Summary

In this chapter, you learned about how to asynchronously and securely deliver an ML model to Edge nodes without stopping the running service. We also covered the steps for setting up a container that can be optionally deployed by simply modifying the node-policy property, publishing a model file, and retrieving that at the Edge. The service-mms example service was kept simple as a shell script so that you could easily understand the steps involved. You also got the opportunity to practice hzn mms commands with various subcommand options. In Chapter 14, Building a Real-World Example Application, we will use the MMS concept presented here to build an ML-based application that detects objects in a video stream.

But first, let’s delve deeper into the features Open Horizon provides to help you protect your edge computing solution in the next chapter.