Set of activities related to the VisionAI capabilities in Google Cloud Platform.
Extracts data from documents using Google Vision AI capabilities. Supports all major file formats like pdf, jpg, jpeg, png, tiff and gif. Please note that if a document contains more than 5 pages, only the first 5 pages will be extracted.
| Technical Name |
Type |
Minimal Agent Version |
| extractUsingOcr |
asynchronous
|
WIN-2.0.0
|
Input Parameters:
| Name |
Type |
Attributes |
Default |
Description |
| filePath |
string |
mandatory
|
|
Full path of the existing file. Supports all major file formats like pdf, jpg, jpeg, png, tiff and gif. |
Errors:
| Error Class |
Package |
Description |
| InvalidArgument |
irpa_core |
Invalid arguments |
| GoogleVisionAiAuthError |
irpa_googlevisionai |
Missing or Invalid authorization error |
