Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

When verifying the installation of Nutanix Enterprise AI (NAI) via the kubectl get pods -n nai-system command, the READY column indicates the number of containers in the pod that are currently running and healthy compared to the total number of containers defined for that pod.

Meaning of 2/2: Critical system pods in the NAI architecture (such as monitoring components like prometheus-nai or pods equipped with service mesh/proxy sidecars) are often configured with multiple containers—typically the main application container and a sidecar (e.g., for metrics collection, logging, or traffic management).

Health Indication: A value of 2/2 confirms that both the primary container and its essential sidecar are fully up and running. This state indicates the pod is completely healthy and operating with its full high-availability or monitoring capabilities enabled. A value of 1/2 would indicate a degraded state where one container has failed, and 1/1 applies to single-container pods, but 2/2 is the specific indicator for multi-container system pods being fully operational.

Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

To onboard a custom or "unvalidated" model directly from Hugging Face into the Nutanix Enterprise AI dashboard, administrators utilize the Import Model workflow.

Workflow: In the "Import Model" wizard, there is a specific option to import from Hugging Face . 1 This requires the user to input the Repository ID (often referred to in generic UI options as the "URL" or path to the model, e.g., meta-llama/Llama-2-7b).

Why D is correct: This option allows the platform to pull the model weights and configuration files directly from the specified public repository.

Why others are incorrect:

Using CURL (A): NAI provides cURL code snippets to consume (make inference requests to) a running model, not to import it into the registry.

NGC Catalog (B): This is for NVIDIA-specific models, not general Hugging Face repositories.

Marketplace app (C): This typically refers to Nutanix Marketplace blueprints, not the specific action of importing a raw model weight set from Hugging Face.

Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

The Nutanix Enterprise AI (NAI) dashboard and API endpoints are exposed to the external network via an Ingress Gateway. In the NAI architecture on Kubernetes, Istio (specifically the Envoy Ingress Gateway service) is the component responsible for managing this ingress traffic.

If the NAI dashboard URL is inaccessible, it indicates a failure in the ingress layer where traffic is not being correctly routed to the nai-ui service. Troubleshooting steps for this issue involve checking the status of the Istio ingress gateway service (e.g., nai-ingress-gateway in the envoy-gateway-system or nai-system namespace) to ensure it is running and has successfully claimed an external IP address. While MetalLB provides the IP address, Istio handles the actual HTTP/S routing and termination; therefore, an inaccessibility issue is most directly linked to the Istio service configuration or health.

Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

Nutanix Enterprise AI enforces strict security protocols regarding API Key visibility.

One-Time View: The documentation warns users to "Store the key securely. You cannot view the key again after you close the API Key Details dialog box".

Recovery Policy: Because the keys are not stored in plain text or retrievable via the dashboard for security reasons, if a key is lost, it cannot be recovered or viewed. The mandatory administrative action is to generate a new API key for the endpoint and update any applications that were using the lost credential.

Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

To determine which versions of the nai-core Helm chart are available for installation from the repository, the administrator must use the helm search command. Specifically, the documentation states that after adding the Nutanix Helm repository, the command to search for the version of the nai-core helm chart available is helm search repo ntnx-charts/nai-core --versions.

helm get is used to retrieve information about a deployed release, not to search a repository.

helm pull is used to download the chart, not to list versions.

helm push is used to upload charts.

Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

The Nutanix Enterprise AI documentation provides distinct definitions for each import status state, which is crucial for troubleshooting.

Pending vs. Processing:

Processing: This status indicates that the system is actively downloading the LLM or NIM from the external repository (Hugging Face or NGC).

Pending: This status specifically indicates that "The system is waiting for the resources required to save the LLM." The documentation explicitly cites "if the required storage space is not available" as the primary example for why a model would remain in the Pending state.

Failed States: Options A (Read access) and B (Unauthorized token) would result in a Failed status, not Pending.

Conclusion: Since the status is "Pending" rather than "Processing," the issue is resource-related (storage), not the active download process.

Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

According to the Nutanix Enterprise AI documentation regarding "Viewing Sample API Code," the sample code provided by the dashboard is designed to help developers integrate the endpoint into their applications. The documentation explicitly states: "The sample code contains the URL and API key required to access the endpoint."

These two components are essential for the client application to locate the service (Endpoint URL) and authenticate the request (API Key). User credentials (such as username/password) are not part of the standard inference API request, and infrastructure details like GPU type are abstracted away from the client code.

Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

The Endpoint Details page in the Nutanix Enterprise AI dashboard contains specific widgets for monitoring the performance of a single inference service. 4

Number of Instances Widget: This specific widget displays the scaling configuration and resource consumption of the endpoint. It explicitly lists the Number of vCPUs and the Memory usage per instance that is actively in use to serve the endpoint. 5

Distinction: The "Infrastructure Summary" widget is located on the main Dashboard (not the Endpoint Details page) and displays cluster-wide resource usage, not the specific memory footprint of a single endpoint.

Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:

The Nutanix Enterprise AI Dashboard includes a specific widget designed to provide granular visibility into credential usage patterns. The API Keys (Top 5) widget displays a ranked list of the specific API keys that are driving the most traffic to the inference endpoints.

While the "API Requests Trends" widget shows the total volume of requests over time, the API Keys (Top 5) widget breaks this data down by credential, allowing the administrator to instantly identify which specific users or applications ("busiest credentials") are generating the highest load on the system.

**Comprehensive and Detailed Explanation From Exact Extract of Nutanix Artificial Intelligence documents knowledge without any external URL or links:**

To make a Large Language Model (LLM) available for deployment in Nutanix Enterprise AI, the administrator must use the **Models** section within the Nutanix Enterprise AI (NAI) dashboard. The correct workflow involves using the **Import Model** interface.

Within this interface, the administrator can choose to import a model directly from the **Hugging Face** model hub (by providing the repository name and optional token) or perform a **Manual Import** (Upload) for custom or air-gapped models. This action registers the LLM in the NAI repository, changing its status to "Ready," which is the prerequisite for deploying it as an inference endpoint. Options regarding Prism Central marketplace or third-party orchestration tools are incorrect for the specific task of ingesting the model *into* the NAI platform.