{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/google-cloud-dataflow/json-schema/google-cloud-dataflow-google-cloud-datapipelines-v1-pipeline-schema.json",
  "title": "GoogleCloudDatapipelinesV1Pipeline",
  "description": "The main pipeline entity and all the necessary metadata for launching and managing linked jobs.",
  "x-generated": "2026-11-11",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/google-cloud-dataflow-datapipelines-projects-api-openapi.yml#/components/schemas/GoogleCloudDatapipelinesV1Pipeline",
  "type": "object",
  "properties": {
    "workload": {
      "$ref": "#/$defs/GoogleCloudDatapipelinesV1Workload",
      "description": "Workload information for creating new jobs."
    },
    "lastUpdateTime": {
      "readOnly": true,
      "format": "google-datetime",
      "description": "Output only. Immutable. The timestamp when the pipeline was last modified. Set by the Data Pipelines service.",
      "type": "string"
    },
    "scheduleInfo": {
      "$ref": "#/$defs/GoogleCloudDatapipelinesV1ScheduleSpec",
      "description": "Internal scheduling information for a pipeline. If this information is provided, periodic jobs will be created per the schedule. If not, users are responsible for creating jobs externally."
    },
    "state": {
      "type": "string",
      "description": "Required. The state of the pipeline. When the pipeline is created, the state is set to 'PIPELINE_STATE_ACTIVE' by default. State changes can be requested by setting the state to stopping, paused, or resuming. State cannot be changed through UpdatePipeline requests.",
      "enum": [
        "STATE_UNSPECIFIED",
        "STATE_RESUMING",
        "STATE_ACTIVE",
        "STATE_STOPPING",
        "STATE_ARCHIVED",
        "STATE_PAUSED"
      ]
    },
    "jobCount": {
      "format": "int32",
      "type": "integer",
      "description": "Output only. Number of jobs.",
      "readOnly": true
    },
    "pipelineSources": {
      "type": "object",
      "additionalProperties": {
        "type": "string"
      },
      "description": "Immutable. The sources of the pipeline (for example, Knowledge Catalog). The keys and values are set by the corresponding sources during pipeline creation."
    },
    "displayName": {
      "description": "Required. The display name of the pipeline. It can contain only letters ([A-Za-z]), numbers ([0-9]), hyphens (-), and underscores (_).",
      "type": "string"
    },
    "type": {
      "type": "string",
      "enum": [
        "PIPELINE_TYPE_UNSPECIFIED",
        "PIPELINE_TYPE_BATCH",
        "PIPELINE_TYPE_STREAMING"
      ],
      "description": "Required. The type of the pipeline. This field affects the scheduling of the pipeline and the type of metrics to show for the pipeline."
    },
    "schedulerServiceAccountEmail": {
      "description": "Optional. A service account email to be used with the Cloud Scheduler job. If not specified, the default compute engine service account will be used.",
      "type": "string"
    },
    "name": {
      "description": "The pipeline name. For example: `projects/PROJECT_ID/locations/LOCATION_ID/pipelines/PIPELINE_ID`. * `PROJECT_ID` can contain letters ([A-Za-z]), numbers ([0-9]), hyphens (-), colons (:), and periods (.). For more information, see [Identifying projects](https://cloud.google.com/resource-manager/docs/creating-managing-projects#identifying_projects). * `LOCATION_ID` is the canonical ID for the pipeline's location. The list of available locations can be obtained by calling `google.cloud.location.Locations.ListLocations`. Note that the Data Pipelines service is not available in all regions. It depends on Cloud Scheduler, an App Engine application, so it's only available in [App Engine regions](https://cloud.google.com/about/locations#region). * `PIPELINE_ID` is the ID of the pipeline. Must be unique for the selected project and location.",
      "type": "string"
    },
    "createTime": {
      "readOnly": true,
      "format": "google-datetime",
      "type": "string",
      "description": "Output only. Immutable. The timestamp when the pipeline was initially created. Set by the Data Pipelines service."
    }
  },
  "$defs": {
    "GoogleCloudDatapipelinesV1FlexTemplateRuntimeEnvironment": {
      "type": "object",
      "properties": {
        "subnetwork": {
          "type": "string",
          "description": "Subnetwork to which VMs will be assigned, if desired. You can specify a subnetwork using either a complete URL or an abbreviated path. Expected to be of the form \"https://www.googleapis.com/compute/v1/projects/HOST_PROJECT_ID/regions/REGION/subnetworks/SUBNETWORK\" or \"regions/REGION/subnetworks/SUBNETWORK\". If the subnetwork is located in a Shared VPC network, you must use the complete URL."
