UiPath Extraction API

Extract structured data fields from documents

Documentation

Specifications

Schemas & Data

📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/uipath-orchestrator-schema.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/orchestrator-job-schema.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/orchestrator-robot-schema.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/orchestrator-queue-definition-schema.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/orchestrator-queue-item-schema.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/orchestrator-asset-schema.json
📊
JSONStructure
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-structure/orchestrator-job-structure.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/automation-hub-automation-schema.json
📊
JSONStructure
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-structure/automation-hub-automation-structure.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/uipath-document-understanding-schema.json
📊
JSONStructure
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-structure/document-understanding-digitization-result-structure.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/data-service-entity-record-schema.json
📊
JSONStructure
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-structure/data-service-entity-record-structure.json
📊
JSONStructure
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-structure/platform-management-user-structure.json
📊
JSONSchema
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-schema/test-manager-test-case-schema.json
📊
JSONStructure
https://raw.githubusercontent.com/api-evangelist/uipath/refs/heads/main/json-structure/test-manager-test-case-structure.json

Other Resources

OpenAPI Specification

uipath-extraction-api-openapi.yml Raw ↑
openapi: 3.1.0
info:
  title: UiPath Automation Hub Alerts Extraction API
  description: The UiPath Automation Hub API provides access to the automation pipeline and idea management platform, allowing developers to programmatically create, retrieve, and manage automation ideas, projects, and pipeline data. The API is accessible at the tenant-scoped endpoint https://cloud.uipath.com/{orgName}/{tenantName}/automationhub_/api/v1/ and uses token-based authentication generated from the Automation Hub Admin Console. It is designed for organizations building Center of Excellence workflows, integrating Automation Hub data with external tools, or automating pipeline governance processes. A Postman collection and Swagger interface are available for exploring and testing endpoints.
  version: '1.0'
  contact:
    name: UiPath Support
    url: https://support.uipath.com
  termsOfService: https://www.uipath.com/legal/terms-of-use
servers:
- url: https://cloud.uipath.com/{orgName}/{tenantName}/automationhub_/api/v1
  description: UiPath Automation Cloud Automation Hub
  variables:
    orgName:
      default: your-org
      description: The name of your UiPath organization
    tenantName:
      default: your-tenant
      description: The name of your UiPath tenant
security:
- apiKeyAuth: []
tags:
- name: Extraction
  description: Extract structured data fields from documents
paths:
  /projects/{projectId}/extraction/start:
    post:
      operationId: extractDocumentAsync
      summary: UiPath Start Asynchronous Document Extraction
      description: Submits a previously digitized document for asynchronous data extraction. The extractors to apply and the document type must be specified in the request body. Returns a requestId to poll for results. Results are retained for 24 hours. Use GET /extraction/{requestId}/result to retrieve extracted field values once processing completes.
      tags:
      - Extraction
      parameters:
      - $ref: '#/components/parameters/projectId'
        example: example-value
      - name: api-version
        in: query
        required: false
        description: API version to use for this request
        schema:
          type: string
          default: '1'
        example: 1.0.0
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ExtractionRequest'
            examples:
              extractDocumentAsyncRequestExample:
                summary: Default extractDocumentAsync request
                x-microcks-default: true
                value:
                  documentId: example-value
                  documentTypeId: example-value
                  extractorsOptions:
                  - {}
      responses:
        '200':
          description: Extraction job started; use the returned requestId to poll for results
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AsyncJobStartResponse'
              examples:
                extractDocumentAsync200Example:
                  summary: Default extractDocumentAsync 200 response
                  x-microcks-default: true
                  value:
                    requestId: example-value
                    status: NotStarted
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
  /projects/{projectId}/extraction/{requestId}/result:
    get:
      operationId: getExtractionResult
      summary: UiPath Get Asynchronous Extraction Result
      description: Retrieves the result of an asynchronous extraction request by its requestId. The job status can be NotStarted, Running, Failed, or Succeeded. Poll this endpoint until the status is Succeeded or Failed. Returns extracted field values with associated confidence scores. Results are available for 24 hours from the time the job completed.
      tags:
      - Extraction
      parameters:
      - $ref: '#/components/parameters/projectId'
        example: example-value
      - $ref: '#/components/parameters/requestId'
        example: example-value
      - name: api-version
        in: query
        required: false
        description: API version to use for this request
        schema:
          type: string
          default: '1'
        example: 1.0.0
      responses:
        '200':
          description: Extraction result or current job status
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ExtractionResult'
              examples:
                getExtractionResult200Example:
                  summary: Default getExtractionResult 200 response
                  x-microcks-default: true
                  value:
                    requestId: example-value
                    status: NotStarted
                    result:
                      documentId: example-value
                      extractionResult: {}
