opencontainers.image.ref.name
    ubuntu
  • org.opencontainers.image.revision
    75056862be722cb5c30912919554c4172efdbb93
  • org.opencontainers.image.source
    https://github.com/modelscope/data-juicer
  • org.opencontainers.image.title
    data-juicer
  • org.opencontainers.image.url
    https://github.com/modelscope/data-juicer
  • org.opencontainers.image.version
    v1.4.1

Environment
CUDA_VERSION

12.4.1

JAVA_HOME

/opt/jdk

LD_LIBRARY_PATH

/usr/local/nvidia/lib:/usr/local/nvidia/lib64

LIBRARY_PATH

/usr/local/cuda/lib64/stubs

NCCL_VERSION

2.21.5-1

NVARCH

x86_64

NVIDIA_DRIVER_CAPABILITIES

compute,utility

NVIDIA_PRODUCT_NAME

CUDA

NVIDIA_REQUIRE_CUDA

cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536

NVIDIA_VISIBLE_DEVICES

all

NV_CUDA_COMPAT_PACKAGE

cuda-compat-12-4

NV_CUDA_CUDART_DEV_VERSION

12.4.127-1

NV_CUDA_CUDART_VERSION

12.4.127-1

NV_CUDA_LIB_VERSION

12.4.1-1

NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE

cuda-nsight-compute-12-4=12.4.1-1

NV_CUDA_NSIGHT_COMPUTE_VERSION

12.4.1-1

NV_CUDNN_PACKAGE

libcudnn9-cuda-12=9.1.0.70-1

NV_CUDNN_PACKAGE_DEV

libcudnn9-dev-cuda-12=9.1.0.70-1

NV_CUDNN_PACKAGE_NAME

libcudnn9-cuda-12

NV_CUDNN_VERSION

9.1.0.70-1

NV_LIBCUBLAS_DEV_PACKAGE

libcublas-dev-12-4=12.4.5.8-1

NV_LIBCUBLAS_DEV_PACKAGE_NAME

libcublas-dev-12-4

NV_LIBCUBLAS_DEV_VERSION

12.4.5.8-1

NV_LIBCUBLAS_PACKAGE

libcublas-12-4=12.4.5.8-1

NV_LIBCUBLAS_PACKAGE_NAME

libcublas-12-4

NV_LIBCUBLAS_VERSION

12.4.5.8-1

NV_LIBCUSPARSE_DEV_VERSION

12.3.1.170-1

NV_LIBCUSPARSE_VERSION

12.3.1.170-1

NV_LIBNCCL_DEV_PACKAGE

libnccl-dev=2.21.5-1+cuda12.4

NV_LIBNCCL_DEV_PACKAGE_NAME

libnccl-dev

NV_LIBNCCL_DEV_PACKAGE_VERSION

2.21.5-1

NV_LIBNCCL_PACKAGE

libnccl2=2.21.5-1+cuda12.4

NV_LIBNCCL_PACKAGE_NAME

libnccl2

NV_LIBNCCL_PACKAGE_VERSION

2.21.5-1

NV_LIBNPP_DEV_PACKAGE

libnpp-dev-12-4=12.2.5.30-1

NV_LIBNPP_DEV_VERSION

12.2.5.30-1

NV_LIBNPP_PACKAGE

libnpp-12-4=12.2.5.30-1

NV_LIBNPP_VERSION

12.2.5.30-1

NV_NVML_DEV_VERSION

12.4.127-1

NV_NVPROF_DEV_PACKAGE

cuda-nvprof-12-4=12.4.127-1

NV_NVPROF_VERSION

12.4.127-1

NV_NVTX_VERSION

12.4.127-1

PATH

/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin


Layers

[#000] sha256:3c645031de2917ade93ec54b118d5d3e45de72ef580b8f419a8cdc41e01d042c - 0.23% (28.2 MB)

[#001] sha256:0d6448aff88945ea46a37cfe4330bdb0ada228268b80da6258a0fec63086f404 - 0.04% (4.41 MB)

[#002] sha256:0a7674e3e8fe69dcd7f1424fa29aa033b32c42269aab46cbe9818f8dd7154754 - 0.45% (54.9 MB)

[#003] sha256:b71b637b97c5efb435b9965058ad414f07afa99d320cf05e89f10441ec1becf4 - 0.0% (185 Bytes)

[#004] sha256:56dc8550293751a1604e97ac949cfae82ba20cb2a28e034737bafd7382559609 - 0.0% (6.72 KB)