        },
        "network": {
          "type": "string",
          "description": "Network to which VMs will be assigned. If empty or unspecified, the service will use the network \"default\"."
        },
        "additionalExperiments": {
          "type": "array",
          "description": "Additional experiment flags for the job.",
          "items": {
            "type": "string"
          }
        },
        "zone": {
          "description": "The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones) for launching worker instances to run your pipeline. In the future, worker_zone will take precedence.",
          "type": "string"
        },
        "serviceAccountEmail": {
          "description": "The email address of the service account to run the job as.",
          "type": "string"
        },
        "additionalUserLabels": {
          "type": "object",
          "description": "Additional user labels to be specified for the job. Keys and values must follow the restrictions specified in the [labeling restrictions](https://cloud.google.com/compute/docs/labeling-resources#restrictions). An object containing a list of key/value pairs. Example: `{ \"name\": \"wrench\", \"mass\": \"1kg\", \"count\": \"3\" }`.",
          "additionalProperties": {
            "type": "string"
          }
        },
        "flexrsGoal": {
          "type": "string",
          "description": "Set FlexRS goal for the job. https://cloud.google.com/dataflow/docs/guides/flexrs",
          "enum": [
            "FLEXRS_UNSPECIFIED",
            "FLEXRS_SPEED_OPTIMIZED",
            "FLEXRS_COST_OPTIMIZED"
          ]
        },
        "tempLocation": {
          "type": "string",
          "description": "The Cloud Storage path to use for temporary files. Must be a valid Cloud Storage URL, beginning with `gs://`."
        },
        "ipConfiguration": {
          "type": "string",
          "enum": [
            "WORKER_IP_UNSPECIFIED",
            "WORKER_IP_PUBLIC",
            "WORKER_IP_PRIVATE"
          ],
          "description": "Configuration for VM IPs."
        },
        "workerRegion": {
          "type": "string",
          "description": "The Compute Engine region (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in which worker processing should occur, e.g. \"us-west1\". Mutually exclusive with worker_zone. If neither worker_region nor worker_zone is specified, defaults to the control plane region."
        },
        "numWorkers": {
          "description": "The initial number of Compute Engine instances for the job.",
          "type": "integer",
          "format": "int32"
        },
        "machineType": {
          "type": "string",
          "description": "The machine type to use for the job. Defaults to the value from the template if not specified."
        },
        "maxWorkers": {
          "description": "The maximum number of Compute Engine instances to be made available to your pipeline during execution, from 1 to 1000.",
          "format": "int32",
          "type": "integer"
        },
        "kmsKeyName": {
          "type": "string",
          "description": "Name for the Cloud KMS key for the job. Key format is: projects//locations//keyRings//cryptoKeys/"
        },
        "enableStreamingEngine": {
          "type": "boolean",
          "description": "Whether to enable Streaming Engine for the job."
        },
        "workerZone": {
          "description": "The Compute Engine zone (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in which worker processing should occur, e.g. \"us-west1-a\". Mutually exclusive with worker_region. If neither worker_region nor worker_zone is specified, a zone in the control plane region is chosen based on available capacity. If both `worker_zone` and `zone` are set, `worker_zone` takes precedence.",
          "type": "string"
        }
      },
      "description": "The environment values to be set at runtime for a Flex Template."
    },
    "GoogleCloudDatapipelinesV1LaunchFlexTemplateParameter": {
      "description": "Launch Flex Template parameter.",
      "properties": {
        "transformNameMappings": {
          "type": "object",
          "description": "Use this to pass transform name mappings for streaming update jobs. Example: `{\"oldTransformName\":\"newTransformName\",...}`",
          "additionalProperties": {
            "type": "string"
          }
        },
        "parameters": {
          "additionalProperties": {
            "type": "string"
          },
          "description": "The parameters for the Flex Template. Example: `{\"num_workers\":\"5\"}`",
          "type": "object"
        },
        "jobName": {
          "description": "Required. The job name to use for the created job. For an update job request, the job name should be the same as the existing running job.",
          "type": "string"
        },
        "environment": {
          "$ref": "#/$defs/GoogleCloudDatapipelinesV1FlexTemplateRuntimeEnvironment",
          "description": "The runtime environment for the Flex Template job."
