User Guide

Concepts and usage instructions for AI applications, inference, templates, model libraries, and images.

Reading Guide

• For deployment, see Quick Start.
• For GPU deployment, see NVIDIA/CUDA.
• Read in this order: AI Applications (including Application Templates) → AI Inference (including Inference Templates / AI Model Library) → AI Images.

Console Menu and Feature Overview

After entering Artificial Intelligence, the menu is divided into Applications, Inference, and Images:

• Applications: Application instances (Dify/OpenClaw/ComfyUI), application templates.
• Inference: Inference instances (Ollama), inference templates, inference model library.
• Images: Managed under "Artificial Intelligence" → "Images"; selected when creating templates.

Terminology

• Template: Resource configuration such as CPU/memory/GPU required to run an instance.
• Model Library: Reusable model resources for use by inference applications.
• Image: Container image for the instance runtime environment, determining functionality and version.

Typical Relationship

Instance = Image + Spec + (optional) Model.

🗃️ AI Applications

4 items

🗃️ AI Inference

3 items

📄️ AI Images

Container images for running AI applications. Managed in the console under Artificial Intelligence → Images; selected when creating templates. The LLM type must match the template.