AzureOpenAI – Create

Azure OpenAI is a Microsoft Azure service providing access to OpenAI models and tooling for building intelligent applications (NLP, computer vision, deep learning). QualiWare AI uses this service for its conversational and retrieval features.

Required Azure Role

Either one of these built-in roles (or a custom role with equivalent permissions):

  • Owner — full access including role assignments
  • Contributor — manage resources (no role assignments)

If role assignment is needed with Contributor, also grant User Access Administrator.

Azure Administration Tools / Interface

This guide uses the Azure Portal and a manual creation process.

Create and Manage Steps (Azure Portal)

  1. Go to Azure OpenAI and click Create.
  1. After clicking Next, proceed to the Networking section.Networking requirements must comply with the organization’s Azure cloud security policies. The configuration should ensure that the service is accessible to both QualiWare and the Azure App Service hosting the QualiWare Bot application.It is recommended to either:
    • Integrate with a Virtual Network (VNet), or
    • Restrict access to known sources by whitelisting IP addresses.

    Please note: If the Azure AI Search indexer uses an authentication method such as System-assigned or Managed Identity, and source IP restrictions are in place, performance may be slower during indexing, especially during the initial run.

     

  1. Tags are optional. Proceed to Review + create and then Create to provision the service.

Deployment Model

AI Model Requirements for QualiWare AIAgent and QualiChat

  • The following AI models are required to support the functionality of QualiWare AIAgent and QualiChat:
    • GPT-4o / GPT-5 – for conversational capabilities
    • text-embedding-ada-002 – for data indexing and semantic search

    Please note that while both QualiWare AIAgent and QualiChat support GPT-5 for advanced chat capabilities, users may experience slower response times due to the model’s deep reasoning and complex processing.

    Recommended Usage:

    1. GPT-4o
      • Optimized for faster responses
      • Suitable for scenarios where speed is prioritized over depth
    2. GPT-5*
      • Provides detailed explanations and deep reasoning
      • Ideal for use cases requiring high-quality, thoughtful responses

Deploy Models (Azure AI Foundry)

  1. Open the Azure AI Foundry portal and go to Deployments. (You can find the portal link from the Azure OpenAI service home page.)
  1. Click Deploy model and choose to deploy a Base model. Search for the models listed above and confirm deployment.