Zuva Field Extraction API

openapi: 3.0.1
info:
  title: Zuva DocAI Classification Field Extraction API
  description: The Zuva DocAI API is a RESTful contract and document AI API for extracting structured data from unstructured documents. It provides asynchronous file submission, OCR, field extraction across 1,400+ pre-built fields, multi-level document classification across 220+ document types, language detection, and a searchable fields catalog. All requests are authenticated with a Bearer API token and served from regional hosts (US and EU).
  termsOfService: https://zuva.ai/terms/zuva/
  contact:
    name: Zuva Support
    url: https://zuva.ai/
  version: '2.0'
servers:
- url: https://{region}.app.zuva.ai/api/v2
  description: Zuva DocAI regional API server
  variables:
    region:
      default: us
      description: Deployment region for the Zuva DocAI API.
      enum:
      - us
      - eu
security:
- bearerAuth: []
tags:
- name: Field Extraction
  description: Extract field values from documents.
paths:
  /extraction:
    post:
      operationId: createExtraction
      tags:
      - Field Extraction
      summary: Create field extraction requests.
      description: Submit one or more files and field IDs to extract. Accepts up to 100 file IDs and 100 field IDs per request. Returns one request per file.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractionRequest'
      responses:
        '202':
          description: Extraction requests accepted and queued.
          content:
            application/json:
              schema:
                type: object
                properties:
                  file_ids:
                    type: array
                    items:
                      type: string
                  field_ids:
                    type: array
                    items:
                      type: string
                  status:
                    type: string
  /extractions:
    get:
      operationId: getExtractions
      tags:
      - Field Extraction
      summary: Query multiple extraction requests.
      parameters:
      - name: request_id
        in: query
        required: false
        description: Comma-separated list of extraction request IDs.
        schema:
          type: string
      responses:
        '200':
          description: Extraction request statuses.
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/Request'
  /extraction/{request_id}:
    get:
      operationId: getExtraction
      tags:
      - Field Extraction
      summary: Retrieve an extraction request status.
      parameters:
      - $ref: '#/components/parameters/RequestId'
      responses:
        '200':
          description: Extraction request status.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Request'
  /extraction/{request_id}/results/text:
    get:
      operationId: getExtractionResultsText
      tags:
      - Field Extraction
      summary: Retrieve extraction text results.
      description: Fetch extracted field values with text spans and locations.
      parameters:
      - $ref: '#/components/parameters/RequestId'
      responses:
        '200':
          description: Extraction results.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionResults'
components:
  schemas:
    ExtractionRequest:
      type: object
      required:
      - file_ids
      - field_ids
      properties:
        file_ids:
          type: array
          description: Up to 100 file IDs.
          items:
            type: string
        field_ids:
          type: array
          description: Up to 100 field IDs.
          items:
            type: string
        options:
          type: object
          properties:
            field_heuristics:
              type: array
              items:
                type: object
    ExtractionResults:
      type: object
      properties:
        request_id:
          type: string
        file_id:
          type: string
        results:
          type: array
          items:
            type: object
            properties:
              field_id:
                type: string
              text:
                type: string
              spans:
                type: array
                items:
                  type: object
                  properties:
                    start:
                      type: integer
                    end:
                      type: integer
    Request:
      type: object
      properties:
        request_id:
          type: string
        file_id:
          type: string
        field_ids:
          type: array
          items:
            type: string
        status:
          type: string
          enum:
          - queued
          - processing
          - complete
          - failed
  parameters:
    RequestId:
      name: request_id
      in: path
      required: true
      description: The unique identifier of an asynchronous request.
      schema:
        type: string
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: 'Zuva API token passed in the Authorization header as `Authorization: Bearer <token>`.'