document-understanding
latest
false
Document Understanding API guide
- Getting Started
- Examples Using the Document Understanding™ Cloud API v1
- Licensing
- Troubleshooting
Run the generative extractor via the Document Understanding API using a project ID and a sample curl POST request.
Start extracting fields from a document using generative extractor
Tip:
The Project ID is obtained from the response received from the Get project information call.
curl -X 'POST' \
'{AutomationCloudURL}/<Organization_Name>/<Tenant_Name>/du_/api/framework/projects/<Project_ID>/extractors/generative_extractor/extraction?api-version=1' \
-H 'accept: text/plain' \
-H 'Authorization: Bearer <your-access-token>' \
-H 'Content-Type: application/json' \
-d '{
"documentId": "fa83da2a-1498-ee11-8925-000d3a67a01e",
"prompts": [
{
"id": "Invoice Number",
"question": "Extract the invoice number from the provided document."
},
{
"id": "Date",
"question": "What is the invoice date mentioned in the document?"
},
{
"id": "Total",
"question": "Extract the total amount from the invoice."
}
]
}'
curl -X 'POST' \
'{AutomationCloudURL}/<Organization_Name>/<Tenant_Name>/du_/api/framework/projects/<Project_ID>/extractors/generative_extractor/extraction?api-version=1' \
-H 'accept: text/plain' \
-H 'Authorization: Bearer <your-access-token>' \
-H 'Content-Type: application/json' \
-d '{
"documentId": "fa83da2a-1498-ee11-8925-000d3a67a01e",
"prompts": [
{
"id": "Invoice Number",
"question": "Extract the invoice number from the provided document."
},
{
"id": "Date",
"question": "What is the invoice date mentioned in the document?"
},
{
"id": "Total",
"question": "Extract the total amount from the invoice."
}
]
}'
Response of extracting fields from a document using generative extractor
{
"extractionResult": {
"DocumentId": "fa83da2a-1498-ee11-8925-000d3a67a01e",
"ResultsVersion": 0,
"ResultsDocument": {
"Bounds": {
"StartPage": 0,
"PageCount": 1,
"TextStartIndex": 0,
"TextLength": 864
},
"Language": "eng",
"DocumentGroup": "",
"DocumentCategory": "",
"DocumentTypeId": "Unknown",
"DocumentTypeName": "Unknown",
"DocumentTypeDataVersion": 0,
"DataVersion": 0,
"DocumentTypeSource": "Automatic",
"DocumentTypeField": {
"Components": [],
"Value": "Unknown",
"UnformattedValue": "",
"Reference": {
"TextStartIndex": 0,
"TextLength": 0,
"Tokens": []
},
"DerivedFields": [],
"Confidence": 1.0,
"OperatorConfirmed": false,
"OcrConfidence": -1.0,
"TextType": "Unknown"
},
"Fields": [
{
"FieldId": "Invoice Number",
"FieldName": "Invoice Number",
"FieldType": "Text",
"IsMissing": false,
"DataSource": "Automatic",
"Values": [
{
"Components": [],
"Value": "INV-3337",
"UnformattedValue": "",
"Reference": {
"TextStartIndex": 69,
"TextLength": 8,
"Tokens": [
{
"TextStartIndex": 69,
"TextLength": 8,
"Page": 0,
"PageWidth": 595.0,
"PageHeight": 841.0,
"Boxes": [
[
115.73,
451.94,
37.17,
14.11
]
]
}
]
},
"DerivedFields": [],
"Confidence": 0.0,
"OperatorConfirmed": false,
"OcrConfidence": 1.0,
"TextType": "Unknown"
}
],
"DataVersion": 0,
"OperatorConfirmed": false
},
{
"FieldId": "Date",
"FieldName": "Date",
"FieldType": "Text",
"IsMissing": false,
"DataSource": "Automatic",
"Values": [
{
"Components": [],
"Value": "January 25, 2016",
"UnformattedValue": "",
"Reference": {
"TextStartIndex": 191,
"TextLength": 16,
"Tokens": [
{
"TextStartIndex": 191,
"TextLength": 16,
"Page": 0,
"PageWidth": 595.0,
"PageHeight": 841.0,
"Boxes": [
[
147.35,
451.94,
31.3,
14.11
