Document AI API API Reference

Terms of Service: https://portal.cloudmersive.com/terms-of-service

Version: v1

Authentication

Apikey

API Key Authentication

type

apiKey

name

Apikey

header

Analyze

Enforce Policies to a Document to allow or block it using Advanced AI

POST /document-ai/document/analyze/enforce-policy

Enforce Policies to a Document to allow or block it using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.

DocumentPolicyRequest

Input request, including document and policy rules

Code Example:

Request Content-Types: application/json, text/json, application/*+json

Request Example

{
  "InputFile": "string (byte)",
  "Rules": [
    {
      "RuleId": "string",
      "RuleType": "string",
      "RuleDescription": "string"
    }
  ]
}

200 OK

DocumentPolicyResult

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "CleanResult": "boolean",
  "RiskScore": "number (double)",
  "RuleViolations": [
    {
      "RuleId": "string",
      "RuleViolationRiskScore": "number (double)",
      "RuleViolationRationale": "string"
    }
  ]
}

Extract

Extract Text from a Document using AI

POST /document-ai/document/extract/text

Extract raw text from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Supports a wide range of languages. Consumes 100 API calls per page.

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

ExtractTextResponse

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "PageResults": [
    {
      "PageNumber": "integer (int32)",
      "TextResult": "string"
    }
  ]
}

Extract

Extract Field Values from a Document using AI

POST /document-ai/document/extract/fields

Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.

FieldNames: string

in header

Desired fields to extract, comma separated

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

ExtractFieldsResponse

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "Results": [
    {
      "FieldName": "string",
      "FieldStringValue": "string"
    }
  ]
}

Extract

Extract Field Values from a Document using Advanced AI

POST /document-ai/document/extract/fields/advanced

Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.

AdvancedExtractFieldsRequest

Input request, including document file as byte array, and information on which fields to extract

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

Code Example:

Request Content-Types: application/json, text/json, application/*+json

Request Example

{
  "InputFile": "string (byte)",
  "FieldsToExtract": [
    {
      "FieldName": "string",
      "FieldOptional": "boolean",
      "FieldDescription": "string",
      "FieldExample": "string"
    }
  ],
  "MaximumPagesProcessed": "integer (int32)",
  "Preprocessing": "string",
  "ResultCrossCheck": "string",
  "RotateImageDegrees": "number (double)"
}

200 OK

ExtractFieldsAdvancedResponse

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "Results": [
    {
      "FieldName": "string",
      "FieldStringValue": "string"
    }
  ],
  "ConfidenceScore": "number (double)"
}

Extract

Extract Tables of Data from a Document using AI

POST /document-ai/document/extract/tables

Extract Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumeds 100 API calls per page.

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

ExtractTablesResponse

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "TableResults": [
    {
      "Title": "string",
      "Rows": [
        {
          "Cells": [
            {
              "CellHeader": "string",
              "CellValue": "string"
            }
          ]
        }
      ]
    }
  ]
}

Extract

Extract Barcodes of from a Document using AI

POST /document-ai/document/extract/barcodes

Extract all barcodes from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

ExtractBarcodesAiResponse

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "BarcodeResults": [
    {
      "BarcodeType": "string",
      "BarcodeValue": "string"
    }
  ]
}

Extract

Extract All Fields and Tables of Data from a Document using AI

POST /document-ai/document/extract/all

Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

ExtractFieldsAndTablesResponse

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "FieldResults": [
    {
      "FieldName": "string",
      "FieldStringValue": "string"
    }
  ],
  "TableResults": [
    {
      "Title": "string",
      "Rows": [
        {
          "Cells": [
            {
              "CellHeader": "string",
              "CellValue": "string"
            }
          ]
        }
      ]
    }
  ]
}

Extract

Extract Classification or Category from a Document using AI

POST /document-ai/document/extract/classify

Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.

Categories: string

in header

Desired classification to extract

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

DocumentClassificationResult

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "DocumentCategoryResult": "string"
}

Extract

Extract Classification or Category from a Document using Advanced AI

POST /document-ai/document/extract/classify/advanced

Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.

AdvancedExtractClassificationRequest

Input request to perform the classification on

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

Code Example:

Request Content-Types: application/json, text/json, application/*+json

Request Example

{
  "InputFile": "string (byte)",
  "Categories": [
    {
      "CategoryName": "string",
      "CategoryDescription": "string"
    }
  ],
  "Preprocessing": "string",
  "ResultCrossCheck": "string",
  "MaximumPagesProcessed": "integer (int32)",
  "RotateImageDegrees": "number (double)"
}

200 OK

DocumentAdvancedClassificationResult

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "DocumentCategoryResult": "string",
  "ConfidenceScore": "number (double)"
}

Extract

Extract Summary from a Document using AI

POST /document-ai/document/extract/summary

Creates a 1 paragraph summary of the input document using Artificial Intelligence. Input document formats supported include DOCX, PDF, PNG and JPG. Consumes 100 API calls per page.

