Affinda Document API - Splitting API

openapi: 3.0.3
info:
  title: Affinda Annotations Add x-hidden to endpoints Document API - Splitting API
  version: 3.0.0
  description: Affinda Annotations API — subset of the Affinda v3 Document Processing API.
servers:
- url: https://{region}.affinda.com
  description: 'Select the correct server for your instance: api (AUS/Global), api.us1 (US), or api.eu1 (EU).'
  variables:
    region:
      default: api
      description: The instance region. Use 'api' for AUS/Global, 'api.us1' for US, or 'api.eu1' for EU. You can find your region in the Affinda web app URL.
      enum:
      - api
      - api.eu1
      - api.us1
      x-ms-parameter-location: client
security:
- ApiKeyAuth: []
tags:
- name: Document API - Splitting
paths:
  /v3/document_splitters:
    get:
      x-hidden: true
      tags:
      - Document API - Splitting
      summary: Get list of all document splitters
      operationId: getAllDocumentSplitters
      description: Returns all the document splitters visible to the user.
      deprecated: true
      parameters:
      - $ref: '#/components/parameters/offsetParam'
      - $ref: '#/components/parameters/limitParam'
      - in: query
        name: organization
        schema:
          $ref: '#/components/schemas/Organization_properties-identifier'
        description: Filter by organization.
      - in: query
        name: include_public
        schema:
          type: boolean
        description: Allows you to include public splitters in the response when you're filtering by organization.
      responses:
        '200':
          description: All documents splitters
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/DocumentSplitter'
        '400':
          $ref: '#/components/responses/400Error'
        '401':
          $ref: '#/components/responses/401Error'
        default:
          $ref: '#/components/responses/DefaultError'
  /v3/document_splitters/{identifier}:
    get:
      x-hidden: true
      tags:
      - Document API - Splitting
      summary: Get specific document splitter
      operationId: getDocumentSplitter
      description: Return a specific document splitter.
      deprecated: true
      parameters:
      - in: path
        required: true
        name: identifier
        description: Document splitter's identifier
        schema:
          $ref: '#/components/schemas/DocumentSplitter_properties-identifier'
      responses:
        '200':
          description: Successfully retrieved document splitter.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocumentSplitter'
        '400':
          $ref: '#/components/responses/400Error'
        '401':
          $ref: '#/components/responses/401Error'
        default:
          $ref: '#/components/responses/DefaultError'
  /v3/validate/{identifier}/split:
    post:
      x-hidden: true
      tags:
      - Document API - Splitting
      summary: Split pages of a document
      operationId: editDocumentPages
      description: 'Split / merge / rotate / delete pages of a document.

        Documents with multiple pages can be splitted into multiple documents, or merged into one document.

        Each page can also be rotated. Edit operations will trigger re-parsing of the documents involved.

        '
      deprecated: true
      parameters:
      - in: path
        required: true
        name: identifier
        description: Document's identifier
        schema:
          $ref: '#/components/schemas/DocumentMeta_properties-identifier'
      requestBody:
        description: Describe how the pages should be edited
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DocumentEditRequest'
      responses:
        '200':
          description: Successfully edited the document and re-parsing is underway.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocumentEditResponse'
        '400':
          $ref: '#/components/responses/400Error'
        '401':
          $ref: '#/components/responses/401Error'
        default:
          $ref: '#/components/responses/DefaultError'
components:
  schemas:
    RegionBias:
      type: object
      nullable: true
      properties:
        country:
          type: string
          nullable: true
          description: A single alpha-2 country code (e.g. AU) used by google geocoding service
        countries:
          type: array
          items:
            type: string
          nullable: true
          description: A list of alpha-2 country codes used by Pelias
        squareCoordinates:
          type: array
          items:
            type: number
          nullable: true
          description: A list of coordinates used by Pelias in the shape of [min_lon, min_lat, max_lon, max_lat]
        strict:
          type: boolean
          description: 'If true, the location must be within the region, as opposed to prefering locations within the region.

            Default to false.