[#005] sha256:ec6d5f6c9ed94d2ee2eeaf048d90242af638325f57696909f1737b3158d838cf - 10.86% (1.28 GB)

[#006] sha256:47b8539d532f561cac6d7fb8ee2f46c902b66e4a60b103d19701829742a0d11e - 0.0% (62.5 KB)

[#007] sha256:fd9cc1ad8dee47ca559003714d462f4eb79cb6315a2708927c240b84d022b55f - 0.0% (1.64 KB)

[#008] sha256:83525caeeb359731f869f1ee87a32acdfdd5efb8af4cab06d8f4fdcf1f317daa - 0.0% (1.49 KB)

[#009] sha256:8e79813a7b9d5784bb880ca2909887465549de5183411b24f6de72fab0802bcd - 20.9% (2.46 GB)

[#010] sha256:312a542960e3345001fc709156a5139ff8a1d8cc21a51a50f83e87ec2982f579 - 0.0% (86.8 KB)

[#011] sha256:ae033ce9621d2cceaef2769ead17429ae8b29f098fb0350bdd4e0f55a36996db - 5.29% (639 MB)

[#012] sha256:8a4a2db6905f8005f677e222673aa05b227db8ab5c8fbbb588b5ed10a2255738 - 0.0% (732 Bytes)

[#013] sha256:34c229c334dca0d656d081a60562aa07cb11af9268a4a1cecced9a327832269c - 0.99% (119 MB)

[#014] sha256:d5e65a0b4d5b7721218b2917482b040775cd2203c1a96ec43e438632d1815835 - 2.5% (302 MB)

[#015] sha256:4f4fb700ef54461cfa02571ae0db9a0dc1e0cdb5577484a6d75e68dc38e8acc1 - 0.0% (32 Bytes)

[#016] sha256:ebbe5bcfb2ad2077aa573b742123d7ad5fd0d751a849b70bc0d11c78543377fd - 1.52% (183 MB)

[#017] sha256:229fddd3eb954661cc5411d5277ec87a42cd37640079ab0db70d47e913e5a99f - 0.0% (101 Bytes)

[#018] sha256:3c489e2c981e2af34a0e33e078696bf4c4e4eb8e6d91756f2fbe616bca7cdb77 - 0.3% (36.2 MB)

[#019] sha256:8c3a6e39e9f52f1a99708f99586aeaf94df5c497b52e88455be41d5d8107e0f8 - 0.21% (25.4 MB)

[#020] sha256:16a488253d8492f5306e62abe99533cd0d2f5b08e7e9041e9ac0225e5c7fa93f - 0.47% (56.7 MB)

[#021] sha256:9dba77d6dcf119ebfd42e538885f1c7a2f3c499d14728ac363ee39cba9d584ed - 56.23% (6.63 GB)


History
2024-04-10 18:52:02 UTC

/bin/sh -c #(nop) ARG RELEASE

2024-04-10 18:52:02 UTC

/bin/sh -c #(nop) ARG LAUNCHPAD_BUILD_ARCH

2024-04-10 18:52:02 UTC

/bin/sh -c #(nop) LABEL org.opencontainers.image.ref.name=ubuntu

2024-04-10 18:52:02 UTC

/bin/sh -c #(nop) LABEL org.opencontainers.image.version=22.04

2024-04-10 18:52:04 UTC

/bin/sh -c #(nop) ADD file:3bd10da0673e2e72cb06a1f64a9df49a36341df39b0f762e3d1b38ee4de296fa in /

2024-04-10 18:52:04 UTC

/bin/sh -c #(nop) CMD ["/bin/bash"]

2024-04-22 23:42:16 UTC (buildkit.dockerfile.v0)

ENV NVARCH=x86_64

2024-04-22 23:42:16 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536

2024-04-22 23:42:16 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_CUDART_VERSION=12.4.127-1

2024-04-22 23:42:16 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4

2024-04-22 23:42:16 UTC (buildkit.dockerfile.v0)

ARG TARGETARCH

2024-04-22 23:42:16 UTC (buildkit.dockerfile.v0)

LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>

2024-04-22 23:42:16 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/${NVARCH}/cuda-keyring_1.1-1_all.deb && dpkg -i cuda-keyring_1.1-1_all.deb && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit

2024-04-22 23:42:16 UTC (buildkit.dockerfile.v0)

