Ad hoc

We strongly recommand to use the Docker image for the pipeline dependency management. Please check the Docker image creation guide here!!!

However, if you are not familiar with Docker, and you want a quick solution to manage the extra dependencies for your pipeline, you can use the default runtime image provided by the IDOML platform and install the extra dependencies in the notebook cell using the !pip install command. Be sure that the command should be executed at the beginning of the notebook.

IDOML platform provides a default runtime image with different python versions and the most common libraries for data science and machine learning. You can select the runtime image when you create a new pipeline.