            '
          example: true
    DocumentSplit:
      type: object
      required:
      - pages
      description: Describe a split of a document.
      properties:
        identifier:
          allOf:
          - $ref: '#/components/schemas/DocumentMeta_properties-identifier'
          - description: Specify document identifier in the first split to signal that this is the root document where other splits are splitted from. Don't specify document identifier in subsequent splits.
        pages:
          type: array
          items:
            $ref: '#/components/schemas/DocumentSplitPage'
    Meta:
      type: object
      properties:
        identifier:
          type: string
          description: Unique identifier for the document
        customIdentifier:
          type: string
          nullable: true
          description: Optional identifier for the document that you can set to track the document in the Affinda system.  Is not required to be unique.
          example: 46ab8b02-0e5b-420c-877c-8b678d46a834
        fileName:
          $ref: '#/components/schemas/FileName'
        ready:
          type: boolean
          nullable: false
          example: true
          description: If true, the document has finished processing. Particularly useful if an endpoint request specified wait=False, when polling use this variable to determine when to stop polling
        readyDt:
          type: string
          format: date-time
          example: '2020-12-10T01:43:32.276724Z'
          nullable: true
          description: The datetime when the document was ready
        failed:
          type: boolean
          nullable: false
          example: false
          description: If true, some exception was raised during processing. Check the 'error' field of the main return object.
        expiryTime:
          $ref: '#/components/schemas/ExpiryTime'
        language:
          type: string
          nullable: true
          example: en
          description: The document's language.
        pdf:
          type: string
          nullable: true
          example: https://affinda-api.s3.amazonaws.com/media/documents/Document.pdf?AWSAccessKeyId=KEY&Signature=SIG&Expires=1663302062
          description: The URL to the document's pdf (if the uploaded document is not already pdf, it's converted to pdf as part of the parsing process).
        parentDocument:
          type: object
          nullable: true
          description: If this document is part of a splitted document, this attribute points to the original document that this document is splitted from.
          properties:
            identifier:
              $ref: '#/components/schemas/Meta_properties-identifier'
        childDocuments:
          type: array
          description: If this document has been splitted into a number of child documents, this attribute points to those child documents.
          items:
            type: object
            properties:
              identifier:
                $ref: '#/components/schemas/Meta_properties-identifier'
        pages:
          type: array
          items:
            $ref: '#/components/schemas/PageMeta'
          description: The document's pages.
        isVerified:
          type: boolean
          nullable: false
          example: false
          description: This is true if the 'confirm' button has been clicked in the Affinda validation tool
        reviewUrl:
          type: string
          nullable: true
          example: https://app.affinda.com/review/XJ5kK123?signature=12345
          description: Signed URL (valid for 60 minutes) to access the validation tool.  Not applicable for documents types such a resumes.
        ocrConfidence:
          type: number
          nullable: true
          example: 0.97
          description: The overall confidence in the conversion of image to text.  (only applicable for images or PDF documents without a text layer)
        createdDt:
          type: string
          format: date-time
        documentType:
          type: string
          example: resume
        regionBias:
          $ref: '#/components/schemas/RegionBias'
        isOcrd:
          type: boolean
    RequestError:
      type: object
      additionalProperties: false
      required:
      - type
      - errors
      properties:
        type:
          type: string
          example: validation_error
        errors:
          type: array
          items:
            type: object
            required:
            - attr
            - code
            - detail
            properties:
              attr:
                type: string
                nullable: true
                example: non_field_errors
              code:
                type: string
                example: unique
              detail:
                type: string
                example: This index name has already been used
    DocumentMeta_properties-identifier:
      type: string
      description: Unique identifier for the document
    DocumentSplitPage:
      type: object
      required:
      - id
      description: List the pages within this split. Not including a page here will signal that the page should be deleted.
      properties:
        id:
          type: integer
          description: Page's ID
          minimum: 1
