how use intelligent api to inject ocr

To use intelligent APIs to inject OCR (Optical Character Recognition) capabilities into your app, you can leverage the Vision framework provided by Apple. The Vision framework offers a range of capabilities for visual intelligence, including text extraction from images. Here's a brief overview of how you can integrate OCR using the Vision framework:

1. Recognize Text Request: Use the RecognizeTextRequest to detect and extract lines of text from an image. This is useful for documents with a structured format, such as tables and lists.

2. Recognize Documents Request: This new API can extract structural elements and important information from documents, such as tables, lists, and machine-readable codes like QR codes. It can also identify important information like email addresses, phone numbers, or URLs.

3. Swift Enhancements: The Vision framework has introduced a new Swift API, which simplifies the integration of these capabilities into your apps. The new API uses async/await syntax for better performance and ease of use.

For a more detailed guide on using the Vision framework for OCR, you can refer to the session Read documents using the Vision framework (00:01:22) from WWDC 2025. This session provides insights into how to use the Vision framework to read and understand documents effectively.