customize

Guide Azure OpenAI model deployment with version, SKU, capacity, and RAI policy configuration.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill provides an interactive guided workflow to deploy Azure OpenAI models with full customization. It enables precise selection of model version, deployment SKU, capacity, content filtering (RAI policy), and advanced options such as dynamic quota, priority processing, and spillover, eliminating the need for manual scripting and scattered configuration.

Core Features & Use Cases

  • Guided deployment flow: step-by-step configuration of model, version, SKU, capacity, and policy.
  • Advanced controls: enable dynamic quota, priority processing (PTU deployments), and spillover to backup deployments.
  • Cross-region and MaaS support: handle region capacity and non-OpenAI models with appropriate deployment paths.
  • Real-world scenario: precisely deploy an Azure OpenAI model with tailored policy for enterprise workloads.

Quick Start

Start the guided deployment to configure version, SKU, capacity, RAI policy, and advanced options for an Azure OpenAI model.

Frequently Asked Questions about customize

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

FAQPage Schema
How do I deploy Azure OpenAI models with custom SKU and capacity settings?

To deploy Azure OpenAI models with custom SKU and capacity settings, use a guided deployment workflow that prompts you for model version, SKU type like GlobalStandard or ProvisionedManaged, and capacity planning inputs. It configures the deployment without manual scripting.

Can I configure RAI policy and content filtering during an Azure OpenAI deployment?

Yes, you can configure RAI policy and content filtering during an Azure OpenAI deployment by specifying your desired policy inputs in the guided workflow. This ensures the deployed model adheres to enterprise content safety requirements.

Does Azure OpenAI deployment support PTU and dynamic quota for enterprise workloads?

Azure OpenAI deployment supports PTU priority processing and dynamic quota for enterprise workloads through advanced configuration options. The guided workflow enables these features to handle capacity allocation across regions.

What is region spillover and how does it work for Azure OpenAI model deployments?

Region spillover for Azure OpenAI model deployments redirects traffic to backup deployments when primary region capacity is exhausted. It is an advanced option configurable during the guided deployment workflow.

Do I need Azure CLI to deploy Azure OpenAI models with advanced customization?

Yes, you need Azure CLI installed and proper authentication configured to deploy Azure OpenAI models with advanced customization. The guided deployment workflow requires these to execute the configured model, region, and policy settings.