        },
        "update": {
          "description": "Set this to true if you are sending a request to update a running streaming job. When set, the job name should be the same as the running job.",
          "type": "boolean"
        },
        "containerSpecGcsPath": {
          "type": "string",
          "description": "Cloud Storage path to a file with a JSON-serialized ContainerSpec as content."
        },
        "launchOptions": {
          "type": "object",
          "additionalProperties": {
            "type": "string"
          },
          "description": "Launch options for this Flex Template job. This is a common set of options across languages and templates. This should not be used to pass job parameters."
        }
      },
      "type": "object"
    },
    "GoogleCloudDatapipelinesV1LaunchFlexTemplateRequest": {
      "properties": {
        "launchParameter": {
          "$ref": "#/$defs/GoogleCloudDatapipelinesV1LaunchFlexTemplateParameter",
          "description": "Required. Parameter to launch a job from a Flex Template."
        },
        "validateOnly": {
          "type": "boolean",
          "description": "If true, the request is validated but not actually executed. Defaults to false."
        },
        "location": {
          "type": "string",
          "description": "Required. The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request. For example, `us-central1`, `us-west1`."
        },
        "projectId": {
          "description": "Required. The ID of the Cloud Platform project that the job belongs to.",
          "type": "string"
        }
      },
      "description": "A request to launch a Dataflow job from a Flex Template.",
      "type": "object"
    },
    "GoogleCloudDatapipelinesV1LaunchTemplateParameters": {
      "type": "object",
      "properties": {
        "transformNameMapping": {
          "type": "object",
          "description": "Map of transform name prefixes of the job to be replaced to the corresponding name prefixes of the new job. Only applicable when updating a pipeline.",
          "additionalProperties": {
            "type": "string"
          }
        },
        "parameters": {
          "description": "The runtime parameters to pass to the job.",
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        "environment": {
          "$ref": "#/$defs/GoogleCloudDatapipelinesV1RuntimeEnvironment",
          "description": "The runtime environment for the job."
        },
        "update": {
          "description": "If set, replace the existing pipeline with the name specified by jobName with this pipeline, preserving state.",
          "type": "boolean"
        },
        "jobName": {
          "type": "string",
          "description": "Required. The job name to use for the created job."
        }
      },
      "description": "Parameters to provide to the template being launched."
    },
    "GoogleCloudDatapipelinesV1LaunchTemplateRequest": {
      "type": "object",
      "description": "A request to launch a template.",
      "properties": {
        "validateOnly": {
          "description": "If true, the request is validated but not actually executed. Defaults to false.",
          "type": "boolean"
        },
        "gcsPath": {
          "description": "A Cloud Storage path to the template from which to create the job. Must be a valid Cloud Storage URL, beginning with 'gs://'.",
          "type": "string"
        },
        "location": {
          "description": "The [regional endpoint] (https://cloud.google.com/dataflow/docs/concepts/regional-endpoints) to which to direct the request.",
          "type": "string"
        },
        "launchParameters": {
          "$ref": "#/$defs/GoogleCloudDatapipelinesV1LaunchTemplateParameters",
          "description": "The parameters of the template to launch. This should be part of the body of the POST request."
        },
        "projectId": {
          "description": "Required. The ID of the Cloud Platform project that the job belongs to.",
          "type": "string"
        }
      }
    },
    "GoogleCloudDatapipelinesV1RuntimeEnvironment": {
      "description": "The environment values to set at runtime.",
      "type": "object",
      "properties": {
        "workerZone": {
          "type": "string",
          "description": "The Compute Engine zone (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in which worker processing should occur, e.g. \"us-west1-a\". Mutually exclusive with worker_region. If neither worker_region nor worker_zone is specified, a zone in the control plane's region is chosen based on available capacity. If both `worker_zone` and `zone` are set, `worker_zone` takes precedence."
        },
        "additionalExperiments": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Additional experiment flags for the job."
        },
        "zone": {
          "type": "string",
          "description": "The Compute Engine [availability zone](https://cloud.google.com/compute/docs/regions-zones/regions-zones) for launching worker instances to run your pipeline. In the future, worker_zone will take precedence."
