Skip to main content
NetApp Console local deployment

Connect your LLM and enable the NetApp Console assistant in NetApp Console local deployment

Contributors netapp-tonias netapp-ml94669
PDFs

Connect your large language model (LLM) to NetApp Console local deployment to enable the Console assistant and AI-assisted storage management.

Note This documentation regarding connecting an LLM to the Console assistant to enable AI features is provided as a technology preview. With this preview offering, NetApp reserves the right to modify offering details, contents, and timeline before General Availability.
Required access roles

Super admin or Organization admin. Learn about access roles.

After setup, users open the Console assistant from the dashboard and choose an access mode:

  • In Read only mode, the assistant answers questions and provides guidance without making changes.

  • In Read/write mode, the assistant can act on storage infrastructure. It shows details for review and confirmation before each change. For asynchronous operations, such as volume creation, it creates a job that users can check from the assistant.

To connect your LLM, select a provider path, enter endpoint details and API key, and then select a model in Administration > AI Tools. Assistant actions stay within your storage policies and role-based access controls.

Gather what you need before you connect an LLM

Before you connect your LLM, gather the following:

  • Your provider type decision: OpenAI or OpenAI-compatible. Learn about provider choices.

  • A valid API key for the provider path you select.

  • The endpoint URL for your provider path.

  • Your proxy or gateway URL, if your organization requires one.

  • Your user name or single sign-on (SSO) ID for the LLM provider account, if required.

  • Network access from Console local deployment to the selected endpoint.

  • Storage classes and role-based access controls for the assistant actions you plan to allow.

For supported model details, see Learn about supported LLM providers and models in NetApp Console local deployment.

Connect an LLM to NetApp Console local deployment

Enter provider settings, API key, and model to connect your LLM to Console local deployment.

Steps

  1. Log in to the NetApp Console local deployment.

  2. Select Administration > AI Tools.

  3. Select the menu, and then select Edit.

  4. In Provider type, select a provider type.

    Learn about LLM integration in NetApp Console local deployment.

  5. If prompted for a provider endpoint, enter the endpoint URL for the provider path you selected.

  6. Enter the proxy or gateway URL and credentials.

  7. In the User name field, enter your user name or SSO ID if your provider path requires it.

  8. In the API key field, paste the API key from your selected provider path.

  9. Select a model from the list.

  10. Review the configuration, and then select Save.

    If save or test fails, verify the provider type, endpoint URL, API key, and selected model, and then try again.

Troubleshoot your LLM integration.

Verify that LLM integration works

After you save the configuration, verify assistant availability and behavior.

Steps

  1. Confirm that the Console assistant button appears on the NetApp Console local deployment dashboard.

  2. Open the assistant in Read only mode and run a basic query.

  3. Open the assistant in Read/write mode and confirm that storage-changing actions require user confirmation before execution.

  4. Verify that the users who need action workflows have the required role-based access controls.

After you complete validation, users can open the Console assistant from the dashboard and describe tasks in plain language. For usage examples and end-user workflows, see Use the NetApp Console assistant.

Protect credentials and monitor LLM usage

  • Use a dedicated API key for Console local deployment integration when possible.

  • Rotate API keys according to your organization policy.

  • Restrict who can edit AI Tools settings to required admin roles only.

  • Monitor provider-side API usage and alerts to track abnormal activity or cost spikes.