Generative AI Development with Podman AI Lab, InstructLab, & OpenShift AI

Let's take a look at how you can get started working with generative AI in your application development process using open-source tools like Podman AI Lab (podman-desktop.io/extensions/...) to help build and serve applications with LLMs, InstructLab (instructlab.ai) to fine-tune models locally from your machine, and OpenShift AI (developers.redhat.com/product...) to handle the operationalizing of building and serving AI on an OpenShift cluster.

[@maxjesch]

Awesome video! super dense information

[@dewaynebranch776]

The world has changed again, wow

[@smithright]

Excellent work, folks. I've been looking for a stack to scale agentic teaming applications. OpenShift seems best in class for hosting scalable AI services, and this AI dev stack already seems impressive and pragmatic.
There are so many data pipeline and orchestration tools. Hosted Apache Beam via GCP DataFlow seems strong for data pipeline orchestration, and I'm considering dedicated openshift on GCP for that reason. I'd be curious about perspectives on the best middleware for service orchestration and canary deployments on openshift.

[@yairrodriguez475]

share the slides

[@techpriestjoe]

A LLM is NOT a database. Tho you can train this behavior to some extend it would be smarter to query against a db, maybe wikipedia for your usecase. Just please please please dont spread this misconception. People already call this an "AI" which it is by far not.