        rotation:
          type: integer
          minimum: -360
          maximum: 360
          description: Specify a degree of rotation if you want to rotate a page. Possitive number for clockwise rotation, and negative number for counter-clockwise rotation.
          example: 90
    DocumentSplitter_properties-identifier:
      type: string
      description: Uniquely identify a document splitter.
      example: NqIvMvZl
    DocumentEditRequest:
      type: object
      required:
      - splits
      properties:
        splits:
          type: array
          items:
            $ref: '#/components/schemas/DocumentSplit'
    DocumentSplitter:
      type: object
      required:
      - identifier
      - name
      - type
      - organization
      - extractor
      - llmHint
      properties:
        identifier:
          type: string
          description: Uniquely identify a document splitter.
          example: NqIvMvZl
        name:
          type: string
        type:
          $ref: '#/components/schemas/DocumentSplitterType'
        organization:
          $ref: '#/components/schemas/Organization_properties-identifier'
          nullable: true
        extractor:
          $ref: '#/components/schemas/Extractor_properties-identifier'
          nullable: true
        llmHint:
          type: string
          nullable: true
          description: The hint about when to split which is passed into the LLM prompt.
    Organization_properties-identifier:
      type: string
      description: Uniquely identify an organization.
      example: mEFayXdO
    ExpiryTime:
      type: string
      nullable: true
      format: date-time
      description: The date/time in ISO-8601 format when the document will be automatically deleted.  Defaults to no expiry.
    DocumentSplitterType:
      type: string
      description: The different types of document splitters
      enum:
      - llm
      - llm_v2
      - extractor
      - keyword
    FileName:
      type: string
      nullable: true
      description: Optional filename of the file
      example: Document.pdf
    Meta_properties-identifier:
      type: string
      description: Unique identifier for the document
    PageMeta:
      type: object
      required:
      - id
      - pageIndex
      - image
      - width
      - height
      - rotation
      properties:
        id:
          type: integer
          minimum: 1
        pageIndex:
          type: integer
          example: 0
          minimum: 0
          description: Page number within the document, starts from 0.
        image:
          type: string
          nullable: true
          example: https://affinda-api.s3.amazonaws.com/media/pages/Page.png?AWSAccessKeyId=KEY&Signature=SIG&Expires=1663302062
          description: The URL to the image of the page.
        imageTranslated:
          type: string
          nullable: true
          example: https://affinda-api.s3.amazonaws.com/media/pages/PageTranslated.png?AWSAccessKeyId=KEY&Signature=SIG&Expires=1663302062
          description: The URL to the translated image of the page.
        height:
          type: number
          example: 700
          description: Height of the page's image in px.
        width:
          type: number
          example: 500
          description: Width of the page's image in px.
        rotation:
          type: integer
          example: 90
          minimum: -360
          maximum: 360
          description: The degree of rotation applied to the page. Greater than 0 indicates clockwise rotation. Less than 0 indicates counter-clockwise rotation.
    Extractor_properties-identifier:
      type: string
      description: Uniquely identify an extractor.
      example: resume
    DocumentEditResponse:
      type: array
      items:
        $ref: '#/components/schemas/Meta'
  responses:
    DefaultError:
      description: UnexpectedError
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/RequestError'
      x-ms-error-response: true
    400Error:
      description: Bad request. If it is a validation error will contain a list of each invalid field
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/RequestError'
      x-ms-error-response: true
    401Error:
      description: Authorisation error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/RequestError'
      x-ms-error-response: true
  parameters:
    limitParam:
      in: query
      name: limit
      required: false
      schema:
        type: integer
        minimum: 1
        maximum: 100
        example: 20
      description: The numbers of results to return.
      x-ms-parameter-location: method
    offsetParam:
      in: query
      name: offset
      required: false
      schema:
        type: integer
        minimum: 0
        example: 0
      description: The number of documents to skip before starting to collect the result set.
      x-ms-parameter-location: method
  securitySchemes:
    ApiKeyAuth:
      type: http
      scheme: bearer
      description: 'Basic authentication using an API key, e.g. `{Authorization: Bearer aff_0bb4fbdf97b7e4111ff6c0015471094155f91}`.

        You can find your API key within the Settings page of the [Affinda web app](https://app.affinda.com/). You can obtain an API key by [signing up for a free trial](https://app.affinda.com/auth/register).'