Supercharge your Cloud-native Applications with Generative AI
Register Now
Event details
Date: June 27, 2024
Time: 16:00 UTC
Abstract
Over 80% of enterprises will have used generative AI (gen AI) APIs or deployed generative AI-enabled applications by 2026, according to Gartner. The barriers for joining these enterprises and integrating generative AI into the application development process are lower than ever. No need for extra funding or complex environments, just the know-how this video provides.
We will illustrate how developers can use gen AI to build, deploy, and run applications locally for little to no cost. We cover how to prototype LLMs for your specific use case and explain how to further evaluate and refine these models.
We will answer questions like:
How do we serve the model? Where do we serve the model? How do we connect to the endpoints? Do we need authorization for some kind of token? How do we monitor not only the model that's being served, but also the application that's able to connect to the model? How do we integrate those with the applications we already have and with new applications we want to build? How do we deploy our model to a Kubernetes environment?
Speakers
Legare Kerrison is a Technical Product Marketing Intern at Red Hat, specializing in Podman Desktop AI. In this role, she creates content and has conversations that drive understanding and adoption of Red Hat’s products.
Ian was a long-time developer in the UK Government space, a JAVA fanatic who worked on various AI and Ux projects until jumping the fence to join Red Hat in 2012. Since then he has been fighting the fight for developers, enthusing about the technologies provided by Red Hat, most notably OpenShift. He now works as a Developer Advocate and will talk about OpenShift all day if you let him.
