Actions a_ocr_extract

Extract Text (OCR)

Extracts text from a PDF or image via Azure Document Intelligence.

What does it do?

Reads and extracts text written inside an image or scanned document.

Receives an image file, detects the characters using Optical Character Recognition (OCR) and returns the plain text.

Essential if you ask customers to send photos of their ID, invoices or bank transfer receipts.

name	type
`file_url`	string

Fixed branches

file_url_field string required default: "file_url"

mode "read" | "layout" | "tables" required default: "read"

output_field string required default: "extracted_text"

memory_key string optional

{
  "file_url_field": "file_url",
  "mode": "read",
  "output_field": "extracted_text"
}