ENV CUDA_VERSION=12.4.1

2024-04-22 23:42:28 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-12-4=${NV_CUDA_CUDART_VERSION} ${NV_CUDA_COMPAT_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit

2024-04-22 23:42:28 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/nvidia/lib" >> /etc/ld.so.conf.d/nvidia.conf && echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit

2024-04-22 23:42:28 UTC (buildkit.dockerfile.v0)

ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin

2024-04-22 23:42:28 UTC (buildkit.dockerfile.v0)

ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64

2024-04-22 23:42:28 UTC (buildkit.dockerfile.v0)

COPY NGC-DL-CONTAINER-LICENSE / # buildkit

2024-04-22 23:42:28 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_VISIBLE_DEVICES=all

2024-04-22 23:42:28 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_LIB_VERSION=12.4.1-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_NVTX_VERSION=12.4.127-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNPP_VERSION=12.2.5.30-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNPP_PACKAGE=libnpp-12-4=12.2.5.30-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBCUSPARSE_VERSION=12.3.1.170-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-4

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBCUBLAS_VERSION=12.4.5.8-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-4=12.4.5.8-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNCCL_PACKAGE_VERSION=2.21.5-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NCCL_VERSION=2.21.5-1

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNCCL_PACKAGE=libnccl2=2.21.5-1+cuda12.4

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ARG TARGETARCH

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-libraries-12-4=${NV_CUDA_LIB_VERSION} ${NV_LIBNPP_PACKAGE} cuda-nvtx-12-4=${NV_NVTX_VERSION} libcusparse-12-4=${NV_LIBCUSPARSE_VERSION} ${NV_LIBCUBLAS_PACKAGE} ${NV_LIBNCCL_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENV NVIDIA_PRODUCT_NAME=CUDA

2024-04-22 23:46:26 UTC (buildkit.dockerfile.v0)

ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_LIB_VERSION=12.4.1-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_CUDART_DEV_VERSION=12.4.127-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_NVML_DEV_VERSION=12.4.127-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBCUSPARSE_DEV_VERSION=12.3.1.170-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNPP_DEV_VERSION=12.2.5.30-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNPP_DEV_PACKAGE=libnpp-dev-12-4=12.2.5.30-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBCUBLAS_DEV_VERSION=12.4.5.8-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBCUBLAS_DEV_PACKAGE_NAME=libcublas-dev-12-4

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBCUBLAS_DEV_PACKAGE=libcublas-dev-12-4=12.4.5.8-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_NSIGHT_COMPUTE_VERSION=12.4.1-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE=cuda-nsight-compute-12-4=12.4.1-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_NVPROF_VERSION=12.4.127-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_NVPROF_DEV_PACKAGE=cuda-nvprof-12-4=12.4.127-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNCCL_DEV_PACKAGE_NAME=libnccl-dev

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNCCL_DEV_PACKAGE_VERSION=2.21.5-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NCCL_VERSION=2.21.5-1

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ENV NV_LIBNCCL_DEV_PACKAGE=libnccl-dev=2.21.5-1+cuda12.4

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

ARG TARGETARCH

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>

2024-04-22 23:54:41 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-dev-12-4=${NV_CUDA_CUDART_DEV_VERSION} cuda-command-line-tools-12-4=${NV_CUDA_LIB_VERSION} cuda-minimal-build-12-4=${NV_CUDA_LIB_VERSION} cuda-libraries-dev-12-4=${NV_CUDA_LIB_VERSION} cuda-nvml-dev-12-4=${NV_NVML_DEV_VERSION} ${NV_NVPROF_DEV_PACKAGE} ${NV_LIBNPP_DEV_PACKAGE} libcusparse-dev-12-4=${NV_LIBCUSPARSE_DEV_VERSION} ${NV_LIBCUBLAS_DEV_PACKAGE} ${NV_LIBNCCL_DEV_PACKAGE} ${NV_CUDA_NSIGHT_COMPUTE_DEV_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit

2024-04-22 23:54:42 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_DEV_PACKAGE_NAME} ${NV_LIBNCCL_DEV_PACKAGE_NAME} # buildkit

2024-04-22 23:54:42 UTC (buildkit.dockerfile.v0)

ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs

2024-04-23 00:11:02 UTC (buildkit.dockerfile.v0)

ENV NV_CUDNN_VERSION=9.1.0.70-1

2024-04-23 00:11:02 UTC (buildkit.dockerfile.v0)

