Kensho Extract API

openapi: 3.0.2
info:
  version: 3.0.0
  title: Kensho Extract API
  description: "Kensho Extract allows users to quickly transform their unstructured documents into a machine-readable format\
    \ that identifies titles, subtitles, paragraphs, tables, and footers detected within the document in their natural reading\
    \ order. \nKensho Extract interprets messy page layout, structuring text into cohesive paragraphs that can be effectively\
    \ analyzed and searched. <br><br> The Kensho Extract API V3 has incorporated changes to how users must call the API.\n\
    Please note there are more required fields in API V3 than API V2 (deprecated). The following fields are *mandatory* for\
    \ `/v3/extractions`: file, document_type, ocr and enhanced_table_extraction. <br><br> API V3 introduces new upload and\
    \ download functionality, allowing the upload of the original document and retrieval of the extracted document output\
    \ via pre-signed URLs. The pre-signed URLs expire after 15 minutes. <br> These new endpoints must be called in the following\
    \ order.\n  - `/v3/extractions/upload-url`\n    - followed by POST'ing the document to the `url` provided in the response\n\
    \  - `/v3/extractions/upload-complete`\n  - `/v3/extractions/download-url/{request_id}`\n    - followed by a calling the\
    \ GET `output_url` provided in the response\n"
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
  schemas:
    Node:
      type: object
      properties:
        type:
          type: string
          enum:
          - DOCUMENT
          - PARAGRAPH
          - H1
          - H2
        content:
          type: string
        children:
          type: array
          items:
            $ref: '#/components/schemas/Node'
    ContentTree:
      type: object
      properties:
        uid:
          type: string
          description: Identifier for a content node that is unique across all nodes in a document
        type:
          type: string
          description: Type of a content node, must be one of document|paragraph|H1|H2|table|table_cell|table_title
        content:
          type: string
          description: Text that corresponds to the content node (optional)
        children:
          type: array
          description: List of child content nodes (recursive)
          items:
            $ref: '#'
      required:
      - uid
      - type
      - content
      - children
    Annotations:
      type: array
      description: Additional data about structure of the document that references text content nodes by their UIDs
      items:
        type: object
        description: Individual annotation
        properties:
          type:
            type: string
            description: Type of an annotation, (e.g. table structure / row header, etc.).
          content_uids:
            type: array
            description: Non-empty list of UIDs of content nodes corresponding to the annotation.
            items:
              type: string
            minItems: 1
          data:
            type: object
        required:
        - type
        - content_uids
    Output:
      type: object
      properties:
        content_tree:
          type: object
          $ref: '#/components/schemas/ContentTree'
        annotations:
          type: object
          $ref: '#/components/schemas/Annotations'
      required:
      - content_tree
      - annotations
paths:
  /v3/extractions:
    post:
      description: Submit a document for extraction
      requestBody:
        content:
          multipart/form-data:
            schema:
              required:
              - file
              - document_type
              - ocr
              - enhanced_table_extraction
              type: object
              properties:
                file:
                  type: string
                  description: The document to extract. The maximum file size is 100MB.
                  format: binary
                document_type:
                  type: string
                  description: 'The output document format. Kensho Extract offers three document types: `hierarchical`, `hierarchical_v2`,
                    and `general`.

                    Please refer to our [overview page](home) for a detailed breakdown of which model will provide the most
                    optimal output for your use case.

                    '
                ocr:
                  type: string
                  description: 'Identifies whether the document is scanned or is a native pdf. This must be `true` or `false`.

                    See the [OCR](ocr) page for more information.

                    '
                enhanced_table_extraction:
                  type: string
                  description: 'Use our newest model to extract data from complex tables more accurately than ever.                     This
                    must be `true` or `false`.

                    '
                figure_extraction:
                  type: string
                  description: 'Use our newest model to extract data from figures.                     This must be `true`
                    or `false`.

                    See the [Figure Extraction](figex) page for more information.

