deploy-model

Route Azure OpenAI deployment requests to preset, customize, or capacity modes.

Updated Oct 22, 2024
One-click install
npx skills add https://github.com/DigiBanks99/dotfiles --skill deploy-model-digibanks99
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deploy-model
Source: https://github.com/DigiBanks99/dotfiles/tree/main/modules/agents/.config/.agents/skills/microsoft-foundry/models/deploy-model
Command: npx skills add https://github.com/DigiBanks99/dotfiles --skill deploy-model-digibanks99

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Unified and deterministic deployment of Azure OpenAI models by routing requests to the correct deployment path (preset, customize, or capacity discovery), reducing manual steps and errors.

Core Features & Use Cases

  • Unified entry point for Azure OpenAI model deployments, enabling quick path selection or full customization.
  • Supports capacity discovery, project/region resolution, and SKU selection across multiple regions and accounts.
  • Routes to preset for fast deployments or to customize for version/SKU/capacity/RAI policy, with cross-region fallbacks when needed.

Quick Start

Prompt the skill with a model name and your desired deployment mode (preset, customize, or capacity) to begin the deployment workflow.

Frequently Asked Questions about deploy-model

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate Azure OpenAI model deployment across multiple regions?

Azure OpenAI deployment routing analyzes user intent to direct requests to preset, customize, or capacity modes. It resolves projects, validates quotas, and orchestrates deployment across SKUs for efficient model provisioning.

What is the difference between preset, customize, and capacity modes for Azure OpenAI provisioning?

Preset mode enables fast deployments, customize allows full control over version, SKU, capacity, and RAI policy, and capacity mode focuses on discovery. The router analyzes your intent to select the appropriate path, including cross-region fallbacks when needed.

Can I provision Anthropic models through the Azure OpenAI deployment router?

Yes, the Azure OpenAI deployment router supports Anthropic provisioning. When required by the customized deployment flow, it orchestrates the necessary REST API calls to provision Anthropic models alongside standard Azure OpenAI SKUs.

Does the Azure OpenAI deployment router enforce authentication and pre-deployment validation?

Yes, Azure OpenAI deployment routing enforces authentication and performs pre-deployment validations. It checks capacity, resolves target regions, and validates quotas before handing off to the preset or customize deployment flows for execution.

How do I check Azure OpenAI capacity and quotas before deploying a model?

Checking Azure OpenAI capacity and quotas is handled by the capacity discovery mode. The router analyzes your deployment intent, resolves the target region, and verifies available SKU capacity across accounts before initiating the provisioning workflow.