Generative extractor

Important:

This feature is currently part of an audit process and is not to be considered part of the FedRAMP Authorization until the review is finalized. See here the full list of features currently under review.

Start extracting fields from a document using generative extractor

Important:

This feature is currently part of an audit process and is not to be considered part of the FedRAMP Authorization until the review is finalized. See here the full list of features currently under review.

Tip: The Project ID is obtained from the response received from the Get project information call.

curl -X 'POST' \
  'https://cloud.uipath.com/<Organization_Name>/<Tenant_Name>/du_/api/framework/projects/<Project_ID>/extractors/generative_extractor/extraction?api-version=1' \
  -H 'accept: text/plain' \
  -H 'Authorization: Bearer eyJhbGciOiJSUzI1NiIsImtpZCI6IjkxODQzNjM3MzVGRDU1RDgyQ0JBNTM2N0Y1MDdCNEEwOEUzMkUxNkEiLCJ4NXQiOiJrWVEyTnpYOVZkZ3N1bE5uOVFlMG9JNHk0V28iLCJ0eXAiOiJKV1QifQ.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.DLF7AK_Q2xwnR0VJxagXLNM6kuxjDt0F6d_UEV3AmEhr_Gi8Ykn4UXVfa-YbnnZvx5mLcZdT9kAZIPVi3FvE7R6N_60FS7j72TMjhaBtKVzt7NBxMjdXmuEqoom9wyRhX5IXEdWxhg5GGseL_m7fbLcBJYrHIvmZCIcTVNLMd73E5TzJwaW3TpQ_cZOBtvjhOZ-lIZus_R2hPez3v5E_d2BsmV9kbIf-DnhQm5LfUvD2JYytSiTiiWQVDE4lVDqQri88feUwSMOKp7e1Z_Kg9i7mf7SHjL9uH0tQWczTOP0LDHHN0uOsJsVhmlmMREyMjnjF0X8vA2PVda3uyjUJqg' \
  -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

Important:

This feature is currently part of an audit process and is not to be considered part of the FedRAMP Authorization until the review is finalized. See here the full list of features currently under review.

{
    "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
    }
}