Yandex Cloud Vision OCR icon

Yandex Cloud Vision OCR

Recognize text in images using Yandex Cloud Vision OCR API

Actions3

Text Recognition → Recognize Async

AI-generated

Summary

Start asynchronous text recognition on binary image or PDF data using Yandex Cloud Vision OCR and receive an operation ID for later result retrieval.

Inputs

  • Binary Property (required) — The name of the binary property in the input containing the image or PDF data to recognize.
  • MIME Type — The MIME type of the input image or PDF; can be set to auto-detect to infer type automatically.
  • Languages — Languages to detect in the image, supporting multiple selections; defaults to Russian and English.
  • Model — The OCR model to apply for recognition, such as general text, handwritten, table, document templates, or license plates.

Output shape

a single item with JSON containing the asynchronous recognition operation ID, status 'RUNNING', requested MIME type, model, and languages

The node returns immediately with an operation ID and relevant parameters. The workflow author should use the 'Get Recognition Results' operation with the returned operation ID to poll for and retrieve the completed recognition results.

Links

Discussion