RUN cat /kaggle_requirements.txt >> /requirements.txt

# Install Kaggle packages

RUN uv pip install --system --no-cache -r /requirements.txt

# Install manual packages:

# b/183041606#comment5: the Kaggle data proxy doesn't support these APIs. If the library is missing, it falls back to using a regular BigQuery query to fetch data.

RUN uv pip uninstall --system --no-cache google-cloud-bigquery-storage

# uv cannot install this in requirements.txt without --no-build-isolation

# to avoid affecting the larger build, we'll post-install it.

RUN uv pip install --no-build-isolation --no-cache --system "git+https://github.com/Kaggle/learntools"

# newer daal4py requires tbb>=2022, but libpysal is downgrading it for some reason

RUN uv pip install --system --no-cache "tbb>=2022" "libpysal==4.9.2"

# b/404590350: Ray and torchtune have conflicting tune cli, we will prioritize torchtune.

# b/315753846: Unpin translate package, currently conflicts with adk 1.17.0

# b/468379293: Unpin Pandas once cuml/cudf are compatible, version 3.0 causes issues

# b/468383498: numpy will auto-upgrade to 2.4.x, which causes issues with numerous packages

# b/468367647: Unpin protobuf, version greater than v5.29.5 causes issues with numerous packages

RUN uv pip install --system --force-reinstall --no-cache --no-deps torchtune "google-cloud-translate==3.12.1" "numpy==2.0.2" "pandas==2.2.2"

RUN uv pip install --system --force-reinstall --no-cache "protobuf==5.29.5"

# Adding non-package dependencies:

ADD clean-layer.sh /tmp/clean-layer.sh

# Install GPU-specific non-pip packages.

{{ if eq .Accelerator "gpu" }}

RUN uv pip install --system --no-cache "pycuda"

{{ end }}

$PACKAGE_PATH/tensorflow_decision_forests/keras/

RUN apt-get install -y libfreetype6-dev && \

apt-get install -y libglib2.0-0 libxext6 libsm6 libxrender1 libfontconfig1 --fix-missing && \

/tmp/clean-layer.sh

RUN mkdir -p /usr/share/nltk_data && \

# NLTK Downloader no longer continues smoothly after an error, so we explicitly list

/tmp/clean-layer.sh

# Tesseract and some associated utility packages

RUN apt-get install tesseract-ocr -y && \

/tmp/clean-layer.sh

ENV TESSERACT_PATH=/usr/bin/tesseract \

# For Facets, we also include an empty path to include $PWD.

# install imagemagick for wand

# https://docs.wand-py.org/en/latest/guide/install.html#install-imagemagick-on-debian-ubuntu

RUN apt-get install libmagickwand-dev && \

/tmp/clean-layer.sh

# Override default imagemagick policies

ADD patches/imagemagick-policy.xml /etc/ImageMagick-6/policy.xml