        '401':
          $ref: '#/components/responses/Unauthorized'
        '404':
          $ref: '#/components/responses/NotFound'
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
components:
  schemas:
    FieldValue:
      type: object
      description: The extracted value with confidence and source reference
      properties:
        Value:
          description: Extracted value, which may be a string, number, or object depending on field type
          example: example-value
        Confidence:
          type: number
          format: float
          minimum: 0
          maximum: 1
          description: Confidence score for the extracted value (0.0 to 1.0)
          example: 1.0
        OcrConfidence:
          type: number
          format: float
          minimum: 0
          maximum: 1
          description: OCR confidence score for the text underlying this value
          example: 1.0
        TextType:
          type: string
          enum:
          - Printed
          - Handwritten
          description: Whether the source text was printed or handwritten
          example: Printed
    ExtractionResultData:
      type: object
      description: Structured extraction result containing field values and confidence scores
      properties:
        ResultsVersion:
          type: integer
          description: Version of the extraction results format
          example: 1.0.0
        DocumentId:
          type: string
          description: Document identifier of the extracted document
          example: abc123
        Fields:
          type: array
          items:
            $ref: '#/components/schemas/ExtractedField'
          description: List of extracted field values
          example: []
    ExtractorOption:
      type: object
      description: Configuration for applying a specific extractor
      required:
      - extractorId
      properties:
        extractorId:
          type: string
          description: Unique identifier of the extractor to apply
          example: abc123
    AsyncJobStartResponse:
      type: object
      description: Response returned when an asynchronous processing job is started
      properties:
        requestId:
          type: string
          description: Unique identifier of the asynchronous job. Use this to poll for results.
          example: abc123
        status:
          type: string
          enum:
          - NotStarted
          - Running
          - Failed
          - Succeeded
          description: Initial status of the asynchronous job
          example: NotStarted
    ExtractedField:
      type: object
      description: A single extracted field with its value and confidence metadata
      properties:
        FieldId:
          type: string
          description: Identifier of the extracted field as defined in the extractor schema
          example: abc123
        FieldName:
          type: string
          description: Display name of the extracted field
          example: Example Name
        IsMissing:
          type: boolean
          description: Whether the field was not found in the document
          example: true
        Value:
          $ref: '#/components/schemas/FieldValue'
    ErrorResponse:
      type: object
      description: Standard error response body
      properties:
        message:
          type: string
          description: Human-readable error message
          example: example-value
        errorCode:
          type: string
          description: Error code identifier
          example: example-value
        traceId:
          type: string
          description: Trace identifier for support and debugging
          example: abc123
    ExtractionResult:
      type: object
      description: Result of an asynchronous extraction job
      properties:
        requestId:
          type: string
          description: Unique identifier of the extraction job
          example: abc123
        status:
          type: string
          enum:
          - NotStarted
          - Running
          - Failed
          - Succeeded
          description: Current status of the extraction job
          example: NotStarted
        result:
          type: object
          description: Extraction output, populated when status is Succeeded
          properties:
            documentId:
              type: string
              description: Document ID from which data was extracted
            extractionResult:
              $ref: '#/components/schemas/ExtractionResultData'
          example: example-value
    ExtractionRequest:
      type: object
      description: Request payload for extracting data from a previously digitized document
      required:
      - documentId
      - extractorsOptions
      properties:
        documentId:
          type: string
          description: Document ID returned by the digitization endpoint
          example: abc123
        documentTypeId:
          type: string
          description: Document type identifier to guide extraction
          example: abc123
        extractorsOptions:
          type: array
          items:
            $ref: '#/components/schemas/ExtractorOption'
          description: Extractors to apply with their configuration options
          example: []
  responses:
    NotFound:
      description: The requested resource was not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    Unauthorized:
      description: The request lacks valid authentication credentials
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    BadRequest:
      description: The request was malformed or contained invalid parameters
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  parameters:
    projectId:
      name: projectId
      in: path
      required: true
      description: Unique identifier of the Document Understanding project
      schema:
        type: string
    requestId:
      name: requestId
      in: path
      required: true
      description: Unique identifier of the asynchronous job request to retrieve results for
      schema:
        type: string
  securitySchemes:
    apiKeyAuth:
      type: apiKey
      in: header
      name: Authorization
      description: 'API token generated from the Automation Hub Admin Console under Platform Setup > Open API. Include as a Bearer token in the Authorization header: "Bearer {token}".'
externalDocs:
  description: UiPath Automation Hub API Documentation
  url: https://docs.uipath.com/automation-hub/automation-cloud/latest/api-guide/introduction-to-automation-hub-api-1