Prerequisites for setting up Cloudera AI Inference service

Consider the following prerequisites before setting up Cloudera AI Inference service.

Cloudera Data Platform CLI

You must dowload Cloudera Data Platform CLI and install it on your machine to create a Cloudera AI Inference service instance. For information on how to download Cloudera Data Platform CLI, in the Cloudera Data Platform console, click on the left navigation Help > Download CLI. You must use Cloudera Data Platform CLI version 0.9.123 or higher with Cloudera AI Inference service.

Compute cluster-enabled Cloudera Data Platform environment

Cloudera AI Inference service requires a compute cluster-enabled Cloudera Data Platform environment. You must either create the compute cluster-enabled environment, or convert your existing environment.

Data Lake and Cloudera Manager supported versions

JSON Web Token based authentication from Cloudera AI Workbenches to Cloudera AI Inference service requires Data Lake version 7.2.18 or above, and Cloudera Manager version 7.12 or above.

AI Registry

A AI Registry must first be deployed in the same Cloudera Data Platform environment in which you plan to deploy Cloudera AI Inference service. That is, Cloudera AI Inference service can only deploy models registered to a AI Registry in the same Cloudera Data Platform environment. For this release, AI Registry version CML2024.09-1 or higher version must be created before provisioning the Cloudera AI Inference service. If you have an existing AI Registry in the environment, you must first upgrade it to version CML2024.09-1 before provisioning Cloudera AI Inference service.