Databricks · Schema

TaskSettings

AIAnalyticsApache SparkBig DataClean RoomsCloud ComputingDataData AnalyticsData EngineeringData GovernanceDelta LakeDelta SharingETLIdentity ManagementLakehouseMachine LearningMLflowModel ServingSecuritySQLUnity CatalogVector SearchVisualize

Properties

Name	Type	Description
task_key	string	A unique key for the task within the job. Used to reference the task in dependencies and logging.
description	string	A description of the task.
depends_on	array	An array of objects specifying the task dependencies. Each dependency is identified by its task_key.
existing_cluster_id	string	An existing cluster to run the task on.
new_cluster	object
job_cluster_key	string	Reference to a job_clusters entry.
notebook_task	object
spark_jar_task	object
spark_python_task	object
spark_submit_task	object
pipeline_task	object
python_wheel_task	object
sql_task	object
dbt_task	object
run_if	string	Condition to run this task.
timeout_seconds	integer	Timeout for this individual task.
max_retries	integer	Maximum number of retries for a failed task.
min_retry_interval_millis	integer	Minimum interval between retry attempts.
retry_on_timeout	boolean	Whether to retry when the task times out.
email_notifications	object
libraries	array	Libraries to install on the cluster running this task.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/TaskSettings",
  "title": "TaskSettings",
  "type": "object",
  "required": [
    "task_key"
  ],
  "properties": {
    "task_key": {
      "type": "string",
      "description": "A unique key for the task within the job. Used to reference the task in dependencies and logging.",
      "examples": [
        "etl_task_1"
      ]
    },
    "description": {
      "type": "string",
      "description": "A description of the task.",
      "example": "A sample description."
    },
    "depends_on": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "task_key": {
            "type": "string"
          },
          "outcome": {
            "type": "string"
          }
        }
      },
      "description": "An array of objects specifying the task dependencies. Each dependency is identified by its task_key.",
      "example": []
    },
    "existing_cluster_id": {
      "type": "string",
      "description": "An existing cluster to run the task on.",
      "example": "500123"
    },
    "new_cluster": {
      "$ref": "#/components/schemas/CreateClusterRequest"
    },
    "job_cluster_key": {
      "type": "string",
      "description": "Reference to a job_clusters entry.",
      "example": "example_value"
    },
    "notebook_task": {
      "type": "object",
      "properties": {
        "notebook_path": {
          "type": "string",
          "description": "The absolute path of the notebook in the workspace."
        },
        "source": {
          "type": "string",
          "enum": [
            "WORKSPACE",
            "GIT"
          ],
          "description": "The source of the notebook."
        },
        "base_parameters": {
          "type": "object",
          "additionalProperties": {
            "type": "string"
          },
          "description": "Base parameters to pass to the notebook. These can be overridden at run time."
        }
      },
      "example": "example_value"
    },
    "spark_jar_task": {
      "type": "object",
      "properties": {
        "main_class_name": {
          "type": "string"
        },
        "parameters": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "jar_uri": {
          "type": "string"
        }
      },
      "example": "example_value"
    },
    "spark_python_task": {
      "type": "object",
      "properties": {
        "python_file": {
          "type": "string",
          "description": "URI of the Python file to execute."
        },
        "parameters": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "source": {
          "type": "string",
          "enum": [
            "WORKSPACE",
            "GIT"
          ]
        }
      },
      "example": "example_value"
    },
    "spark_submit_task": {
      "type": "object",
      "properties": {
        "parameters": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "example": "example_value"
    },
    "pipeline_task": {
      "type": "object",
      "properties": {
        "pipeline_id": {
          "type": "string"
        },
        "full_refresh": {
          "type": "boolean"
        }
      },
      "example": "example_value"
    },
    "python_wheel_task": {
      "type": "object",
      "properties": {
        "package_name": {
          "type": "string"
        },
        "entry_point": {
          "type": "string"
        },
        "parameters": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "named_parameters": {
          "type": "object",
          "additionalProperties": {
            "type": "string"
          }
        }
      },
      "example": "example_value"
    },
    "sql_task": {
      "type": "object",
      "properties": {
        "query": {
          "type": "object",
          "properties": {
            "query_id": {
              "type": "string"
            }
          }
        },
        "dashboard": {
          "type": "object",
          "properties": {
            "dashboard_id": {
              "type": "string"
            }
          }
        },
        "alert": {
          "type": "object",
          "properties": {
            "alert_id": {
              "type": "string"
            }
          }
        },
        "warehouse_id": {
          "type": "string"
        },
        "parameters": {
          "type": "object",
          "additionalProperties": {
            "type": "string"
          }
        }
      },
      "example": "example_value"
    },
    "dbt_task": {
      "type": "object",
      "properties": {
        "project_directory": {
          "type": "string"
        },
        "commands": {
          "type": "array",
          "items": {
            "type": "string"
          }
        },
        "schema": {
          "type": "string"
        },
        "warehouse_id": {
          "type": "string"
        },
        "catalog": {
          "type": "string"
        },
        "profiles_directory": {
          "type": "string"
        }
      },
      "example": "example_value"
    },
    "run_if": {
      "type": "string",
      "enum": [
        "ALL_SUCCESS",
        "AT_LEAST_ONE_SUCCESS",
        "NONE_FAILED",
        "ALL_DONE",
        "AT_LEAST_ONE_FAILED",
        "ALL_FAILED"
      ],
      "description": "Condition to run this task.",
      "example": "ALL_SUCCESS"
    },
    "timeout_seconds": {
      "type": "integer",
      "description": "Timeout for this individual task.",
      "example": 10
    },
    "max_retries": {
      "type": "integer",
      "description": "Maximum number of retries for a failed task.",
      "example": 10
    },
    "min_retry_interval_millis": {
      "type": "integer",
      "description": "Minimum interval between retry attempts.",
      "example": 10
    },
    "retry_on_timeout": {
      "type": "boolean",
      "description": "Whether to retry when the task times out.",
      "example": true
    },
    "email_notifications": {
      "$ref": "#/components/schemas/JobEmailNotifications"
    },
    "libraries": {
      "type": "array",
      "items": {
        "$ref": "#/components/schemas/Library"
      },
      "description": "Libraries to install on the cluster running this task.",
      "example": []
    }
  }
}