Cloudmersive Run Batch Job API

openapi: 3.2.0
info:
  title: Document AI Run Batch Job API
  description: Extract structured data including named fields, tables, barcodes, classifications, and summaries from common document formats, scanned documents, and photos of documents using AI. Also supports handwriting and low quality photos and scans, as well as digital document input. Supports a wide range of languages, and is able to analyze and infer semantic structure from the visual layout for documents.
  termsOfService: https://portal.cloudmersive.com/terms-of-service
  contact:
    name: Cloudmersive
    url: https://www.cloudmersive.com
    email: support@cloudmersive.com
  version: v1
servers:
- url: https://api.cloudmersive.com
security:
- Apikey: []
tags:
- name: RunBatchJob
paths:
  /document-ai/document/batch-job/extract/text:
    post:
      tags:
      - RunBatchJob
      summary: Extract Text from a Document using AI as a Batch Job
      description: 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.
      operationId: ExtractTextFromDocumentBatchJob
      parameters:
      - in: header
        name: recognitionMode
        description: Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            text/plain:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
            text/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                InputFile:
                  type: string
                  description: Input document, or photos of a document, to extract data from
                  format: binary
  /document-ai/document/batch-job/extract/fields/advanced:
    post:
      tags:
      - RunBatchJob
      summary: Extract Field Values from a Document using Advanced AI as a Batch Job
      description: 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.
      operationId: ExtractFieldsFromDocumentAdvancedBatchJob
      parameters:
      - in: header
        name: recognitionMode
        description: Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            text/plain:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
            text/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/AdvancedExtractFieldsRequest'
          text/json:
            schema:
              $ref: '#/components/schemas/AdvancedExtractFieldsRequest'
          application/*+json:
            schema:
              $ref: '#/components/schemas/AdvancedExtractFieldsRequest'
        description: Input document and parameters
  /document-ai/document/batch-job/extract/all:
    post:
      tags:
      - RunBatchJob
      summary: Extract All Fields and Tables of Data from a Document using AI as a Batch Job
      description: 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.
      operationId: ExtractAllFieldsAndTablesFromDocumentBatchJob
      parameters:
      - in: header
        name: recognitionMode
        description: Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            text/plain:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
            text/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                InputFile:
                  type: string
                  description: Input document, or photos of a document, to extract data from
                  format: binary
  /document-ai/document/batch-job/extract/classify:
    post:
      tags:
      - RunBatchJob
      summary: Extract Classification or Category from a Document using AI as a Batch Job
      description: 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.
      operationId: ExtractClassificationFromDocumentBatchJob
      parameters:
      - in: header
        name: Categories
        description: Desired classification to extract
        schema:
          type: string
      - in: header
        name: recognitionMode
        description: Optional; Recognition mode - Advanced (default) provides the highest accuracy but slower speed, while Normal provides faster response but lower accuracy for low quality images
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            text/plain:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
            text/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentBatchJobResult'
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                InputFile:
                  type: string
                  description: Input document, or photos of a document, to extract data from
                  format: binary
  /document-ai/document/batch-job/batch-job/status:
    get:
      tags:
      - RunBatchJob
      summary: Get the status and result of an Extract Document Batch Job
      description: 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.
      operationId: GetAsyncJobStatus
      parameters:
      - in: query
        name: AsyncJobID
        description: Job ID for the batch job to get the status of
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            text/plain:
              schema:
                $ref: '#/components/schemas/ExtractDocumentJobStatusResult'
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentJobStatusResult'
            text/json:
              schema:
                $ref: '#/components/schemas/ExtractDocumentJobStatusResult'
components:
  schemas:
    ExtractFieldsResponse:
      description: Result of extracting fields from a document
      type: object
      properties:
        Successful:
          description: True if successful, false otherwise
          type: boolean
        Results:
          description: Field value results from the extraction operation
          type: array
          items:
            $ref: '#/components/schemas/FieldValue'
      additionalProperties: false
    ExtractTextResponse:
      description: Result of extracting text from a document
      type: object
      properties:
        Successful:
          description: True if successful, false otherwise
          type: boolean
        PageResults:
          description: Page results from the extraction operation
          type: array
          items:
            $ref: '#/components/schemas/ExtractedTextPage'
      additionalProperties: false
    ExtractedTextPage:
      description: Extracted page from an input document
      type: object
      properties:
        PageNumber:
          format: int32
          description: Page number index, 1-based
          type: integer
        TextResult:
          description: Text content of the page
          type: string
      additionalProperties: false
    TableResultRow:
