Known issues with AI Registry standalone API

These are some of the known issues you might run into while using AI Registry standlone API.

NGC model download timeout

The NGC model import might time out, and the corresponding model version status is shown as “failed”. You can access the logs found in the API v2 pod by performing the steps mentioned in the Debugging the model import failure troubleshooting section.

Retry the model import request again.

PATCH API does not work

PATCH model/model version API are currently unsupported.

Cloudera AI Inference service is unable to discover the AI Registry

In certain cases, the Cloudera AI Inference service is unable to discover the AI Registry.

After upgrading AI Registry, follow the Manually Updating AI Registry Configuration steps listed in the Troubleshooting section or delete and create model-registry to ensure that Cloudera AI Inference service continues to work.