NCP-AI 試験問題を無料オンラインアクセス

An NAI administrator has successfully imported a model from Hugging Face and created an endpoint for the model. The endpoint is in the Active state. From within the Endpoint section in NAI, the endpoint has been tested with a Sample Request, the response is accurate, and the Status shows SucceedeD.
The administrator has provided the endpoint URL and generated and provided API keys to the developers. However, the developers are having issues connecting to the endpoint. They keep getting 400 Bad Request errors when attempting to prompt the model.
What should the administrator do next to ensure the developers are able to successfully prompt the model?

• A.Re-import the model from Hugging Face, create a new endpoint and provide new URL and API keys to the developers.
• B.Provide the developers the 'Sample Request' code from the endpoint by clicking 'View Sample Request'.
• C.Check the Status of the endpoint again to make sure it was not accidentally HibernateD.
• D.Add additional resources to 'scale up' the number of instances of the endpoint.

An administrator has installed and deployed NAI, but the UI is not launching.
Which command should the administrator use to ensure that all pods are successfully deployed?

• A.kubectl get pods -n kube-system
• B.kubectl get pods -n nai-system
• C.kubectl get pods -n ntnx-base
• D.kubectl get pods -n knative-serving

An administrator is working with a development team to integrate a customer service application with a large language model deployed on the Nutanix Enterprise AI platform. The model provides natural language responses, and the secure application needs to send user input and receive model-generated replies in real time.
The following requirements must be met:
The application must be connected to the correct API endpoint exposed by the model.
A valid API key must be used to authenticate each request.
The response format must match the expected schema in the application.
The administrator must test and confirm successful communication before production rollout.
Which step should the administrator perform to configure and validate the application successfully?

• A.Confirm the response meets requirements using the copied endpoint URL and API key from the portal.
• B.Configure access to the endpoint by assigning the application a role in Prism Central.
• C.Set up the application in the hypervisor management interface and validate access using VM-level health checks.
• D.Expose the model endpoint publicly by assigning an external IP address and bypass authentication for faster testing.

Nutanix Enterprise AI supports the NVIDIA GPU Operator when it is configured to use which GPU-virtualization mode?

• A.SR-IOV
• B.GPU paravirtualization
• C.vGPU MIG
• D.GPU Passthrough only

Which widget within the Endpoint Details page can an administrator verify the memory usage associated with the endpoint?

• A.Infrastructure Summary
• B.Endpoints (Top 5)
• C.API Requests Trends
• D.Number of Compute Instances