],
[
147.35,
485.68,
12.23,
14.11
],
[
147.35,
500.36,
19.57,
14.11
]
]
}
]
},
"DerivedFields": [],
"Confidence": 0.0,
"OperatorConfirmed": false,
"OcrConfidence": 1.0,
"TextType": "Unknown"
}
],
"DataVersion": 0,
"OperatorConfirmed": false
},
{
"FieldId": "Total",
"FieldName": "Total",
"FieldType": "Text",
"IsMissing": false,
"DataSource": "Automatic",
"Values": [
{
"Components": [],
"Value": "$93.50",
"UnformattedValue": "",
"Reference": {
"TextStartIndex": 374,
"TextLength": 6,
"Tokens": [
{
"TextStartIndex": 374,
"TextLength": 6,
"Page": 0,
"PageWidth": 595.0,
"PageHeight": 841.0,
"Boxes": [
[
178.76,
451.94,
26.91,
14.43
]
]
}
]
},
"DerivedFields": [],
"Confidence": 0.0,
"OperatorConfirmed": false,
"OcrConfidence": 1.0,
"TextType": "Unknown"
}
],
"DataVersion": 0,
"OperatorConfirmed": false
}
],
"Tables": []
},
"ExtractorPayloads": null,
"BusinessRulesResults": null
}
}
{
"extractionResult": {
"DocumentId": "fa83da2a-1498-ee11-8925-000d3a67a01e",
"ResultsVersion": 0,
"ResultsDocument": {
"Bounds": {
"StartPage": 0,
"PageCount": 1,
"TextStartIndex": 0,
"TextLength": 864
},
"Language": "eng",
"DocumentGroup": "",
"DocumentCategory": "",
"DocumentTypeId": "Unknown",
"DocumentTypeName": "Unknown",
"DocumentTypeDataVersion": 0,
"DataVersion": 0,
"DocumentTypeSource": "Automatic",
"DocumentTypeField": {
"Components": [],
"Value": "Unknown",
"UnformattedValue": "",
"Reference": {
"TextStartIndex": 0,
"TextLength": 0,
"Tokens": []
},
"DerivedFields": [],
"Confidence": 1.0,
"OperatorConfirmed": false,
"OcrConfidence": -1.0,
"TextType": "Unknown"
},
"Fields": [
{
"FieldId": "Invoice Number",
"FieldName": "Invoice Number",
"FieldType": "Text",
"IsMissing": false,
"DataSource": "Automatic",
"Values": [
{
"Components": [],
"Value": "INV-3337",
"UnformattedValue": "",
"Reference": {
"TextStartIndex": 69,
"TextLength": 8,
"Tokens": [
{
"TextStartIndex": 69,
"TextLength": 8,
"Page": 0,
"PageWidth": 595.0,
"PageHeight": 841.0,
"Boxes": [
[
115.73,
451.94,
37.17,
14.11
]
]
}
]
},
"DerivedFields": [],
"Confidence": 0.0,
"OperatorConfirmed": false,
"OcrConfidence": 1.0,
"TextType": "Unknown"
}
],
"DataVersion": 0,
"OperatorConfirmed": false
},
{
"FieldId": "Date",
"FieldName": "Date",
"FieldType": "Text",
"IsMissing": false,
"DataSource": "Automatic",
"Values": [
{
"Components": [],
"Value": "January 25, 2016",
"UnformattedValue": "",
"Reference": {
"TextStartIndex": 191,
"TextLength": 16,
"Tokens": [
{
"TextStartIndex": 191,
"TextLength": 16,
"Page": 0,
"PageWidth": 595.0,
"PageHeight": 841.0,
"Boxes": [
[
147.35,
451.94,
31.3,
14.11
],
[
147.35,
485.68,
12.23,
14.11
],
[
147.35,
500.36,
19.57,
14.11
]
]
}
]
},
"DerivedFields": [],
"Confidence": 0.0,
"OperatorConfirmed": false,
"OcrConfidence": 1.0,
"TextType": "Unknown"
}
],
"DataVersion": 0,
"OperatorConfirmed": false
},
{
"FieldId": "Total",
"FieldName": "Total",
"FieldType": "Text",
"IsMissing": false,
"DataSource": "Automatic",
"Values": [
{
"Components": [],
"Value": "$93.50",
"UnformattedValue": "",
"Reference": {
"TextStartIndex": 374,
"TextLength": 6,
"Tokens": [
{
"TextStartIndex": 374,
"TextLength": 6,
"Page": 0,
"PageWidth": 595.0,
"PageHeight": 841.0,
"Boxes": [
[
178.76,
451.94,
26.91,
14.43
]
]
}
]
},
"DerivedFields": [],
"Confidence": 0.0,
"OperatorConfirmed": false,
"OcrConfidence": 1.0,
"TextType": "Unknown"
}
],
"DataVersion": 0,
"OperatorConfirmed": false
}
],
"Tables": []
},
"ExtractorPayloads": null,
"BusinessRulesResults": null
}
}