Mindee Passport and ID Extraction

arazzo: 1.0.1
info:
  title: Mindee Passport and ID Extraction
  summary: Enqueue a passport or identity document with polygon locations, poll until processed, then read the extracted holder fields.
  description: >-
    Applies the Mindee asynchronous extraction pattern to passports and other
    identity documents. The workflow uploads an ID document against an identity
    extraction model with the polygon option enabled so each field carries its
    bounding box location, polls the shared jobs endpoint until the job is
    Processed, and fetches the inference to read holder fields such as name,
    document number, nationality, and expiry. Every step spells out its request
    inline so the flow can be read and executed without opening the underlying
    OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: extractionApi
  url: ../openapi/mindee-extraction-api-openapi.yml
  type: openapi
- name: jobsApi
  url: ../openapi/mindee-jobs-api-openapi.yml
  type: openapi
workflows:
- workflowId: passport-id-extraction
  summary: Upload a passport or ID document with polygon locations and read the extracted holder fields.
  description: >-
    Sends an identity document to the extraction enqueue endpoint with polygon
    location calculation enabled, polls the job until processing finishes, and
    retrieves the parsed identity fields with their bounding box locations.
  inputs:
    type: object
    required:
    - authorization
    - modelId
    - file
    properties:
      authorization:
        type: string
        description: Mindee API key sent in the Authorization header.
      modelId:
        type: string
        description: UUID of the extraction model trained for identity documents.
      file:
        type: string
        description: The passport or ID document file to upload as binary form data.
      filename:
        type: string
        description: Optional filename to associate with the uploaded document.
  steps:
  - stepId: enqueueDocument
    description: >-
      Send the identity document to the asynchronous extraction queue with the
      polygon option enabled so each field carries a bounding box location.
    operationId: Enqueue_Extraction_Product_Inference_v2_products_extraction_enqueue_post
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    requestBody:
      contentType: multipart/form-data
      payload:
        model_id: $inputs.modelId
        file: $inputs.file
        filename: $inputs.filename
        polygon: true
    successCriteria:
    - condition: $statusCode == 202
    outputs:
      jobId: $response.body#/job/id
      status: $response.body#/job/status
  - stepId: pollJob
    description: >-
      Poll the shared jobs endpoint until the identity extraction job reports
      Processed or Failed.
    operationId: Get_Job_Status_v2_jobs__job_id__get
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    - name: job_id
      in: path
      value: $steps.enqueueDocument.outputs.jobId
    - name: redirect
      in: query
      value: false
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      status: $response.body#/job/status
    onSuccess:
    - name: jobProcessed
      type: goto
      stepId: getResult
      criteria:
      - context: $response.body
        condition: $.job.status == "Processed"
        type: jsonpath
    - name: jobPending
      type: goto
      stepId: pollJob
      criteria:
      - context: $response.body
        condition: $.job.status == "Processing"
        type: jsonpath
  - stepId: getResult
    description: >-
      Retrieve the completed extraction inference and read the structured
      identity fields and their locations parsed from the document.
    operationId: Get_Extraction_Product_Result_v2_products_extraction_results__inference_id__get
    parameters:
    - name: Authorization
      in: header
      value: $inputs.authorization
    - name: inference_id
      in: path
      value: $steps.enqueueDocument.outputs.jobId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      inferenceId: $response.body#/inference/id
      fields: $response.body#/inference/result/fields
  outputs:
    jobId: $steps.enqueueDocument.outputs.jobId
    fields: $steps.getResult.outputs.fields