New Year Sale Limited Time 70% Discount Offer - Ends in 0d 00h 00m 00s - Coupon code: 70percent

Nutanix NCP-AI Nutanix Certified Professional - Artificial Intelligence NCP-AI 6.10 Exam Practice Test

Demo: 22 questions
Total 75 questions

Nutanix Certified Professional - Artificial Intelligence NCP-AI 6.10 Questions and Answers

Question 1

What prerequisites must be skipped when adding GPU nodes to a managed Kubernetes service on an Azure AKS cluster using Azure CLI?

Options:

A.

Install the GPU driver

B.

Install the Worker driver

C.

Install the Worker Connector

D.

Install the GPU Connector

Question 2

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?

Options:

A.

Provide the developers the 'Sample Request' code from the endpoint by clicking 'View Sample Request'.

B.

Check the Status of the endpoint again to make sure it was not accidentally Hibernated.

C.

Re-import the model from Hugging Face, create a new endpoint and provide new URL and API keys to the developers.

D.

Add additional resources to 'scale up' the number of instances of the endpoint.

Question 3

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

Options:

A.

API Requests Trends

B.

Infrastructure Summary

C.

Endpoints (Top 5)

D.

Number of Compute Instances

Question 4

An administrator needs to spot the busiest credentials at a glance.

Which Dashboard widget provides insight into the most frequently used credentials?

Options:

A.

Endpoints Summary

B.

API Keys (Top 5)

C.

Infrastructure Summary

D.

API Requests Trends

Question 5

An administrator is deploying the required infrastructure on-premise using NKP on Nutanix to install NAI.

Which type of storage should be created during the deployment process to save the models?

Options:

A.

Volume

B.

CIFS

C.

NFS

D.

Block

Question 6

Which deployment type of Nutanix Enterprise AI is supported in Amazon EKS?

Options:

A.

Standalone

B.

Cloud Cluster

C.

GPT-in-a-Box 2.0

D.

Bare Metal

Question 7

An AI/ML administrator has received a message from the cloud platform operations team who manage the underlying compute infrastructure that there may be a resource consumption issue impacting the workload.

The AI/ML administrator isn't aware of any problems reported from the consumers of the Nutanix Enterprise AI system but has noted that additional workloads were placed on the platform recently, as well as the introduction of GPUs.

With the cloud platform team reporting a resource consumption issue, and the consumers of the service not reporting any issues, what steps should the AI/ML administrator take?

Options:

A.

Ask the Cloud Platform Operations Team to add additional CPUs to the Nutanix Enterprise AI Servers.

B.

Increase the Endpoint instances for all of the configured Endpoints on the Nutanix Enterprise AI platform.

C.

Review the Cluster & Node Usage to identify if a specific resource is being exhausted and increase it.

D.

Ask the Cloud Platform Operations Team to scale the Kubernetes Cluster worker nodes up/out.

Question 8

Which endpoint attribute displays the number and name of the GPUs per instance?

Options:

A.

Accelerator

B.

Description

C.

Status

D.

Inference Engine

Question 9

An administrator logs onto the Nutanix Enterprise AI Dashboard and notices that all current GPU and non-GPU Endpoints are marked as Hibernated. After reviewing the Audit Events section, the administrator notes that no anomalous behavior events have occurred since the day before.

What is the most likely cause as to why all of the current Endpoints are hibernated seemingly at random?

Options:

A.

The GPU GB license has been exceeded.

B.

The vCPU and GPU GB licenses has expired.

C.

The vCPU and GPU GB trial licenses are close to expiry.

D.

The vCPU license has expired.

Question 10

An AI/ML admin is testing access to an endpoint using Open AI compatible clients, but is unable to successfully access the endpoint.

What could be the issue?

Options:

A.

API key has been created by another AI/ML admin.

B.

Endpoint has not been configured with the right LLM.

C.

API key has been removed from the endpoint.

D.

Endpoint as been created by another AI/ML admin.

Question 11

An AI/ML administrator is monitoring a Nutanix Enterprise AI cluster and receives an alert that the cluster's health status is Critical.

The administrator logs into the NAI Dashboard and gathers the following information:

The Infrastructure Summary component is marked as Critical (red status).

A system message indicates that their newly added Custom Chatbot service is waiting for available resources to start.

A resource usage summary shows that CPU usage is at or near 100%.

Other services are running but are responding more slowly than usual.

The cluster is currently not configured to automatically add more resources when needed.

Based on the information that the administrator gathered, what is the most appropriate action that the administrator should take to remediate the issue?

Options:

A.

Enable automatic resource scaling within NKP and allow for more CPU resources to be allocated to the clusters.

B.

Enable automatic resource scaling within NAI to allow for more CPU resources to be allocated to the clusters.

