sensible-so Reference document API

openapi: 3.0.3
info:
  title: Sensible Classification Configuration Reference document API
  version: v0
  description: Classify a document into one of the document types defined in your Sensible account, synchronously or asynchronously. Use classification to route documents in a workflow or label documents in a system of record.
  contact:
    name: Sensible
    url: https://www.sensible.so
    email: support@sensible.so
  license:
    name: Proprietary
    url: https://www.sensible.so/terms
servers:
- url: https://api.sensible.so/v0
  description: Production server
security:
- bearerAuth: []
tags:
- name: Reference document
paths:
  /document_types/{type-id}/goldens:
    parameters:
    - $ref: '#/components/parameters/documentTypeId'
    post:
      operationId: create-reference-document
      summary: Create reference document
      description: Specify document metadata in the request, and get back an `upload_url` at which to put the PDF, for example with `curl -T ./sample.pdf`.
      tags:
      - Reference document
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostGolden'
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GoldenResponse'
          description: The created reference document
        '400':
          $ref: '#/components/responses/400'
        '401':
          $ref: '#/components/responses/401'
        '404':
          $ref: '#/components/responses/404'
        '415':
          $ref: '#/components/responses/415'
        '500':
          $ref: '#/components/responses/500'
    get:
      operationId: list-reference-documents
      summary: List all reference documents in a document type
      description: List all reference documents in a document type
      tags:
      - Reference document
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetAllGoldens'
          description: List of reference documents for the current account
        '400':
          $ref: '#/components/responses/400'
        '401':
          $ref: '#/components/responses/401'
        '404':
          $ref: '#/components/responses/404'
        '415':
          $ref: '#/components/responses/415'
        '500':
          $ref: '#/components/responses/500'
  /extract_text_from_golden/{type-name}:
    parameters:
    - $ref: '#/components/parameters/documentTypeName'
    post:
      operationId: extract-all-text-from-reference-document
      summary: Extract all text from reference document
      description: Get all the text (lines) for a reference document as standardized output. The output is an array of pages with metadata such as text positioning. If you specify a configuration, Sensible uses preprocessors defined in the configuration to process the text.
      tags:
      - Reference document
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PostGoldenExtraction'
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResponseStandardText'
          description: All the text in the document
        '400':
          $ref: '#/components/responses/400'
        '401':
          $ref: '#/components/responses/401'
        '404':
          $ref: '#/components/responses/404'
        '415':
          $ref: '#/components/responses/415'
        '500':
          $ref: '#/components/responses/500'
  /document_types/{type-id}/goldens/{document-name}:
    parameters:
    - $ref: '#/components/parameters/documentTypeId'
    - $ref: '#/components/parameters/documentName'
    put:
      operationId: update-reference-document
      summary: Update metadata for a reference document
      description: Update metadata for a reference document
      tags:
      - Reference document
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PutGolden'
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GoldenResponse'
          description: The updated reference document
        '400':
          $ref: '#/components/responses/400'
        '401':
          $ref: '#/components/responses/401'
        '404':
          $ref: '#/components/responses/404'
        '415':
          $ref: '#/components/responses/415'
        '500':
          $ref: '#/components/responses/500'
    get:
      operationId: get-reference-document
      summary: Get reference document metadata
      description: Get download URL and other metadata for a reference document.
      tags:
      - Reference document
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GoldenResponse'
          description: The identified reference document
        '400':
          $ref: '#/components/responses/400'
        '401':
          $ref: '#/components/responses/401'
        '404':
          $ref: '#/components/responses/404'
        '415':
          $ref: '#/components/responses/415'
        '500':
          $ref: '#/components/responses/500'
    delete:
      operationId: delete-reference-document
      summary: Delete reference document
      description: Delete a reference document and break associations to any configs.
      tags:
      - Reference document
      responses:
        '204':
          $ref: '#/components/responses/204'
        '400':
          $ref: '#/components/responses/400'
        '401':
          $ref: '#/components/responses/401'
        '404':
          $ref: '#/components/responses/404'
        '415':
          $ref: '#/components/responses/415'
        '500':
          $ref: '#/components/responses/500'
  /document_types/{type-id}/goldens/{document-name}/configuration:
    parameters:
    - $ref: '#/components/parameters/documentTypeId'
    - $ref: '#/components/parameters/documentName'
    delete:
      operationId: delete-reference-document-association
      summary: Unassociate reference document from configuration
      description: Break the association between a reference document and its configuration.
