Doctly Extractors API

openapi: 3.2.0
info:
  title: Doctly Documents Extractors API
  description: Doctly converts PDF, DOCX, and image documents into clean Markdown or structured JSON. Submit a document for asynchronous processing, then poll the document by id (or receive a webhook callback) to retrieve the signed output_file_url. Custom extractors run structured-data extraction against a document. All requests authenticate with a Bearer API key.
  termsOfService: https://doctly.ai/terms
  contact:
    name: Doctly Support
    url: https://docs.doctly.ai
  version: '1.0'
servers:
- url: https://api.doctly.ai/api/v1
security:
- bearerAuth: []
tags:
- name: Extractors
  description: Manage and run custom structured-data extractors.
paths:
  /e:
    get:
      operationId: listExtractors
      tags:
      - Extractors
      summary: List extractors
      description: Retrieve a list of active extractors for your account.
      parameters:
      - name: skip
        in: query
        schema:
          type: integer
          default: 0
        description: Pagination offset.
      - name: limit
        in: query
        schema:
          type: integer
          default: 100
        description: Records per page.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractorsPublic'
        '401':
          description: Unauthorized
  /e/{slug}:
    post:
      operationId: runExtractor
      tags:
      - Extractors
      summary: Run an extractor
      description: Execute an extractor (by slug) against a document file or url to produce structured output asynchronously. Returns a document record; poll GET /documents/{id} or supply a callback_url.
      parameters:
      - name: slug
        in: path
        required: true
        schema:
          type: string
        description: Extractor slug identifier.
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              $ref: '#/components/schemas/RunExtractorRequest'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocumentCreateExtractionResponse'
        '404':
          description: Not Found
  /e/{extractor_id}:
    get:
      operationId: getExtractor
      tags:
      - Extractors
      summary: Get an extractor
      description: Retrieve details of a specific extractor.
      parameters:
      - name: extractor_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
        description: Extractor ID.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractorPublic'
        '404':
          description: Not Found
    put:
      operationId: updateExtractor
      tags:
      - Extractors
      summary: Update an extractor
      description: Update an existing extractor's name or slug.
      parameters:
      - name: extractor_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
        description: Extractor ID.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractorUpdate'
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractorPublic'
        '404':
          description: Not Found
    delete:
      operationId: deleteExtractor
      tags:
      - Extractors
      summary: Delete an extractor
      description: Delete an extractor (soft delete).
      parameters:
      - name: extractor_id
        in: path
        required: true
        schema:
          type: string
          format: uuid
        description: Extractor ID.
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Message'
        '404':
          description: Not Found
components:
  schemas:
    ExtractorPublic:
      type: object
      properties:
        id:
          type: string
          format: uuid
        name:
          type: string
        slug:
          type: string
        description:
          type:
          - string
          - 'null'
        cost_type:
          $ref: '#/components/schemas/CostType'
        cost_credits:
          type: integer
    DocumentCreateResponse:
      type: object
      properties:
        id:
          type: string
          format: uuid
        file_name:
          type: string
        file_size:
          type: integer
          description: Size in bytes.
        page_count:
          type:
          - integer
          - 'null'
          description: Number of pages; null until processed.
        status:
          $ref: '#/components/schemas/DocumentStatus'
        accuracy:
          $ref: '#/components/schemas/AccuracyLevel'
        extractor_id:
          type:
          - string
          - 'null'
          format: uuid
        created_at:
          type: string
          format: date-time
    ExtractorUpdate:
      type: object
      properties:
        name:
          type: string
          maxLength: 255
        slug:
          type: string
          minLength: 3
          maxLength: 100
    RunExtractorRequest:
      type: object
      properties:
        file:
          type: string
          format: binary
          description: Document file to process.
        url:
          type: string
          format: uri
          description: Alternative to file - a remote document URL to fetch and process.
        callback_url:
          type: string
          format: uri
          description: Webhook URL notified when extraction completes.
    CostType:
      type: string
      enum:
      - PER_PAGE
      - PER_DOCUMENT
      description: How an extractor's credits are charged.
    DocumentCreateExtractionResponse:
      allOf:
      - $ref: '#/components/schemas/DocumentCreateResponse'
      - type: object
        properties:
          extractor_id:
            type: string
            format: uuid
          extractor:
            $ref: '#/components/schemas/ExtractorPublic'
    AccuracyLevel:
      type: string
      enum:
      - lite
      - ultra
      default: lite
      description: Conversion accuracy. lite is faster (default); ultra generates multiple versions per page and selects the most accurate, but takes longer.
    Message:
      type: object
      properties:
        message:
          type: string
    DocumentStatus:
      type: string
      enum:
      - PENDING
      - PROCESSING
      - COMPLETED
      - FAILED
      - EXPIRED
      description: Lifecycle status of a document processing job.
    ExtractorsPublic:
      type: object
      properties:
        data:
          type: array
          items:
            $ref: '#/components/schemas/ExtractorPublic'
        count:
          type: integer
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Bearer API key, sent as `Authorization: Bearer YOUR_API_KEY`.'