TechnologiesMachine Learning & AI

_Vision_FoundationModels cross-import overlay

iOSmacOStvOSwatchOSvisionOS

_Vision_FoundationModels is a cross-import overlay that bridges Vision with FoundationModels, surfacing image-analysis capabilities as tools a language model can call. Use BarcodeReaderTool to decode barcodes and OCRTool to recognize text from images within a model's reasoning, letting your language model interpret visual content as part of its responses. The overlay activates automatically when you import both Vision and FoundationModels.

Image-Analysis Tools 2

Vision-backed tools a language model can call to interpret visual content during its reasoning.

  • St
    BarcodeReaderTool
    A tool that scans machine-readable codes in an image.
  • St
    OCRTool
    A tool that recognizes text in an image.
← Machine Learning & AI