Introduction

Scope

This user guide describes how to use NeuReality SDK for operating the NR1™ AI Inference Appliance.

The documentation covers the following aspects of NR1 AI Inference Appliance operation:

1. AI Server for general operation, monitoring and observability.

2. Deployment API for optimizing and deploying AI pipelines on NR1™ AI-CPU processing units in NR1 AI Inference Appliance.

3. Management API for service provisioning, querying service info and health, and server configuration and health.

4. Serving API and producing serving requests.

5. Service orchestration with Kubernetes

Documentation related to NR1 AI Inference Appliance setup and maintenance may be found in documentation library of NeuReality Developer Portal.

The following tutorials are included:

1. Deployment API (Toolchain)

2. Serving API (Client-side runtime)

3. Management API

4. Orchestration with Kubernetes

Audience

This document is intended for users of NeuReality SDK - data scientists, AI, MLOps and DevOps engineers who are interested in deployment of AI applications with NR1 AI Inference Appliance.