Amazon Kendra Sync Data Source and Query

arazzo: 1.0.1
info:
  title: Amazon Kendra Sync Data Source and Query
  summary: Start a data source sync job on an existing connector, wait for it to succeed, then query the refreshed index.
  description: >-
    Triggers an on-demand synchronization of an existing data source connector,
    polls ListDataSourceSyncJobs until the started job leaves the SYNCING state
    and reports SUCCEEDED, then runs a Query so the freshly crawled content is
    reflected in search results. Each step inlines its request, including the AWS
    JSON protocol X-Amz-Target header, so the flow can be read and executed
    without opening the underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: kendraApi
  url: ../openapi/amazon-kendra-openapi.yml
  type: openapi
workflows:
- workflowId: sync-data-source-and-query
  summary: Start a sync job, wait for SUCCEEDED, then query the refreshed index.
  description: >-
    Starts a synchronization job on an existing data source, polls the sync job
    list until it succeeds, and runs a search query against the refreshed index.
  inputs:
    type: object
    required:
    - indexId
    - dataSourceId
    - queryText
    properties:
      indexId:
        type: string
        description: The identifier of the index that owns the data source.
      dataSourceId:
        type: string
        description: The identifier of the data source to synchronize.
      queryText:
        type: string
        description: The search query to run once the sync completes.
  steps:
  - stepId: startSyncJob
    description: >-
      Start an on-demand synchronization job for the data source connector so it
      re-crawls and re-indexes the source repository.
    operationId: StartDataSourceSyncJob
    parameters:
    - name: IndexId
      in: path
      value: $inputs.indexId
    - name: DataSourceId
      in: path
      value: $inputs.dataSourceId
    - name: X-Amz-Target
      in: header
      value: AWSKendraFrontendService.StartDataSourceSyncJob
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      executionId: $response.body#/ExecutionId
  - stepId: waitForSyncComplete
    description: >-
      Poll the list of sync jobs until the most recent job leaves the SYNCING
      state and reports SUCCEEDED, confirming the crawl finished.
    operationId: ListDataSourceSyncJobs
    parameters:
    - name: IndexId
      in: path
      value: $inputs.indexId
    - name: DataSourceId
      in: path
      value: $inputs.dataSourceId
    - name: X-Amz-Target
      in: header
      value: AWSKendraFrontendService.ListDataSourceSyncJobs
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      history: $response.body#/History
    onSuccess:
    - name: syncSucceeded
      type: goto
      stepId: query
      criteria:
      - context: $response.body
        condition: $.History[0].Status == "SUCCEEDED"
        type: jsonpath
    onFailure:
    - name: retrySyncStatus
      type: retry
      stepId: waitForSyncComplete
      retryAfter: 30
      retryLimit: 20
      criteria:
      - context: $response.body
        condition: $.History[0].Status == "SYNCING"
        type: jsonpath
  - stepId: query
    description: >-
      Run the search query against the refreshed index so newly synced documents
      are reflected in the results.
    operationId: Query
    parameters:
    - name: IndexId
      in: path
      value: $inputs.indexId
    - name: X-Amz-Target
      in: header
      value: AWSKendraFrontendService.Query
    requestBody:
      contentType: application/json
      payload:
        QueryText: $inputs.queryText
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      queryId: $response.body#/QueryId
      resultItems: $response.body#/ResultItems
  outputs:
    executionId: $steps.startSyncJob.outputs.executionId
    queryId: $steps.query.outputs.queryId
    resultItems: $steps.query.outputs.resultItems