Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.dojah.io/llms.txt

Use this file to discover all available pages before exploring further.

The Generic OCR Service allows you to extract structured text and field-level data from virtually any type of document, even if it’s not a standard ID or form. This is useful when working with files like utility bills, handwritten documents, bank statements, or any scanned paper that contains useful data. Whether it’s text-heavy, printed, or partially handwritten, the OCR engine reads and returns usable data in a clean, structured format.

​
What It Does

  • Accepts document uploads (images or PDFs)
  • Uses Optical Character Recognition (OCR) to extract readable content
  • Returns both raw text and structured key-value data
  • Supports multiple languages and document layouts
You can upload anything, from a filled-out physical form to a scanned multi-page document, and receive both unstructured and parsed outputs.

​
Common Use Cases

Use the Generic OCR Service when you need to:
  • Parse bank statements, utility bills, invoices, or receipts
  • Digitize handwritten or scanned documents
  • Extract details from KYC documents that are not government-issued
  • Pre-process form submissions for backend automation
This tool is especially helpful in onboarding, document analysis, or compliance workflows that require supplementary documents beyond standard IDs.

​
When to Use It

  • When you don’t need identity verification but still want to read and use document data
  • When your verification flow includes uploads like proof of address, income, or tax records
  • When you’re processing documents submitted outside of EasyOnboard and need a flexible reader
  • As a fallback when standard document verification does not support a specific file format or region

​
Integration Option

API Lookup

You can access the Generic OCR Service via a simple POST request with a file payload. It returns parsed data and metadata in real time.