      description: Row of a table extracted from a document
      type: object
      properties:
        Cells:
          description: Cells in the row
          type: array
          items:
            $ref: '#/components/schemas/TableResultCell'
      additionalProperties: false
    ExtractDocumentJobStatusResult:
      description: Result of performing a batch job operation
      type: object
      properties:
        Successful:
          description: True if the operation to check the status of the job was successful, false otherwise
          type: boolean
        AsyncJobStatus:
          description: Returns the job status of the Async Job, if applicable.  Possible states are STARTED and COMPLETED
          type: string
        AsyncJobID:
          description: Job ID
          type: string
        ExtractTextResult:
          $ref: '#/components/schemas/ExtractTextResponse'
        ExtractFieldsAndTablesResult:
          $ref: '#/components/schemas/ExtractFieldsAndTablesResponse'
        ExtractFieldsResult:
          $ref: '#/components/schemas/ExtractFieldsResponse'
        ExtractClassificationResult:
          $ref: '#/components/schemas/DocumentClassificationResult'
        ErrorMessage:
          description: Error message (if any)
          type: string
      additionalProperties: false
    TableResult:
      description: Table extracted from a document
      type: object
      properties:
        Title:
          description: Title of the table (optional)
          type: string
        Rows:
          description: Rows of the table
          type: array
          items:
            $ref: '#/components/schemas/TableResultRow'
      additionalProperties: false
    ExtractDocumentBatchJobResult:
      description: Result of performing a split document batch job
      type: object
      properties:
        Successful:
          description: True if successful, false otherwise
          type: boolean
        AsyncJobID:
          description: 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
          type: string
      additionalProperties: false
    ExtractFieldsAndTablesResponse:
      description: Result of extracting fields from a document
      type: object
      properties:
        Successful:
          description: True if successful, false otherwise
          type: boolean
        FieldResults:
          description: Field value results from the extraction operation
          type: array
          items:
            $ref: '#/components/schemas/FieldValue'
        TableResults:
          description: Table value results from the extraction operation
          type: array
          items:
            $ref: '#/components/schemas/TableResult'
      additionalProperties: false
    AdvancedExtractFieldsRequest:
      description: Request to perform an AI field extraction on a document
      type: object
      properties:
        InputFile:
          format: byte
          description: Input document file to perform the operation on as a byte array
          type: string
        FieldsToExtract:
          description: Fields to extract from the document
          type: array
          items:
            $ref: '#/components/schemas/FieldToExtract'
        MaximumPagesProcessed:
          format: int32
          description: 'Optional: Limit the number of pages processed'
          type: integer
        Preprocessing:
          description: '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.'
          type: string
        ResultCrossCheck:
          description: '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.'
          type: string
        RotateImageDegrees:
          format: double
          description: 'Optional: Rotate the input image before recognition by the specified number of degrees; valid values range from -360 to +360.'
          type: number
      additionalProperties: false
    DocumentClassificationResult:
      description: Result of classifying a document using AI
      type: object
      properties:
        Successful:
          description: True if successful, false otherwise
          type: boolean
        DocumentCategoryResult:
          description: Category applied to the document; if a category could not be identified then "other" will be used.  Spaces are replaced with underscores.
          type: string
      additionalProperties: false
    TableResultCell:
      description: Cell of a row of a table extracted from a document
      type: object
      properties:
        CellHeader:
          description: Cell column header
          type: string
        CellValue:
          description: Cell value as a string
          type: string
      additionalProperties: false
    FieldValue:
      description: Field value result of extracting fields from a document
      type: object
      properties:
        FieldName:
          description: Name of the field (note that spaces will be replaced with underscore)
          type: string
        FieldStringValue:
          description: Primary or first string value of the field that was extractged from the document
          type: string
        AdditionalFieldStringValues:
          description: Additional values for this field when the same field is present with multiple values, for example, if two instances of the same form occur in the same document
          type: array
          items:
            type: string
      additionalProperties: false
    FieldToExtract:
      description: Field to extract from a document using AI
      type: object
      properties:
        FieldName:
          description: Name of the field to extract
          type: string
        FieldOptional:
          description: 'Optional: True if the field is optional, false if required (default)'
          type: boolean
        FieldDescription:
          description: '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.'
          type: string
        FieldExample:
          description: 'Optional: Example label or value of the field'
          type: string
      additionalProperties: false
  securitySchemes:
    Apikey:
      type: apiKey
      name: Apikey
      in: header
      description: API Key Authentication
x-provenance:
  method: harvested
  publisher: Cloudmersive
  source: https://api.cloudmersive.com/document-ai/docs/v1/swagger
  note: split by refine-openapis from the provider's own published document, verified by fetch (openapi/_original/*.fetch.json);
    stamped by stamp-openapi-provenance.py (roadmap#793)