arazzo: 1.0.1
info:
  title: Dataiku Create Dataset, Set Schema, and Build
  summary: Create a dataset, apply an explicit schema to it, and kick off a build job.
  description: >-
    Provisions a fully defined Dataiku DSS dataset end to end. The workflow
    creates a dataset, applies an explicit column schema to it, and then starts
    a build job so the dataset is materialized. Every step inlines its request
    so the flow can be executed without opening the underlying OpenAPI
    description.
  version: 1.0.0
sourceDescriptions:
- name: dssPublicApi
  url: ../openapi/dataiku-public-api-openapi.yml
  type: openapi
workflows:
- workflowId: create-dataset-set-schema-build
  summary: Create a dataset, set its schema, and start a build.
  description: >-
    Creates a dataset, applies a column schema with setDatasetSchema, then
    starts a build job for the dataset.
  inputs:
    type: object
    required:
    - apiKey
    - projectKey
    - datasetName
    - datasetType
    - columns
    properties:
      apiKey:
        type: string
        description: DSS API key passed as a Bearer token in the Authorization header.
      projectKey:
        type: string
        description: Project key that will own the dataset.
      datasetName:
        type: string
        description: Name of the dataset to create.
      datasetType:
        type: string
        description: Dataset type (e.g. Filesystem, PostgreSQL).
      datasetParams:
        type: object
        description: Type-specific connection parameters for the dataset.
      columns:
        type: array
        description: Column definitions to apply as the dataset schema.
        items:
          type: object
  steps:
  - stepId: createDataset
    description: Create the dataset shell in the project.
    operationId: createDataset
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.apiKey
    - name: projectKey
      in: path
      value: $inputs.projectKey
    requestBody:
      contentType: application/json
      payload:
        name: $inputs.datasetName
        type: $inputs.datasetType
        params: $inputs.datasetParams
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      datasetName: $response.body#/name
  - stepId: setSchema
    description: Apply the explicit column schema to the newly created dataset.
    operationId: setDatasetSchema
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.apiKey
    - name: projectKey
      in: path
      value: $inputs.projectKey
    - name: datasetName
      in: path
      value: $steps.createDataset.outputs.datasetName
    requestBody:
      contentType: application/json
      payload:
        columns: $inputs.columns
    successCriteria:
    - condition: $statusCode == 200
  - stepId: buildDataset
    description: Start a build job for the dataset now that its schema is set.
    operationId: startJob
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.apiKey
    - name: projectKey
      in: path
      value: $inputs.projectKey
    requestBody:
      contentType: application/json
      payload:
        outputs:
        - projectKey: $inputs.projectKey
          id: $steps.createDataset.outputs.datasetName
          type: DATASET
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      jobId: $response.body#/id
      state: $response.body#/state
  outputs:
    datasetName: $steps.createDataset.outputs.datasetName
    jobId: $steps.buildDataset.outputs.jobId