Activities related to the DocumentAI capabilities in Google Cloud Platform.
Extracts data from documents using processors defined in Google Document AI. Supported file formats: PDF, JPG, JPEG, GIF, PNG. The number of pages allowed per document depends upon the processor.
| Technical Name |
Type |
Minimal Agent Version |
| extractUsingProcessor |
asynchronous
|
WIN-2.0.0
|
Input Parameters:
| Name |
Type |
Attributes |
Default |
Description |
| filePath |
string |
mandatory
|
|
Full path of the existing file. Supported file formats: PDF, JPG, JPEG, GIF, PNG. |
| predictionEndpoint |
string |
mandatory
|
|
Prediction endpoint for the processor created in Google Cloud Platform. Valid endpoint format: https://{LOCATION}-documentai.googleapis.com/{API_VERSION}/projects/{PROJECT_ID}/locations/{LOCATION}/processors/{PROCESSOR_ID} |
Output Parameters:
| Name |
Type |
Description |
| extractedJson |
any |
Extracted result in JSON format. |
Errors:
| Error Class |
Package |
Description |
| InvalidArgument |
irpa_core |
Invalid arguments |
| GoogleDocumentAiAuthError |
irpa_googledocumentai |
Missing or Invalid authorization error |
