VisualIntelligence lets your app surface relevant content from the Visual Intelligence scene through App Intents. You describe what the user is looking at by working with the captured pixel buffer, passing it through a SemanticContentDescriptor so the system can match it against content your app provides. The framework is available on iOS, macOS, and visionOS.
Describing Visual Content 1
Represent the content of the Visual Intelligence scene so the system can match it against content your app provides.
- StSemanticContentDescriptoriOS 26.0+A structure that describes the content of the Visual Intelligence scene using its captured pixel buffer for App Intents matching.