Adobe Creative Cloud PDF Extract Content

arazzo: 1.0.1
info:
  title: Adobe Creative Cloud PDF Extract Content
  summary: Upload a PDF, extract its text and tables with AI, then retrieve the structured result.
  description: >-
    AI-powered content extraction with Adobe PDF Services. The workflow creates
    an upload asset for the source PDF, submits the extract-PDF job requesting
    the desired content elements and table output format, and captures the 201
    Location header pointing at the opaque job status URL. That status URL is
    not modeled as an operation in the description, so once the job has
    completed the workflow retrieves a presigned download URI for the
    structured result asset. Every step spells out its request inline,
    including the bearer token and x-api-key, so the flow can be read and run
    without opening the underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: assetsApi
  url: ../openapi/adobe-creative-cloud-assets-api-openapi.yml
  type: openapi
- name: extractionApi
  url: ../openapi/adobe-creative-cloud-extraction-api-openapi.yml
  type: openapi
workflows:
- workflowId: pdf-extract-content
  summary: Extract text and tables from an uploaded PDF and get the result.
  description: >-
    Creates an upload asset for a PDF, submits an extraction job for the
    requested elements, and retrieves the structured result asset download URI.
  inputs:
    type: object
    required:
    - accessToken
    - apiKey
    - resultAssetID
    properties:
      accessToken:
        type: string
        description: OAuth 2.0 bearer access token from the Adobe IMS token endpoint.
      apiKey:
        type: string
        description: Client ID (x-api-key) from the Adobe Developer Console.
      elementsToExtract:
        type: array
        description: Content types to extract (text and/or tables).
        items:
          type: string
        default:
        - text
        - tables
      tableOutputFormat:
        type: string
        description: Format for extracted table data (csv or xlsx).
        default: csv
      resultAssetID:
        type: string
        description: Asset ID of the extraction result asset to fetch a download URI for.
  steps:
  - stepId: createUploadAsset
    description: >-
      Create an upload asset for the source PDF, obtaining an asset ID and a
      presigned upload URI.
    operationId: createAsset
    parameters:
    - name: Authorization
      in: header
      value: "Bearer $inputs.accessToken"
    - name: x-api-key
      in: header
      value: $inputs.apiKey
    requestBody:
      contentType: application/json
      payload:
        mediaType: application/pdf
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      assetID: $response.body#/assetID
      uploadUri: $response.body#/uploadUri
  - stepId: submitExtract
    description: >-
      Submit the extract-PDF job referencing the uploaded asset and the
      requested elements. Responds 201 with a Location header for job status.
    operationId: extractPdf
    parameters:
    - name: Authorization
      in: header
      value: "Bearer $inputs.accessToken"
    - name: x-api-key
      in: header
      value: $inputs.apiKey
    requestBody:
      contentType: application/json
      payload:
        assetID: $steps.createUploadAsset.outputs.assetID
        elementsToExtract: $inputs.elementsToExtract
        tableOutputFormat: $inputs.tableOutputFormat
    successCriteria:
    - condition: $statusCode == 201
    outputs:
      jobLocation: $response.headers.Location
  - stepId: getResultDownloadUri
    description: >-
      Retrieve the presigned download URI for the structured extraction result
      asset once the job has completed.
    operationId: getAsset
    parameters:
    - name: Authorization
      in: header
      value: "Bearer $inputs.accessToken"
    - name: x-api-key
      in: header
      value: $inputs.apiKey
    - name: assetID
      in: path
      value: $inputs.resultAssetID
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      downloadUri: $response.body#/downloadUri
  outputs:
    sourceAssetID: $steps.createUploadAsset.outputs.assetID
    jobLocation: $steps.submitExtract.outputs.jobLocation
    downloadUri: $steps.getResultDownloadUri.outputs.downloadUri