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

SummarizeDocumentResponse

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "DocumentSummaryText": "string"
}

RunBatchJob

Extract Text from a Document using AI as a Batch Job

POST /document-ai/document/batch-job/extract/text

Creates an async batch job for processing a large document as an AI batch job. Input document formats supported include DOCX, PDF, PNG and JPG. Supports a wide range of languages. Requires Managed Instance or Private Cloud deployment.

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

ExtractDocumentBatchJobResult

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "AsyncJobID": "string"
}

RunBatchJob

Extract Field Values from a Document using Advanced AI as a Batch Job

POST /document-ai/document/batch-job/extract/fields/advanced

Creates an async batch job for processing a large document as an AI batch job. Extract Field Values (e.g. Invoice Number, Invoice Date, Business Card Phone Number, etc.) from a document using Advanced AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.

AdvancedExtractFieldsRequest

undefined

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

Code Example:

Request Content-Types: application/json, text/json, application/*+json

Request Example

{
  "InputFile": "string (byte)",
  "FieldsToExtract": [
    {
      "FieldName": "string",
      "FieldOptional": "boolean",
      "FieldDescription": "string",
      "FieldExample": "string"
    }
  ],
  "MaximumPagesProcessed": "integer (int32)",
  "Preprocessing": "string",
  "ResultCrossCheck": "string",
  "RotateImageDegrees": "number (double)"
}

200 OK

ExtractDocumentBatchJobResult

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "AsyncJobID": "string"
}

RunBatchJob

Extract All Fields and Tables of Data from a Document using AI as a Batch Job

POST /document-ai/document/batch-job/extract/all

Creates an async batch job for processing a large document as an AI batch job. Extract all Fields and Tables, comprised of rows and columns of data, from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

ExtractDocumentBatchJobResult

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "AsyncJobID": "string"
}

RunBatchJob

Extract Classification or Category from a Document using AI as a Batch Job

POST /document-ai/document/batch-job/extract/classify

Creates an async batch job for processing a large document as an AI batch job. Extract Classification or Category (e.g. Invoice, Receipt, Tax Form, or Form 1040, Form 1040 EZ, etc.) from a document using AI. Input document formats supported include DOCX, PDF, PNG and JPG. Requires Managed Instance or Private Cloud deployment.

Categories: string

in header

Desired classification to extract

recognitionMode: string

in header

Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images

InputFile: file

in formData

Input document, or photos of a document, to extract data from

Code Example:

200 OK

ExtractDocumentBatchJobResult

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "AsyncJobID": "string"
}

RunBatchJob

Get the status and result of an Extract Document Batch Job

GET /document-ai/document/batch-job/batch-job/status

Returns the result of the Async Job - possible states can be STARTED or COMPLETED. This API is only available for Cloudmersive Managed Instance and Private Cloud deployments.

AsyncJobID: string

in query

(no description)

Code Example:

200 OK

ExtractDocumentJobStatusResult

Response Content-Types: text/plain, application/json, text/json

Response Example (200 OK)

{
  "Successful": "boolean",
  "AsyncJobStatus": "string",
  "AsyncJobID": "string",
  "ExtractTextResult": {
    "Successful": "boolean",
    "PageResults": [
      {
        "PageNumber": "integer (int32)",
        "TextResult": "string"
      }
    ]
  },
  "ExtractFieldsAndTablesResult": {
    "Successful": "boolean",
    "FieldResults": [
      {
        "FieldName": "string",
        "FieldStringValue": "string"
      }
    ],
    "TableResults": [
      {
        "Title": "string",
        "Rows": [
          {
            "Cells": [
              {
                "CellHeader": "string",
                "CellValue": "string"
              }
            ]
          }
        ]
      }
    ]
  },
  "ExtractFieldsResult": {
    "Successful": "boolean",
    "Results": [
      {
        "FieldName": "string",
        "FieldStringValue": "string"
      }
    ]
  },
  "ExtractClassificationResult": {
    "Successful": "boolean",
    "DocumentCategoryResult": "string"
  },
  "ErrorMessage": "string"
}

