Sample processor output

This page contains detailed information on output produced by processors offered by Document AI.

The files on this page are sample documents in a variety of structures and the raw outputs from the Document AI API in the Document format.

The fields returned in the response can be limited by using a FieldMask when making a processing request.

Digitize text

Processors Output samples

Enterprise Document OCR (Optical Character Recognition)

Category Digitize
Solution type General
Functions OCR, Quality Analysis
Release stage General availability
Access status Public
Full processor details Detailed entry
Sample input file
pretrained-ocr-v1.2-2022-11-10
Output Document JSON
pretrained-ocr-v2.0-2023-06-02
Output Document JSON
Checkbox Extraction - Document JSON
Font Detection - Document JSON
Math OCR - Document JSON
pretrained-ocr-v2.1-2024-08-07
Output Document JSON