      tags:
      - Reference document
      responses:
        '204':
          $ref: '#/components/responses/204'
        '400':
          $ref: '#/components/responses/400'
        '401':
          $ref: '#/components/responses/401'
        '404':
          $ref: '#/components/responses/404'
        '415':
          $ref: '#/components/responses/415'
        '500':
          $ref: '#/components/responses/500'
components:
  schemas:
    PutGolden:
      type: object
      properties:
        name:
          $ref: '#/components/schemas/DocumentName'
        configuration:
          $ref: '#/components/schemas/AssociatedConfigurationName'
      additionalProperties: false
    PostGolden:
      type: object
      description: Upload url for putting the document
      properties:
        name:
          $ref: '#/components/schemas/DocumentName'
        configuration:
          $ref: '#/components/schemas/AssociatedConfigurationName'
      required:
      - name
      additionalProperties: false
    GoldenResponse:
      type: object
      properties:
        name:
          $ref: '#/components/schemas/DocumentName'
        created:
          $ref: '#/components/schemas/Date'
        configuration:
          $ref: '#/components/schemas/AssociatedConfigurationName'
        error:
          type: string
          description: Any errors that occurred processing the reference document
        upload_url:
          type: string
          description: If present, the URL to which a reference document can be PUT
        download_url:
          type: string
          description: If present, the URL to GET to retrieve the reference document
        thumbnail_url:
          type: string
          description: If present, the URL to GET to retrieve a thumbnail image of the first page of the reference document
      required:
      - name
      - created
      additionalProperties: false
    UniqueId:
      type: string
      format: uuid
      description: Unique identifier
      example: 3fa85f64-5717-4562-b3fc-2c963f66afa6
    AssociatedConfigurationName:
      type: string
      pattern: ^[a-z0-9_]*$
      minLength: 3
      maxLength: 128
      description: User-friendly name of the configuration to associate to the reference document
      example: anyco_auto_insurance_quote
    ResponseStandardText:
      description: all the text in the document, standardized as an array of pages with lines and their metadata, including positioning
      type: object
      example:
        pages:
        - width: 8.5
          height: 11
          rotation: 0
          transform:
            a: 1
            c: 0
            e: 0
            b: 0
            d: 1
            f: 0
          lines:
          - text: Extract your first data
            boundingPolygon:
            - x: 1.111
              y: 0.472
            - x: 4.661
              y: 0.472
            - x: 4.661
              y: 0.806
            - x: 1.111
              y: 0.806
          - text: Hello world!
            boundingPolygon:
            - x: 0.444
              y: 1.792
            - x: 2.07
              y: 1.792
            - x: 2.07
              y: 2.083
            - x: 0.444
              y: 2.083
          - text: Inside documents,
            boundingPolygon:
            - x: 4.25
              y: 2.042
            - x: 5.982
              y: 2.042
            - x: 5.982
              y: 2.236
            - x: 4.25
              y: 2.236
    DocumentTypeName:
      description: Unique user-friendly name for a document type
      example: auto_insurance_quotes_all_carriers
      type: string
    GetAllGoldens:
      type: array
      items:
        $ref: '#/components/schemas/GoldenResponse'
    PostGoldenExtraction:
      type: object
      properties:
        golden:
          type: string
          description: user-friendly name for the reference document
          example: best_scan_doc_num_1234
        configuration:
          type: object
          description: 'SenseML configuration as a JSON object, not stringified JSON, for example, `"configuration": {"fields":[]}`. If you leave out this parameter, then Sensible returns the best-scoring extraction from the configurations in the document type.  If you specify it, Sensible ignores the `environment` parameter.'
          example:
            fields: []
    DocumentName:
      description: Unique user-friendly name for a document
      example: best_scan_form_num_1234
      type: string
    Date:
      type: string
      format: date-time
      description: ISO 8601 date-time.
    Name:
      type: string
      pattern: ^[a-z0-9_]*$
      minLength: 3
      maxLength: 128
      description: User-friendly name
  responses:
    '500':
      description: Internal Server Error
      content:
        text/plain:
          schema:
            title: Sensible encountered an unknown error
            type: string
            example: Sensible encountered an unknown error
    '400':
      description: Bad Request
      content:
        text/plain:
          schema:
            title: Bad Request
            type: string
            example: Either a specific set of messages about fields in the request, or error messages like the following examples - Not available to logged in users To use the asynchronous flow you must have persistence enabled Specified document type does not exist Specified document type ${named type} does not exist No published configurations found for environment ${environment} Specified golden does not exist Specified configuration/version does not exist Specified configuration/version is not valid Must provide the Content-Type header when request body is present Content-Type must be application/json Missing request body or body.document Could not determine the content type of the document Could not determine the content type of the document. Please check that the document was correctly encoded as Base64 This PDF is invalid. If you submitted this PDF using Base64 encoding, please check that the encoding is correct This PDF is password protected. Please resubmit with password protection disabled This PDF is empty This PDF exceeds the maximum dimensions for OCR of 17 x 17 inches This PDF exceeds the maximum size for OCR of 50MB No fingerprints match for this PDF and fingerprint_mode is set to strict Content type of ${found} does not match declared type of ${expected} Document is not present
    '415':
      description: Unsupported Media Type
      content:
        text/plain:
          schema:
            title: Unsupported Media Type
            type: string
            example: Messages related to the file format of the document to extract data from.
    '404':
      description: Not Found
      content:
        text/plain:
          schema:
            title: Not Found
            type: string
    '401':
      description: Not authorized
      content:
        text/plain:
          schema:
            title: Unauthorized
            type: string
            example: Unauthorized
    '204':
      description: No content
      content:
        text/plain:
          schema:
            title: No Content
            type: string
            example: No Content
  parameters:
    documentName:
      name: document-name
      required: true
      in: path
      description: Unique name for a document. Find it in the Sensible app or from the `/document_types/{type-id}}/goldens` endpoint.
      example: best_scan_form_no_1234
      schema:
        $ref: '#/components/schemas/Name'
    documentTypeId:
      name: type-id
      required: true
      in: path
      description: The unique document type identifier in v4 UUID format. Find IDs using the `/document_types` endpoint.
      schema:
        $ref: '#/components/schemas/UniqueId'
    documentTypeName:
      name: type-name
      required: true
      in: path
      description: User-friendly name for a document type
      schema:
        $ref: '#/components/schemas/DocumentTypeName'
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: Bearer token using a Sensible API key. Create keys at https://app.sensible.so/account/.