Schema Definitions

AdvancedExtractClassificationRequest: object

Request to perform an AI document classification on a document

InputFile: string (byte): Input document file to perform the operation on as a byte array
Categories: DocumentCategories: Possible categories for the document
DocumentCategories
Preprocessing: string: Optional: Set the level of image pre-processing to enhance accuracy. Possible values are 'Auto', 'SmoothEdges', 'SmoothEdgesPlus', 'Compatability' and 'None'. Default is Auto. Set to SmoothEdges to smooth harsh edges in the input image to enhance recognition accuracy. Set to SmoothEdgesPlus to smooth harsh edges to a higher degree. Set to Compatability for maximum PDF feature compatability.
ResultCrossCheck: string: Optional: Set the level of output accuracy cross-checking to perform on the input. Possible values are 'None', 'Advanced', 'Ultra' and 'Hyper'. Default is None. Ultra and Hyper will produce the highest accuracy but at the cost of longer processing times.
MaximumPagesProcessed: integer (int32): Optional: Limit the number of pages processed
RotateImageDegrees: number (double): Optional: Rotate the input image before recognition by the specified number of degrees; valid values range from -360 to +360.

Example

{
  "InputFile": "string (byte)",
  "Categories": [
    {
      "CategoryName": "string",
      "CategoryDescription": "string"
    }
  ],
  "Preprocessing": "string",
  "ResultCrossCheck": "string",
  "MaximumPagesProcessed": "integer (int32)",
  "RotateImageDegrees": "number (double)"
}

AdvancedExtractFieldsRequest: object

Request to perform an AI field extraction on a document

InputFile: string (byte): Input document file to perform the operation on as a byte array
FieldsToExtract: FieldToExtract: Fields to extract from the document
FieldToExtract
MaximumPagesProcessed: integer (int32): Optional: Limit the number of pages processed
Preprocessing: string: Optional: Set the level of image pre-processing to enhance accuracy. Possible values are 'Auto', 'SmoothEdges', 'SmoothEdgesPlus', 'ContrastEdges', 'ContrastEdgesPlus', 'Invert', 'Binarize', 'Compatability' and 'None'. Default is Auto. Set to SmoothEdges to smooth harsh edges in the input image to enhance recognition accuracy. Set to SmoothEdgesPlus to smooth harsh edges to a higher degree. Set to ContrastEdges and ContrastEdgesPlus to enhance contrast and readability for low quality black and white or grayscale images. Set to Invert to invert the input image. Set to Binarize to binarize the input image. Set to Compatability for maximum PDF feature compatability.
ResultCrossCheck: string: Optional: Set the level of output accuracy cross-checking to perform on the input. Possible values are 'None', 'Advanced' and 'Ultra'. Default is None. Ultra will produce the highest accuracy but at the cost of longer processing times.
RotateImageDegrees: number (double): Optional: Rotate the input image before recognition by the specified number of degrees; valid values range from -360 to +360.

Example

{
  "InputFile": "string (byte)",
  "FieldsToExtract": [
    {
      "FieldName": "string",
      "FieldOptional": "boolean",
      "FieldDescription": "string",
      "FieldExample": "string"
    }
  ],
  "MaximumPagesProcessed": "integer (int32)",
  "Preprocessing": "string",
  "ResultCrossCheck": "string",
  "RotateImageDegrees": "number (double)"
}

DocumentAdvancedClassificationResult: object

Result of classifying a document using AI

Successful: boolean: True if successful, false otherwise
DocumentCategoryResult: string: Category applied to the document; if a category could not be identified then "other" will be used. Spaces are replaced with underscores.
ConfidenceScore: number (double): Confidence score between 0.0 and 1.0, where values > 0.8 indicate high confidence

Example

{
  "Successful": "boolean",
  "DocumentCategoryResult": "string",
  "ConfidenceScore": "number (double)"
}

DocumentCategories: object

Document category option

CategoryName: string: Name of the classification
CategoryDescription: string: Optional but recommended: Description of the classification in natural langugage

Example

{
  "CategoryName": "string",
  "CategoryDescription": "string"
}

DocumentClassificationResult: object

Result of classifying a document using AI

Successful: boolean: True if successful, false otherwise
DocumentCategoryResult: string: Category applied to the document; if a category could not be identified then "other" will be used. Spaces are replaced with underscores.