ENV NV_CUDNN_PACKAGE_NAME=libcudnn9-cuda-12

2024-04-23 00:11:02 UTC (buildkit.dockerfile.v0)

ENV NV_CUDNN_PACKAGE=libcudnn9-cuda-12=9.1.0.70-1

2024-04-23 00:11:02 UTC (buildkit.dockerfile.v0)

ENV NV_CUDNN_PACKAGE_DEV=libcudnn9-dev-cuda-12=9.1.0.70-1

2024-04-23 00:11:02 UTC (buildkit.dockerfile.v0)

ARG TARGETARCH

2024-04-23 00:11:02 UTC (buildkit.dockerfile.v0)

LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>

2024-04-23 00:11:02 UTC (buildkit.dockerfile.v0)

LABEL com.nvidia.cudnn.version=9.1.0.70-1

2024-04-23 00:11:02 UTC (buildkit.dockerfile.v0)

RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends ${NV_CUDNN_PACKAGE} ${NV_CUDNN_PACKAGE_DEV} && apt-mark hold ${NV_CUDNN_PACKAGE_NAME} && rm -rf /var/lib/apt/lists/* # buildkit

2025-07-17 01:06:57 UTC (buildkit.dockerfile.v0)

RUN /bin/sh -c sed -i 's/archive.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list && sed -i 's/security.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list # buildkit

2025-07-17 01:09:21 UTC (buildkit.dockerfile.v0)

RUN /bin/sh -c DEBIAN_FRONTEND=noninteractive apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y git curl vim wget python3.10 libpython3.10-dev python3-pip libgl1-mesa-glx libglib2.0-0 && ln -sf /usr/bin/python3.10 /usr/bin/python3 && ln -sf /usr/bin/python3.10 /usr/bin/python && apt-get autoclean && rm -rf /var/lib/apt/lists/* && pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple # buildkit

2025-07-17 01:14:11 UTC (buildkit.dockerfile.v0)

RUN /bin/sh -c DEBIAN_FRONTEND=noninteractive apt-get update && DEBIAN_FRONTEND=noninteractive apt-get install -y ffmpeg libsm6 libxext6 software-properties-common build-essential cmake gfortran libopenblas-dev liblapack-dev postgresql postgresql-contrib libpq-dev # buildkit

2025-07-17 01:14:11 UTC (buildkit.dockerfile.v0)

WORKDIR /opt

2025-07-17 01:14:29 UTC (buildkit.dockerfile.v0)

RUN /bin/sh -c wget https://aka.ms/download-jdk/microsoft-jdk-17.0.9-linux-x64.tar.gz -O jdk.tar.gz && tar -xzf jdk.tar.gz && rm -rf jdk.tar.gz && mv jdk-17.0.9+8 jdk # buildkit

2025-07-17 01:14:29 UTC (buildkit.dockerfile.v0)

ENV JAVA_HOME=/opt/jdk

2025-07-17 01:14:29 UTC (buildkit.dockerfile.v0)

WORKDIR /data-juicer

2025-07-17 01:14:31 UTC (buildkit.dockerfile.v0)

RUN /bin/sh -c pip install uv -i https://pypi.tuna.tsinghua.edu.cn/simple # buildkit

2025-07-17 01:14:36 UTC (buildkit.dockerfile.v0)

RUN /bin/sh -c uv pip install --upgrade setuptools==69.5.1 setuptools_scm -i https://pypi.tuna.tsinghua.edu.cn/simple --system && uv pip install http://dail-wlcb.oss-cn-wulanchabu.aliyuncs.com/data_juicer/recognize-anything-main.zip -i https://pypi.tuna.tsinghua.edu.cn/simple --system # buildkit

2025-07-17 01:14:37 UTC (buildkit.dockerfile.v0)

COPY . . # buildkit

2025-07-17 01:23:00 UTC (buildkit.dockerfile.v0)

RUN /bin/sh -c uv pip install -v -e .[all] -i https://pypi.tuna.tsinghua.edu.cn/simple --system && python -c "import nltk; nltk.download('punkt_tab'); nltk.download('punkt'); nltk.download('averaged_perceptron_tagger'); nltk.download('averaged_perceptron_tagger_eng')" # buildkit

Danger Zone
Delete Tag

Please be careful as this will not just delete the reference but also the actual content!

For example when you have latest and v1.2.3 both pointing to the same image
the deletion of latest will also permanently remove v1.2.3.

Delete