Serve ML Models on Kubernetes with Bodywork

This repository demonstrates how to deploy a ML prediction service service on Kubernetes, using Bodywork. For information on this demo, take a look here. To run this project, follow the steps below. If you are new to Kubernetes, then take a look at our Kubernetes Quickstart Guide.

Install Bodywork

Bodywork is distributed as a Python package that can be installed using Pip,

$ pip install bodywork

Deploy the Service

To deploy the service defined in this repository run,

$ bodywork create deployment https://github.com/bodywork-ml/bodywork-serve-model-project

Logs will be streamed to your terminal until the job has been successfully completed.

Make this Project Your Own

This repository is a GitHub template repository that can be automatically copied into your own GitHub account by clicking the Use this template button above.

After you've cloned the template project, use official Bodywork documentation to help modify the project to meet your own requirements.