Engaging in the AI ecosystem can be a daunting task. There are multiple options to start engaging, but no one gives you a clear path to some level of success. There are stories of advanced math or massive computing required; there must be an easier way. Or, in another way to describe it, we all don’t need to develop Microsoft Word, but it’s essential to know how to use Microsoft Word. In this talk, I’ll be walking through an Open Source project called Caikit which is an Open Source wrapper around multiple AI portions of the ecosystem, so you can see the flexibility that it can give you. We will start with a simple whistle-stop tour of how to understand the AI space then how to access public Open Source models. Then we will move over to my laptop live demoing the Caikit via local containers and cached models to show how easy it is to play with it locally. From there, we will take the demo to the cloud and show a way to deploy it to OpenShift and be able to have an API that can respond with said model(s). Walking out of this room, you’ll see how easy it can be with Open Source software; with a little effort on your computer and downloading some Open Source models, you can start leveraging AI with confidence.
Speakers: JJ Asghar