Deploying with custom Python environments

When you deploy, Modelbit will detect the pip packages needed to replicate your Notebook's environment.

To supply a custom Python environment, use the python_version, python_packages and system_packages parameters.

To deploy to a custom environment with a specific version of sklearn:

mb.deploy(my_deploy_function, python_packages=["scikit-learn==1.0.2",])

To deploy to a custom environment with a specific versions of multiple pip packages:

mb.deploy(my_deploy_function, python_packages=["scikit-learn==1.0.2", "xgboost==1.5.2"])

To deploy to a custom environment with a specific version of Python:

mb.deploy(my_deploy_function, python_version="3.9")

To deploy to a custom environment with specific system libraries (installed using apt-get):

mb.deploy(my_deploy_function, system_packages=["libgomp1"])

With custom Python environment it's possible to deploy many kinds of models. Here are some examples:

• Example sklearn deployment
• Example XGBoost deployment
• Example PyCaret deployment
• Example Prince PCA deployment
• Example BTYD deployment
• Example Prophet deployment
• Example fasttext deployment

Including private packages in your Python environments

You can also upload shared Python libraries and helper code to be available in your Python environments.