        },
        "serviceAccountEmail": {
          "description": "The email address of the service account to run the job as.",
          "type": "string"
        },
        "kmsKeyName": {
          "type": "string",
          "description": "Name for the Cloud KMS key for the job. The key format is: projects//locations//keyRings//cryptoKeys/"
        },
        "additionalUserLabels": {
          "type": "object",
          "additionalProperties": {
            "type": "string"
          },
          "description": "Additional user labels to be specified for the job. Keys and values should follow the restrictions specified in the [labeling restrictions](https://cloud.google.com/compute/docs/labeling-resources#restrictions) page. An object containing a list of key/value pairs. Example: { \"name\": \"wrench\", \"mass\": \"1kg\", \"count\": \"3\" }."
        },
        "maxWorkers": {
          "description": "The maximum number of Compute Engine instances to be made available to your pipeline during execution, from 1 to 1000.",
          "format": "int32",
          "type": "integer"
        },
        "numWorkers": {
          "type": "integer",
          "description": "The initial number of Compute Engine instances for the job.",
          "format": "int32"
        },
        "bypassTempDirValidation": {
          "type": "boolean",
          "description": "Whether to bypass the safety checks for the job's temporary directory. Use with caution."
        },
        "machineType": {
          "type": "string",
          "description": "The machine type to use for the job. Defaults to the value from the template if not specified."
        },
        "tempLocation": {
          "description": "The Cloud Storage path to use for temporary files. Must be a valid Cloud Storage URL, beginning with `gs://`.",
          "type": "string"
        },
        "enableStreamingEngine": {
          "description": "Whether to enable Streaming Engine for the job.",
          "type": "boolean"
        },
        "network": {
          "type": "string",
          "description": "Network to which VMs will be assigned. If empty or unspecified, the service will use the network \"default\"."
        },
        "workerRegion": {
          "type": "string",
          "description": "The Compute Engine region (https://cloud.google.com/compute/docs/regions-zones/regions-zones) in which worker processing should occur, e.g. \"us-west1\". Mutually exclusive with worker_zone. If neither worker_region nor worker_zone is specified, default to the control plane's region."
        },
        "subnetwork": {
          "type": "string",
          "description": "Subnetwork to which VMs will be assigned, if desired. You can specify a subnetwork using either a complete URL or an abbreviated path. Expected to be of the form \"https://www.googleapis.com/compute/v1/projects/HOST_PROJECT_ID/regions/REGION/subnetworks/SUBNETWORK\" or \"regions/REGION/subnetworks/SUBNETWORK\". If the subnetwork is located in a Shared VPC network, you must use the complete URL."
        },
        "ipConfiguration": {
          "enum": [
            "WORKER_IP_UNSPECIFIED",
            "WORKER_IP_PUBLIC",
            "WORKER_IP_PRIVATE"
          ],
          "type": "string",
          "description": "Configuration for VM IPs."
        }
      }
    },
    "GoogleCloudDatapipelinesV1ScheduleSpec": {
      "type": "object",
      "properties": {
        "timeZone": {
          "type": "string",
          "description": "Timezone ID. This matches the timezone IDs used by the Cloud Scheduler API. If empty, UTC time is assumed."
        },
        "nextJobTime": {
          "format": "google-datetime",
          "description": "Output only. When the next Scheduler job is going to run.",
          "type": "string",
          "readOnly": true
        },
        "schedule": {
          "description": "Unix-cron format of the schedule. This information is retrieved from the linked Cloud Scheduler.",
          "type": "string"
        }
      },
      "description": "Details of the schedule the pipeline runs on."
    },
    "GoogleCloudDatapipelinesV1Workload": {
      "type": "object",
      "description": "Workload details for creating the pipeline jobs.",
      "properties": {
        "dataflowLaunchTemplateRequest": {
          "$ref": "#/$defs/GoogleCloudDatapipelinesV1LaunchTemplateRequest",
          "description": "Template information and additional parameters needed to launch a Dataflow job using the standard launch API."
        },
        "dataflowFlexTemplateRequest": {
          "$ref": "#/$defs/GoogleCloudDatapipelinesV1LaunchFlexTemplateRequest",
          "description": "Template information and additional parameters needed to launch a Dataflow job using the flex launch API."
        }
      }
    }
  }
}