During this session, we’ll show you how to use deepset’s Haystack framework and NVIDIA NIM to build and deploy a compound AI application that can run on-premise as well as in cloud native environments.

‍

First, you’ll learn some basics about NVIDIA NIM, which is a collection of containerized microservices designed for optimized inference of state-of-the-art AI models. We’ll follow that with a coding demonstration of building a RAG application with Haystack. Then we’ll show you how to deploy this application with Kubernetes and scale it up.

‍

You’ll leave with not only a better understanding of how to build and scale AI applications, but 1000 free NVIDIA inference requests, so you can try out different models for yourself.

‍