Prerequisites for setting up Cloudera AI Inference service
Consider the following prerequisites before setting up Cloudera AI Inference service.
CDP CLI
To manage your Cloudera AI Inference service using the command-line interface (CLI), you must install the CDP CLI on your local machine. However, if you intend to manage the service solely using the user interface (UI), the CDP CLI is not required.
To create a Cloudera AI Inference service instance using CLI, you must first download and install the CDP CLI on your local machine. To access the download instructions, navigate to from the left navigation menu in the Cloudera Console. You can use CDP CLI version 0.9.123 or later but it is recommended to use the latest available version of the CDP CLI for compatibility with Cloudera AI Inference service.
Compute cluster-enabled Cloudera environment
Cloudera AI Inference service requires a compute cluster-enabled Cloudera 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.
Cloudera AI Registry
A Cloudera AI Registry must first be deployed in the same Cloudera environment in which you plan to deploy Cloudera AI Inference service. That is, Cloudera AI Inference service can
only deploy models registered to a Cloudera AI Registry in the same Cloudera environment. For this release, Cloudera AI Registry version CML2024.09-1 or higher
version must be created before provisioning the Cloudera AI Inference service. If
you have an existing Cloudera AI Registry in the environment, you must
first upgrade it to version CML2024.09-1 before provisioning Cloudera AI Inference service.
