DockerfileB

FROM python:3.8

# Install SDK.
RUN pip install --no-cache-dir apache-beam[gcp]==2.43.0

# Verify that the image does not have conflicting dependencies.
RUN pip check
# install requirements
RUN pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cpu
RUN pip install transformers scipy
RUN pip install pandas

#install cloud sdk for authentication 
ENV GOOGLE_APPLICATION_CREDENTIALS=path to google credentials json file
ENV PATH="${HOME}/.local/bin/:$PATH"

USER root
RUN apt-get update 
RUN apt-get install curl -qq



SHELL ["/bin/bash", "-o", "pipefail", "-e", "-u", "-x", "-c"]

ARG CLOUD_SDK_VERSION=410.0.0
ENV GCLOUD_HOME=/home/google-cloud-sdk

ENV PATH="${GCLOUD_HOME}/bin/:${PATH}"
USER 0

RUN DOWNLOAD_URL="https://dl.google.com/dl/cloudsdk/channels/rapid/downloads/google-cloud-sdk-${CLOUD_SDK_VERSION}-linux-x86_64.tar.gz" \
    && TMP_DIR="$(mktemp -d)" \
    && curl -fL "${DOWNLOAD_URL}" --output "${TMP_DIR}/google-cloud-sdk.tar.gz" \
    && mkdir -p "${GCLOUD_HOME}" \
    && tar xzf "${TMP_DIR}/google-cloud-sdk.tar.gz" -C "${GCLOUD_HOME}" --strip-components=1 \
    && "${GCLOUD_HOME}/install.sh" \
       --bash-completion=false \
       --path-update=false \
       --usage-reporting=false \
       --quiet \
    && rm -rf "${TMP_DIR}" \
    && gcloud --version

# Copy files from official SDK image, including script/dependencies.
COPY --from=apache/beam_python3.8_sdk:2.43.0 /opt/apache/beam /opt/apache/beam

ENV BEAM_HOME=/opt/dataflow

WORKDIR $BEAM_HOME

RUN useradd -m raf && \
    chown -R --from=root raf /opt/dataflow

USER 1001


# prevent the container from shutting down
ENTRYPOINT ["tail"]
CMD ["-f","/dev/null"]