                    '
                include_images:
                  type: string
                  description: 'Whether to return the locations of images. This must be `true` or `false`.

                    '
                include_relations:
                  type: string
                  description: 'Whether to return the relations between items. This must be `true` or `false`.

                    '
                document_id:
                  type: string
                  description: A custom document identifier.
                priority:
                  type: string
                  enum:
                  - low
                  description: The priority level. Anything besides `low` will be considered `high` priority.
                pages:
                  type: string
                  description: 'This specifies the pages to extract. Page numbers start at 1. Format: `1-5,7,11,14-16`.'
                return_absolute_pdf_page_numbers:
                  type: boolean
                  default: false
                  description: 'Whether to return absolute PDF page numbers in the output. Absolute PDF page numbers refer
                    to the original page numbers requested, while relative page numbers start at 0 and increment by 1 for
                    each page requested

                    '
                output_format:
                  type: string
                  description: 'This can be `structured_document`, `structured_document_with_locations`, or `structured_document_with_char_offsets`.
                    It determines if the response format will include location bounding box information.

                    <br>

                    Including this parameter requires making a call to `/v3/extractions/download-url/{request_id}` to obtain
                    a URL for downloading the document from AWS.

                    '
      responses:
        '200':
          description: The request was successfully created.
          content:
            application/json:
              schema:
                type: object
                properties:
                  request_id:
                    type: string
                    format: uuid
        '400':
          description: This can be any combination of the required parameters are not provided, a parameter that is invalid,
            or if a specific pages is requested in the `pages` parameter and that page is not in the document. E.g., requesting
            page 57 for a 10 page document.
        '401':
          description: The authentication token is missing or invalid.
        default:
          description: An unexpected error occurred.
      security:
      - bearerAuth: []
  /v3/extractions/upload-url:
    post:
      summary: Upload URL To Submit A Document For Extraction.
      description: Creates the request and returns a pre-signed upload URL to upload the document for extraction.
      requestBody:
        content:
          multipart/form-data:
            schema:
              required:
              - output_format
              - document_type
              - ocr
              - enhanced_table_extraction
              type: object
              properties:
                output_format:
                  type: string
                  description: This can be `structured_document`, `structured_document_with_locations`, or `structured_document_with_char_offsets`.
                    It determines if the extracted document format will include location bounding box information and character
                    offsets.
                document_type:
                  type: string
                  description: 'The output document format. Kensho Extract offers three document types: `hierarchical`, `hierarchical_v2`,
                    and `general`.

                    Please refer to our [overview page](home) for a detailed breakdown of which model will provide the most
                    optimal output for your use case.

                    '
                ocr:
                  type: string
                  description: 'Identifies whether the document is scanned or is a native pdf. This must be `true` or `false`.

                    See the [OCR](ocr) page for more information.

                    '
                enhanced_table_extraction:
                  type: string
                  description: 'Use our newest model to extract data from complex tables more accurately than ever. This must
                    be `true` or `false`.

                    '
                figure_extraction:
                  type: string
                  description: 'Use our newest model to extract data from figures. This must be `true` or `false`.

                    See the [Figure Extraction](figex) page for more information.