C.

Restart the Kubernetes node in a rollout fashion within Prism Central.

D.

Restart the Kubernetes node in a rollout fashion within NAI Dashboard.

Question 12

An Accounting Department is thrilled with the RAG Application that the Application & Data Science Teams recently rolled out. However, they provided some feedback that sometimes (approximately 20% of the time), the documents retrieved are not relevant to their prompts or are too generic.

During development, there was extensive testing between models to make sure the best possible model was selected. The Accounting Department emphasizes that when the responses use the right documents, the results are very good and they are pleased with the completeness, accuracy, and coherence of those responses.

What would be a way to address the irrelevant RAG results without having to rebuild the entire workflow?

Options:

A.

Replace the embedding model with a larger, more general-purpose language model to improve document retrieval.

B.

Fine-tune the Large Language Model on a broader dataset to enable it to generate more relevant responses.

C.

Implement a rerank model as a post retrieval step to re-order initially retrieved documents based on query-document relevance.

D.

Significantly expand the document knowledge base by ingesting a much larger volume of financial reports.

Question 13

How should a non-text-generation LLM endpoint be tested?

Options:

A.

Copy the Sample API Code and URL and run it in the application.

B.

Select Custom Request and upload the provided test file, and click Test.

C.

Create a Sample Request, choose a default prompt, and click Test.

D.

Open the URL on a Browser on the HTTPS web page.

Question 14

An administrator is setting up Nutanix Enterprise AI with a custom domain (ai.company.com) and must comply with security policies requiring a valid TLS certificate from the corporate certificate authority (CA).

Which two steps are necessary to complete this configuration successfully? (Choose two.)

Options:

A.

Add a DNS A record pointing ai.company.com to the NAI IP address in a DNS server.

B.

Create a DNS PTR record for ai.company.com to match the DNS A record.

C.

A CA signed TLS certificate for the configured NAI FQDN.

D.

Use the Nutanix Prism interface to directly assign the FQDN ai.company.com to the NAI IP address.

Question 15

An administrator needs to search for an available NAI helm chart version.

Which command should the administrator use?

Options:

A.

helm pull ntnx-charts/nai-core --versions

B.

helm repo list ntnx-charts/nai-core

C.

helm search repo ntnx-charts/nai-core --versions

D.

helm repo get ntnx-charts --versions

Question 16

An administrator is configuring a new endpoint in Nutanix Enterprise AI (NAI) using an NVIDIA NIM model. During the configuration, the administrator notices that the Use GPU checkbox is selected and cannot be modified.

What is the reason the checkbox is locked in this state?

Options:

A.

Setting is locked due to a cluster-level policy restriction.

B.

All endpoints in NAI require using GPUs.

C.

System has already validated the endpoint configuration.

D.

These models require GPU resources to run.

Question 17

When preparing GPU nodes for a Nutanix Enterprise AI deployment within a GKE environment, how should an administrator treat the installation of the NVIDIA drivers?

Options:

A.

Enable open-source driver.

B.

Install specific version of NVIDIA drivers.

C.

Install latest version of NVIDIA drivers.

D.

Skip installing the GPU driver.

Question 18

An administrator is integrating an application with an endpoint and finds that the application is experiencing high latency.

What action should the administrator take to ensure the lowest latency when creating endpoints?

Options:

A.

Reduce the payload size limit.

B.

Increase the timeout value on the endpoints.

C.

Increase the cache expiration time.

D.

Increase the number of endpoint instances.

Question 19

An administrator attempts to import a pre-trained model into Nutanix Enterprise AI (NAI), but the model fails to appear in the deployment list, and endpoint creation is unavailable.

Which action should the administrator take to troubleshoot the issue?

Options:

A.

Verify that the model format and metadata meet NAI requirements.

B.

Assign a public IP address to the model container for visibility.

C.

Modify the API key to allow administrative access to all endpoints.

D.

Restart the AI cluster to refresh the model registry and endpoint manager.

Question 20

Nutanix AI officially supports which two LLM packaging formats? (Choose two.)

Options:

A.

NVIDIA NIM

B.

ONNX

C.

OLLAMA

D.

Hugging Face

Question 21

What is the correct endpoint PATH that is displayed in the NAI Dashboard?

Options:

A.

/api/v2/chat/completions

B.

/api/v1/chat/completions

C.

/api/v1/chat/endpoints

D.

/api/chat

Question 22

In a new instance of Nutanix Enterprise AI, what task must be completed to create an API key?

Options:

A.

Download LLM and create endpoint.

B.

Provision an API key in NKP.

C.

Provision a GPU worker node.

D.

Create an endpoint first.

Demo: 22 questions
Total 75 questions