Example

{
  "Successful": "boolean",
  "DocumentCategoryResult": "string"
}

DocumentPolicyRequest: object

Request to analyze a document

InputFile: string (byte): Input file as a byte array
Rules: PolicyRule: Rules to apply to the document
PolicyRule

Example

{
  "InputFile": "string (byte)",
  "Rules": [
    {
      "RuleId": "string",
      "RuleType": "string",
      "RuleDescription": "string"
    }
  ]
}

DocumentPolicyResult: object

Result of performing a document policy enforcement operation

CleanResult: boolean: True if the document complies with all of the policies, and false if it does not
RiskScore: number (double): Risk score between 0.0 and 1.0 where values above 0.5 are increasing levels of risk
RuleViolations: PolicyRuleViolation: Policy violations
PolicyRuleViolation

Example

{
  "CleanResult": "boolean",
  "RiskScore": "number (double)",
  "RuleViolations": [
    {
      "RuleId": "string",
      "RuleViolationRiskScore": "number (double)",
      "RuleViolationRationale": "string"
    }
  ]
}

ExtractBarcodesAiResponse: object

Result of extracting barcodes from a document

Successful: boolean: True if successful, false otherwise
BarcodeResults: ExtractedBarcodeItem: Table value results from the extraction operation
ExtractedBarcodeItem

Example

{
  "Successful": "boolean",
  "BarcodeResults": [
    {
      "BarcodeType": "string",
      "BarcodeValue": "string"
    }
  ]
}

ExtractDocumentBatchJobResult: object

Result of performing a split document batch job

Successful: boolean: True if successful, false otherwise
AsyncJobID: string: When creating a job, an Async Job ID is returned. Use the GetAsyncJobStatus API to check on the status of this job using the AsyncJobID and get the result when it finishes

Example

{
  "Successful": "boolean",
  "AsyncJobID": "string"
}

ExtractDocumentJobStatusResult: object

Result of performing a batch job operation

Successful: boolean: True if the operation to check the status of the job was successful, false otherwise
AsyncJobStatus: string: Returns the job status of the Async Job, if applicable. Possible states are STARTED and COMPLETED
AsyncJobID: string: Job ID
ExtractTextResult: ExtractTextResponse
ExtractFieldsAndTablesResult: ExtractFieldsAndTablesResponse
ExtractFieldsResult: ExtractFieldsResponse
ExtractClassificationResult: DocumentClassificationResult
ErrorMessage: string: Error message (if any)

Example

{
  "Successful": "boolean",
  "AsyncJobStatus": "string",
  "AsyncJobID": "string",
  "ExtractTextResult": {
    "Successful": "boolean",
    "PageResults": [
      {
        "PageNumber": "integer (int32)",
        "TextResult": "string"
      }
    ]
  },
  "ExtractFieldsAndTablesResult": {
    "Successful": "boolean",
    "FieldResults": [
      {
        "FieldName": "string",
        "FieldStringValue": "string"
      }
    ],
    "TableResults": [
      {
        "Title": "string",
        "Rows": [
          {
            "Cells": [
              {
                "CellHeader": "string",
                "CellValue": "string"
              }
            ]
          }
        ]
      }
    ]
  },
  "ExtractFieldsResult": {
    "Successful": "boolean",
    "Results": [
      {
        "FieldName": "string",
        "FieldStringValue": "string"
      }
    ]
  },
  "ExtractClassificationResult": {
    "Successful": "boolean",
    "DocumentCategoryResult": "string"
  },
  "ErrorMessage": "string"
}

ExtractFieldsAdvancedResponse: object

Result of extracting fields from a document

Successful: boolean: True if successful, false otherwise
Results: FieldAdvancedValue: Field value results from the extraction operation
FieldAdvancedValue
ConfidenceScore: number (double): Confidence score between 0.0 and 1.0, where values > 0.8 indicate high confidence

Example

{
  "Successful": "boolean",
  "Results": [
    {
      "FieldName": "string",
      "FieldStringValue": "string"
    }
  ],
  "ConfidenceScore": "number (double)"
}

ExtractFieldsAndTablesResponse: object

Result of extracting fields from a document

Successful: boolean: True if successful, false otherwise
FieldResults: FieldValue: Field value results from the extraction operation
FieldValue
TableResults: TableResult: Table value results from the extraction operation
TableResult

Example

{
  "Successful": "boolean",
  "FieldResults": [
    {
      "FieldName": "string",
      "FieldStringValue": "string"
    }
  ],
  "TableResults": [
    {
      "Title": "string",
      "Rows": [
        {
          "Cells": [
            {
              "CellHeader": "string",
              "CellValue": "string"
            }
          ]
        }
      ]
    }
  ]
}

ExtractFieldsResponse: object

Result of extracting fields from a document

Successful: boolean: True if successful, false otherwise
Results: FieldValue: Field value results from the extraction operation
FieldValue

Example

{
  "Successful": "boolean",
  "Results": [
    {
      "FieldName": "string",
      "FieldStringValue": "string"
    }
  ]
}

