Prerequisites for Cloudera AI Registry standalone API
To set up the Cloudera AI Registry standalone API, configure the Cloudera AI Inference service and import pretrained Models.
Prerequisites for Cloudera AI Inference service
Consider the following prerequisites before setting up Cloudera AI Inference service
-
Cloudera Manager supported versions: JSON Web Token-based authentication from Cloudera Control Plane to Cloudera AI Inference service requires Cloudera Manager version 7.12 or higher.
-
LDAP Authentication: User authentication is performed by the Knox service running on Cloudera AI Inference service, which relies on the LDAP configuration defined in the Cloudera Control Plane. Without this LDAP integration, access to APIs and model endpoints is denied.
-
Ozone Credentials: Cloudera AI Inference service requires read-only Ozone S3 credentials to access Ozone for model downloads. Both Ozone and Cloudera AI Inference service must reside within the same Cloudera Manager, as Ozone certificates are dynamically retrieved from the base cluster during Cloudera AI Inference service provisioning.
Prerequisites to import pretrained models
You must add the URL details to allow them in the firewall rules.
NVIDIA GPU Cloud (NGC)
Add the following URL details so they can be allowed in the firewall's rules.
- prod.otel.kaizen.nvidia.com (NVIDIA open telemetry)
- api.ngc.nvidia.com
- files.ngc.nvidia.com
Hugging Face
- huggingface.co
- cdn-lfs.huggingface.co
- *.cloudfront.net (CDN)