Skip to main content
NetApp Console local deployment

Learn about LLM integration in NetApp Console local deployment

Contributors netapp-tonias netapp-ml94669
PDFs

NetApp Console local deployment connects to a large language model (LLM) for AI-assisted storage management. After setup, users can use natural language for storage guidance, analytics, provisioning, and supported operations.

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.

AI-assisted management lets users describe requests in plain language while Console local deployment applies your storage policies.

Console local deployment sends LLM requests only to the endpoint you configure.

What you can do with AI-assisted storage management

When you enable LLM integration, Console local deployment provides these capabilities through the Console assistant:

  • Storage provisioning Describe workload requirements in plain language. Console local deployment recommends and runs a provisioning plan based on your storage classes.

  • Metrics and analytics Ask questions about storage capacity, performance, and other supported metrics in your current fleet state. This capability is read-only.

  • Alert response Ask Console local deployment to investigate an active alert. It analyzes the issue and suggests or runs a supported action based on assigned permissions.

  • ONTAP management Ask the assistant to view or perform supported management operations on registered ONTAP systems. Write operations require review and confirmation.

  • Search and guidance Ask questions about your storage environment or ONTAP administration. Console local deployment returns contextual answers from documentation and current fleet state.

Choose read-only or read/write access for the Console assistant

Users choose an assistant access mode based on the outcome they want:

  • Read only mode for guidance and investigation without making infrastructure changes.

  • Read/write mode for guided execution. Console local deployment shows the proposed action, requests confirmation, and then runs the change.

Understand what controls Console assistant actions

Console local deployment controls Console assistant actions through the same governance model used across the platform:

  • Role-based access controls limit what each user can see and do.

  • Storage policies constrain provisioning and related actions.

  • The assistant uses the scope of the signed-in user when it accesses fleets, systems, and storage resources.

  • The Console assistant requires confirmation before it runs storage-changing actions.

Choose an LLM provider path

NetApp Console local deployment supports these LLM provider types:

  • OpenAI for direct OpenAI model access.

  • OpenAI-compatible for a compatible endpoint, such as an enterprise gateway or proxy service.

  • Anthropic for Anthropic's Claude models.

Model availability depends on the endpoint you configure. Select a model from the list in Console local deployment.

Learn about supported LLM providers and models in NetApp Console local deployment.

Protect LLM credentials and control admin access

Protect the integration with these controls:

  • Treat the API key as a privileged credential and rotate it according to your organization policy.

  • Review provider-side usage and alerts to detect unexpected activity.

Control Console assistant costs by choosing an appropriate LLM provider and model, setting usage limits and alerts with your provider, and monitoring token usage. Only activities that send requests to the LLM consume provider tokens; backend operations do not.

Connect your LLM

After you make these decisions, connect your LLM to enable the NetApp Console assistant.