ExtractTablesResponse: object

Result of extracting tables from a document

Successful: boolean: True if successful, false otherwise
TableResults: TableResult: Table value results from the extraction operation
TableResult

Example

{
  "Successful": "boolean",
  "TableResults": [
    {
      "Title": "string",
      "Rows": [
        {
          "Cells": [
            {
              "CellHeader": "string",
              "CellValue": "string"
            }
          ]
        }
      ]
    }
  ]
}

ExtractTextResponse: object

Result of extracting text from a document

Successful: boolean: True if successful, false otherwise
PageResults: ExtractedTextPage: Page results from the extraction operation
ExtractedTextPage

Example

{
  "Successful": "boolean",
  "PageResults": [
    {
      "PageNumber": "integer (int32)",
      "TextResult": "string"
    }
  ]
}

ExtractedBarcodeItem: object

Extracted barcode result

BarcodeType: string: Type of the barcode identified, possible values are: AZTEC, CODABAR, CODE_39, CODE_93, CODE_128, DATA_MATRIX, EAN_8, EAN_13, ITF, MAXICODE, PDF_417, QR_CODE, RSS_14, RSS_EXPANDED, UPC_A, UPC_E, All_1D, UPC_EAN_EXTENSION, MSI, PLESSEY, IMB, UNKNOWN
BarcodeValue: string: Value of the barcode as a string

Example

{
  "BarcodeType": "string",
  "BarcodeValue": "string"
}

ExtractedTextPage: object

Extracted page from an input document

PageNumber: integer (int32): Page number index, 1-based
TextResult: string: Text content of the page

Example

{
  "PageNumber": "integer (int32)",
  "TextResult": "string"
}

FieldAdvancedValue: object

Field value result of extracting fields from a document

FieldName: string: Name of the field (note that spaces will be replaced with underscore)
FieldStringValue: string: String value of the field that was extractged from the document

Example

{
  "FieldName": "string",
  "FieldStringValue": "string"
}

FieldToExtract: object

Field to extract from a document using AI

FieldName: string: Name of the field to extract
FieldOptional: boolean: Optional: True if the field is optional, false if required (default)
FieldDescription: string: Optional but recommended: Description of the field - use this to describe what the field is, how it is formatted, what is unique about it, etc.
FieldExample: string: Optional: Example label or value of the field

Example

{
  "FieldName": "string",
  "FieldOptional": "boolean",
  "FieldDescription": "string",
  "FieldExample": "string"
}

FieldValue: object

Field value result of extracting fields from a document

FieldName: string: Name of the field (note that spaces will be replaced with underscore)
FieldStringValue: string: String value of the field that was extractged from the document

Example

{
  "FieldName": "string",
  "FieldStringValue": "string"
}

PolicyRule: object

RuleId: string
RuleType: string: Possible values are ALLOW and DENY
RuleDescription: string: Description of the rule in natural language, e.g. Do not allow documents that contain offensive language

Example

{
  "RuleId": "string",
  "RuleType": "string",
  "RuleDescription": "string"
}

PolicyRuleViolation: object

Instances of a policy rule violation

RuleId: string: ID of the rule; if no ID was supplied, the ID is the 1-based index of the rule
RuleViolationRiskScore: number (double): Risk score between 0.0 and 1.0 where values above 0.5 are increasing levels of risk
RuleViolationRationale: string: AI natural language rationale for why this policy was violated

Example

{
  "RuleId": "string",
  "RuleViolationRiskScore": "number (double)",
  "RuleViolationRationale": "string"
}

SummarizeDocumentResponse: object

Result of summarizing a document

Successful: boolean: True if successful, false otherwise
DocumentSummaryText: string: Summary of the document

Example

{
  "Successful": "boolean",
  "DocumentSummaryText": "string"
}

TableResult: object

Table extracted from a document

Title: string: Title of the table (optional)
Rows: TableResultRow: Rows of the table
TableResultRow

Example

{
  "Title": "string",
  "Rows": [
    {
      "Cells": [
        {
          "CellHeader": "string",
          "CellValue": "string"
        }
      ]
    }
  ]
}

TableResultCell: object

Cell of a row of a table extracted from a document

CellHeader: string: Cell column header
CellValue: string: Cell value as a string

Example

{
  "CellHeader": "string",
  "CellValue": "string"
}

TableResultRow: object

Row of a table extracted from a document

Cells: TableResultCell: Cells in the row
TableResultCell

Example

{
  "Cells": [
    {
      "CellHeader": "string",
      "CellValue": "string"
    }
  ]
}