                    '
                document_id:
                  type: string
                  description: A custom document identifier.
                priority:
                  type: string
                  enum:
                  - low
                  description: The priority level. Anything besides `low` will be considered `high` priority.
                pages:
                  type: string
                  description: 'This specifies the pages to extract. Page numbers start at 1. Format: `1-5,7,11,14-16`.'
                num_pages_to_extract:
                  type: integer
                  description: This specifies the total number of pages to extract.
            encoding:
              file:
                contentType: application/pdf
        required: true
      responses:
        '200':
          description: The request was successfully created.
          content:
            application/json:
              schema:
                type: object
                properties:
                  request_id:
                    type: string
                    format: uuid
                  upload_spec:
                    type: object
                    properties:
                      url:
                        type: string
                        description: The URL to POST the document upload to. Returns 204 on success. Refer to the AWS pre-signed
                          URL documentation for detailed information on specific response codes and their meanings.
                      fields:
                        type: object
                        additionalProperties:
                          type: string
                        description: Fields required in the form data of the POST request for uploading the document to the
                          `url`.
        '400':
          description: This can be any combination of the required parameters are not provided or parameter value is invalid.
        '401':
          description: The authentication token is missing or invalid.
        default:
          description: An unexpected error occurred.
      security:
      - bearerAuth: []
  /v3/extractions/upload-complete:
    put:
      summary: Mark The Upload As Complete To Start Extraction
      description: Call this after the document has been uploaded to the pre-signed URL returned by `/v3/extractions/upload-url`.
        The extraction process will not begin until this endpoint is called.
      requestBody:
        content:
          multipart/form-data:
            schema:
              required:
              - request_id
              type: object
              properties:
                request_id:
                  type: uuid
                  description: The request_id for the extraction.
        required: true
      responses:
        '204':
          description: The request was marked as uploaded successfully.
        '400':
          description: The request_id was not provided by the client, or was not created via `/v3/extractions/upload-url`.
        '401':
          description: The authentication token is missing or invalid.
        '404':
          description: The request_id or the uploaded document could not be found.
        default:
          description: An unexpected error occurred.
      security:
      - bearerAuth: []
  /v3/extractions/{request_id}:
    get:
      description: Retrieve the extracted document
      parameters:
      - name: request_id
        in: path
        description: request uuid
        required: true
        schema:
          type: string
          format: uuid
      - name: output_format
        in: query
        description: This can be `structured_document`, `structured_document_with_locations`, or `structured_document_with_char_offsets`.
          It determines if the response format will include location bounding box information.
        required: false
        schema:
          type: string
          default: structured_document_with_locations
      responses:
        '200':
          description: successful operation
          content:
            application/json:
              schema:
                type: object
                properties:
                  status:
                    type: string
                    enum:
                    - success
                    - failed
                    - pending
                  error:
                    type: string
                  output:
                    type: object
                    $ref: '#/components/schemas/Output'
                  metadata:
                    type: object
                    properties: {}
        '400':
          description: 'The request_id was not provided by the client, or output_format was specified when the request was
            created.

            <br>

            If output_format was specified when the request was created, /v3/extractions/download-url/{request_id} must be
            called to get a pre-signed URL to retrieve the extracted output.

            '
        '401':
          description: The authentication token is missing or invalid.
        '404':
          description: The request_id could not be found.
        '405':
          description: The request is on a different API version than the POST request that created the request.
        default:
          description: An unexpected error occurred.
      security:
      - bearerAuth: []
  /v3/extractions/download-url/{request_id}:
    get:
      summary: Retrieve The Extracted Document's Download URL
      description: GET the `output_url` in the response to download the extracted document.
      parameters:
      - name: request_id
        in: path
        description: request uuid
        required: true
        schema:
          type: string
          format: uuid
      responses:
        '200':
          description: successful operation
          content:
            application/json:
              schema:
                type: object
                properties:
                  status:
                    type: string
                    enum:
                    - success
                    - failed
                    - pending
                    - awaiting_document_upload
                    - awaiting_document_upload_complete_notification
                  error:
                    type: string
                  output_url:
                    type: string
                  metadata:
                    type: object
                    properties: {}
        '400':
          description: The request_id was not provided by the client, or output_format was not specified when the request
            was created.
        '401':
          description: The authentication token is missing or invalid.
        '404':
          description: The request_id could not be found.
        '405':
          description: The request is on a different API version than the POST request that created the request, the document
            has not been uploaded, or /v3/extractions/upload-complete has not been called to marked the upload complete.
        default:
          description: An unexpected error occurred.
      security:
      - bearerAuth: []
servers:
- url: https://extract.kensho.com/