Integrate AI services

AI service basics

PREREQUISITES: Integration with Azure OpenAI Service requires Sitefinity CMS 15.0.8229 or later. The integration does not work with previous versions of Sitefinity CMS 15.0.

Sitefinity CMS offers integration with AI service provided by Microsoft Azure. This is the Azure OpenAI service, which requires a Microsoft Azure account. The service allows content creators to use Microsoft’s Azure OpenAI services in content blocks to:

  • Compose new text (MVC and .NET)
  • Summarize text (MVC and .NET)
  • Improve writing (MVC and .NET)
  • Personalize text (.NET only)

For more information, see Generate AI content.

PREREQUISITES: Subscription to Microsoft Azure OpenAI is required. The service is made available by Microsoft Azure OpenAI under Microsoft Azure OpenAI’s terms of service, and Progress does not have control over such terms, the service and its availability.

Integration

To integrate AI services with your Sitefinity CMS project, you need to first install the AI services NuGet package Progress.Sitefinity.AIServiceConnector. You can have only one client per Sitefinity CMS instance.

  1. In Sitefinity CMS backend, navigate to Administration » Modules & Services.
  2. Install the AI services module.
  3. Navigate to Administration » Settings » AI services.
  4. In the API Key field, enter your API key from the Azure portal.
  5. In the Endpoint field, enter the Endpoint from the Azure portal.
  6. In the Deployment name field, add the deployment name from the Azure portal. For more information, see Deploy a model.
  7. In the API version field, enter the API version of the Azure OpenAI service. For more information, see Azure OpenAI Service REST API reference.
  8. Select whether to send Sitefinity CMS user ID to the AI service.
    Enabling this option helps to track and analyze user interactions and activities and detect abusive behavior within the service.
  9. Click Save changes.
IMPORTANT: For projects that upgrade to Sitefinity CMS 15.0, backend iterface settings must be updated:
  1. Navigate to Administration » Settings » Backend interface.
  2. Expand Rich text editor section.
  3. Add "aiAssist" after "html". For more information, see Backend interface settings.
  4. Save changes.

Configuration

The configuration of the AI services happens in the advanced settings. There you can define a prompt for each action and parameters for each prompt that are filled out by content editor to give you a specific prompt to use for content generation. For more information on prompts, see Microsoft Azure’s documentation on Design prompts.

NOTE: The generated text depends on the prompts. Providing similar or identical prompts might result or similar or identical text generation for multiple users.

  1. Navigate to Administration » Settings » Advanced settings » AIservices.
  2. Expand your service client.
  3. Expand Parameters to configure the basic settings parameters here or add new one.
  4. Expand Actions to modify the actions available in the rich-text editor. For each action, you can modify their parameters and:
    • the title of the action visible in the UI.
    • the icon of the action.
    • the prompt sent to the AI service.
  5. Save your changes.

Increase your Sitefinity skills by signing up for our free trainings. Get Sitefinity-certified at Progress Education Community to boost your credentials.

Get started with Integration Hub | Sitefinity Cloud | Sitefinity SaaS

This free lesson teaches administrators, marketers, and other business professionals how to use the Integration hub service to create automated workflows between Sitefinity and other business systems.

Web Security for Sitefinity Administrators

This free lesson teaches administrators the basics about protecting yor Sitefinity instance and its sites from external threats. Configure HTTPS, SSL, allow lists for trusted sites, and cookie security, among others.

Foundations of Sitefinity ASP.NET Core Development

The free on-demand video course teaches developers how to use Sitefinity .NET Core and leverage its decoupled architecture and new way of coding against the platform.

Was this article helpful?