Analyzing with the API

You can use the Vision API to analyze images and documents individually or images in batch.

To get started with the REST API, see the Vision API Postman Collection. For information on how to use the Postman Collection, see Access OCI Vision with REST APIs lab in the Data Science and AI services examples on Github.

For information about using the API and signing requests, see REST APIs and Security Credentials. For information about SDKs, see Software Development Kits and Command Line Interface. For information on file limts, see Limits. If your use case requires a bigger size, or number, of requests than the limit, then contact us with a support ticket so we can understand your requirement.

The AnalyzeDocument and DocumentJob capabilities in Vision are moving to a new service, Document Understanding. The following features are impacted:
  • Table detection
  • Document classification
  • Receipt key-value extraction
  • Document OCR
These features are available in Vision until January 1, 2024. After then, they are available only in Document Understanding.
APIs to Analyze Images with Pretrained or Custom Models:
APIs to Analyze Documents with Pretrained or Custom Models: