mammoth-io Datasets from PDF API

openapi: 3.2.0
info:
  title: Mammoth Io Datasets from PDF API
  version: 0.1.0
  contact:
    name: Mammoth Analytics
    url: https://mammoth.io
    email: support@mammoth.io
  description: 'Operations tagged Datasets from PDF across 2 of this provider''s published API definitions: app.mammoth.io-openapi.json, mammoth-io-openapi.json. Each path carries the servers of the definition it was published in.'
servers:
- url: /api/v2
security:
- bearerAuth: []
- apiKey: []
  apiSecret: []
  workspaceId: []
tags:
- name: Datasets from PDF
paths:
  /workspaces/{workspace_id}/projects/{project_id}/datasets-from-pdf:
    post:
      tags:
      - Datasets from PDF
      summary: Create datasets from Selected Tables of PDF
      description: Takes a file ID and a list of table indices and creates a corresponding dataset in the project
      operationId: CreateDatasetFromPdf
      parameters:
      - name: workspace_id
        in: path
        schema:
          type: integer
          minimum: 1.0
          title: Workspace ID
          description: Workspace refers to a collection of projects. Workspace ID is unique identifier for workspace.
          examples:
          - 4
        description: Workspace refers to a collection of projects. Workspace ID is unique identifier for workspace.
        required: true
        deprecated: false
        examples:
          workspace_id-example-1:
            summary: Sample workspace ID
            value: 4
      - name: project_id
        in: path
        schema:
          type: integer
          minimum: 1.0
          title: Project ID
          description: Project ID of the workspace
          examples:
          - 4
        description: Project ID of the workspace
        required: true
        deprecated: false
        examples:
          project_id-example-1:
            summary: Sample project ID
            value: 4
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/PDFTableInput'
        required: true
      responses:
        '201':
          description: Document created, URL follows
          headers: {}
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/JobResponse'
        '400':
          description: Bad request syntax or unsupported method
          content:
            application/json:
              schema:
                oneOf:
                - properties:
                    status_code:
                      type: integer
                    detail:
                      type: string
                    extra:
                      additionalProperties: {}
                      type:
                      - 'null'
                      - object
                      - array
                  type: object
                  required:
                  - detail
                  - status_code
                  description: Client Error
                  examples:
                  - status_code: 400
                    detail: Bad Request
                    extra: {}
                - properties:
                    status_code:
                      type: integer
                    detail:
                      type: string
                    extra:
                      additionalProperties: {}
                      type:
                      - 'null'
                      - object
                      - array
                  type: object
                  required:
                  - detail
                  - status_code
                  description: Validation Exception
                  examples:
                  - status_code: 400
                    detail: Bad Request
                    extra: {}
        '403':
          description: Request forbidden -- authorization will not help
          content:
            application/json:
              schema:
                properties:
                  status_code:
                    type: integer
                  detail:
                    type: string
                  extra:
                    additionalProperties: {}
                    type:
                    - 'null'
                    - object
                    - array
                type: object
                required:
                - detail
                - status_code
                description: Authorization Exception
                examples:
                - status_code: 403
                  detail: Forbidden
                  extra: {}
        '200':
          description: Datasets will be successfully created from the table list
          content:
            application/json:
              schema:
                type: object
        '401':
          description: Authorization error - invalid or missing credentials
      deprecated: false
    servers:
    - url: /api/v2
components:
  schemas:
    JobSchema:
      properties:
        id:
          type: integer
          minimum: 0.0
          title: Job id
          examples:
          - value:
              id: 10
        status:
          type: string
          enum:
          - success
          - failure
          - processing
          - error
          title: Job status
          description: Job status can be success, failure or processing
          examples:
          - value:
              status: success
        response:
          oneOf:
          - type: object
          - type: array
          description: Result of async task is stored in response
          examples:
          - value:
              response:
                object: some object
        last_updated_at:
          type: string
          format: date-time
          title: Job last updated at
          description: Job last updated at is the time when Job status was last updated
          examples:
          - value:
              last_updated_at: '2021-08-10T10:00:00'
        created_at:
          type: string
          format: date-time
          title: Job created at
          description: Create at is time when async task was created
          examples:
          - value:
              created_at: '2021-08-10T10:00:00'
        path:
          type: string
          title: Job path
          description: API request path of the Job operation
          examples:
          - value:
              path: /api/v2/dataviews/1
        operation:
          type: string
          title: Job operation
          description: Operation is async task name which Job is tracking
          examples:
          - value:
              operation: post_modification_pipeline_execution
      type: object
      required:
      - created_at
      - id
      - last_updated_at
      - operation
      - path
      - response
      - status
      title: JobSchema
    PDFTableInput:
      properties:
        file_object_id:
          type: integer
          title: Mammoth File Object ID
          description: Internal ID of the file object
        file_id:
          oneOf:
          - type: string
          - type: 'null'
          title: PDF File ID
          description: Unique identifier for the uploaded PDF file in pdf2csv
        file_name:
          type: string
          title: File Name
          description: Original name of the uploaded PDF file
        table_list:
          oneOf:
          - items:
              type: integer
            type: array
          - type: 'null'
          title: Table List
          description: Indices of the tables to extract and convert into datasets
        delete_file_after_extract:
          type: boolean
          title: Delete File After Extraction
          description: Whether to delete the file from storage after table extraction is complete
          default: false
        is_preview_needed:
          oneOf:
          - type: boolean
          - type: 'null'
          title: Preview Needed
          description: Flag indicating whether a preview is required before dataset creation
        user_instruction:
          oneOf:
          - type: string
          - type: 'null'
          title: User Instruction
          description: User-provided instruction for custom extraction logic.
        add_to:
          oneOf:
          - additionalProperties:
              type: integer
            type: object
          - type: 'null'
          title: Add To
          description: Table number -> an existing dataset in this project. Those tables are added to that dataset as a new batch instead of becoming datasets of their own.
          examples:
          - value:
              '1': 11
              '2': 12
      type: object
      required:
      - file_name
      - file_object_id
      title: PDFTableInput
      description: Request body containing the file ID and list of table indices to create datasets
      examples:
      - file_object_id: 123
        file_id: abc12345xyz
        file_name: sample_document.pdf
        table_list:
        - 0
        - 2
        - 4
        delete_file_after_extract: false
        is_preview_needed: null
        user_instruction: null
        add_to: null
    JobResponse:
      properties:
        job:
          $ref: '#/components/schemas/JobSchema'
      type: object
      required:
      - job
      title: JobResponse
  securitySchemes:
    bearerAuth:
      type: http
      description: 'Primary credential. Authorization: Bearer mm_<token>. The token is issued server-side and shown once at creation.'
      scheme: bearer
    apiKey:
      type: apiKey
      description: Deprecated — use bearerAuth.
      name: X-API-KEY
      in: header
    apiSecret:
      type: apiKey
      description: Deprecated — use bearerAuth.
      name: X-API-SECRET
      in: header
    workspaceId:
      type: apiKey
      description: Required with X-API-KEY and X-API-SECRET. Deprecated with them — use bearerAuth.
      name: X-WORKSPACE-ID
      in: header
x-refined-from:
- app.mammoth.io-openapi.json
- mammoth-io-openapi.json