{ "$schema": "https://json-schema.org/draft/2020-12/schema", "$id": "#/components/schemas/CreateClusterRequest", "title": "CreateClusterRequest", "type": "object", "required": [ "spark_version" ], "properties": { "cluster_name": { "type": "string", "description": "Cluster name requested by the user. Does not have to be unique. If not specified at creation, the cluster name is an empty string.", "example": "example_value" }, "spark_version": { "type": "string", "description": "The runtime version of the cluster. You can retrieve a list of available runtime versions using the spark-versions endpoint.", "examples": [ "13.3.x-scala2.12" ] }, "node_type_id": { "type": "string", "description": "The node type for the worker nodes. Refer to list-node-types for available node types.", "examples": [ "Standard_DS3_v2" ] }, "driver_node_type_id": { "type": "string", "description": "The node type for the driver node. If unset, the driver node type is set as the same value as node_type_id.", "example": "500123" }, "num_workers": { "type": "integer", "format": "int32", "description": "Number of worker nodes. For a fixed-size cluster, set this to the desired number of workers. For an autoscaling cluster, this field is ignored in favor of autoscale settings.", "example": 10 }, "autoscale": { "$ref": "#/components/schemas/AutoScale" }, "spark_conf": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Map of Spark configuration key-value pairs. These are passed directly to the Spark driver and executors.", "example": "example_value" }, "azure_attributes": { "$ref": "#/components/schemas/AzureAttributes" }, "ssh_public_keys": { "type": "array", "items": { "type": "string" }, "description": "SSH public keys for accessing cluster nodes", "example": [] }, "custom_tags": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Custom tags applied to cluster resources. Databricks adds default tags in addition to any custom tags you specify.", "example": "example_value" }, "cluster_log_conf": { "$ref": "#/components/schemas/ClusterLogConf" }, "init_scripts": { "type": "array", "items": { "$ref": "#/components/schemas/InitScriptInfo" }, "description": "Init scripts to run when the cluster starts", "example": [] }, "spark_env_vars": { "type": "object", "additionalProperties": { "type": "string" }, "description": "Map of environment variable key-value pairs for the Spark process.", "example": "example_value" }, "enable_elastic_disk": { "type": "boolean", "description": "If true, enable autoscaling local storage. When enabled, the amount of disk space used by the cluster auto-adjusts.", "example": true }, "instance_pool_id": { "type": "string", "description": "ID of the instance pool to use for cluster nodes. If specified, the cluster uses the instance pool for both driver and worker nodes.", "example": "500123" }, "policy_id": { "type": "string", "description": "Identifier of the cluster policy used to create the cluster.", "example": "500123" }, "enable_local_disk_encryption": { "type": "boolean", "description": "Whether to enable local disk encryption for the cluster", "example": true }, "runtime_engine": { "type": "string", "enum": [ "STANDARD", "PHOTON" ], "description": "The runtime engine to use. PHOTON provides optimized query execution.", "example": "STANDARD" }, "data_security_mode": { "type": "string", "enum": [ "NONE", "SINGLE_USER", "USER_ISOLATION", "LEGACY_TABLE_ACL", "LEGACY_PASSTHROUGH", "LEGACY_SINGLE_USER", "LEGACY_SINGLE_USER_STANDARD" ], "description": "Data security mode for the cluster. Determines how data access is controlled.", "example": "NONE" }, "single_user_name": { "type": "string", "description": "The name of the single user who can execute commands on the cluster. Required when data_security_mode is SINGLE_USER.", "example": "example_value" } } }