Get Started

Follow the steps below to begin deploying projects, or browse our library of templates and tutorials

Bodywork terminal demo.

How to deploy your project using Bodywork

Deploy your project to Kubernetes in just a few simple steps
Deploy machine learning pipeline

1.

Bodywork is distributed as a Python package. Download it from PyPI.

2.

Add a bodywork.yaml file to your Python project’s Git repo. The contents of this file describes how your project will be deployed.

Bodywork command line interface (CLI).

That's it, you've now deployed your Python project to Kubernetes!

You don’t need to build your own Docker images or understand how to create Kuberentes resources.

Bodywork will fill the gap between executable Python modules and operational jobs and services.

If you’re new to Kubernetes, then check out our guide to Kubernetes for ML - we’ll have you up-and-running with a test cluster on your local machine, in under 10 minutes.

Bodywork command line interface (CLI).

Templates & Tutorials

Use one of the templates below to get a head start deploying your project

bodywork logo

Deploying a model scoring-service.

bodywork logo

Batch-scoring a dataset with a pre-trained ML model.

bodywork logo

How to deploy an automated train-and-serve pipeline.

bodywork logo

A guide to deploying MLflow (and other Python services) to Kubernetes, using Bodywork.

bodywork logo

Build ML pipelines using Jupyter notebooks with Bodywork.

bodywork logo

Rapid deployment of Scikit-Learn models to Kubernetes, using FastAPI with Bodywork.

bodywork logo

Deploying probabilistic programs using PyMC3 with Bodywork.

bodywork logo

Train a ML model and then deploy a Plotly dashboard to visualise performance metrics.

More templates and tutorials can be found on GitHub

GitHub

Subscribe to our Newsletter

You can unsubscribe at any time by clicking on the 'unsubscribe' link in the footer of our emails.

Thank you for subscribing to our newsletter!
Oops! Something went wrong while submitting the form.