StartMLModelTransformJobInput

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://artifacts.apis.io/amazon-neptune/json-schema/amazon-neptune-start-mlmodel-transform-job-input-schema.json",
  "title": "StartMLModelTransformJobInput",
  "x-generated": "2026-11-11",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/amazon-neptune-ml-api-openapi.yml#/components/schemas/StartMLModelTransformJobInput",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "A unique identifier for the new job. The default is an autogenerated UUID."
    },
    "dataProcessingJobId": {
      "type": "string",
      "description": "The job ID of a completed data-processing job. You must include either dataProcessingJobId and a mlModelTrainingJobId, or a trainingJobName."
    },
    "mlModelTrainingJobId": {
      "type": "string",
      "description": "The job ID of a completed model-training job. You must include either dataProcessingJobId and a mlModelTrainingJobId, or a trainingJobName."
    },
    "trainingJobName": {
      "type": "string",
      "description": "The name of a completed SageMaker training job. You must include either dataProcessingJobId and a mlModelTrainingJobId, or a trainingJobName."
    },
    "modelTransformOutputS3Location": {
      "type": "string",
      "description": "The location in Amazon S3 where the model artifacts are to be stored."
    },
    "sagemakerIamRoleArn": {
      "type": "string",
      "description": "The ARN of an IAM role for SageMaker execution. This must be listed in your DB cluster parameter group or an error will occur."
    },
    "neptuneIamRoleArn": {
      "type": "string",
      "description": "The ARN of an IAM role that provides Neptune access to SageMaker and Amazon S3 resources. This must be listed in your DB cluster parameter group or an error will occur."
    },
    "customModelTransformParameters": {
      "$ref": "#/$defs/CustomModelTransformParameters"
    },
    "baseProcessingInstanceType": {
      "type": "string",
      "description": "The type of ML instance used in preparing and managing training of ML models. This is an ML compute instance chosen based on memory requirements for processing the training data and model."
    },
    "baseProcessingInstanceVolumeSizeInGB": {
      "type": "integer",
      "description": "The disk volume size of the training instance in gigabytes. The default is 0. Both input data and the output model are stored on disk, so the volume size must be large enough to hold both data sets. If not specified or 0, Neptune ML selects a disk volume size based on the recommendation generated in the data processing step."
    },
    "subnets": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The IDs of the subnets in the Neptune VPC. The default is None."
    },
    "securityGroupIds": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The VPC security group IDs. The default is None."
    },
    "volumeEncryptionKMSKey": {
      "type": "string",
      "description": "The Amazon Key Management Service (KMS) key that SageMaker uses to encrypt data on the storage volume attached to the ML compute instances that run the training job. The default is None."
    },
    "s3OutputEncryptionKMSKey": {
      "type": "string",
      "description": "The Amazon Key Management Service (KMS) key that SageMaker uses to encrypt the output of the processing job. The default is none."
    }
  },
  "required": [
    "modelTransformOutputS3Location"
  ],
  "$defs": {
    "CustomModelTransformParameters": {
      "type": "object",
      "properties": {
        "sourceS3DirectoryPath": {
          "type": "string",
          "description": "The path to the Amazon S3 location where the Python module implementing your model is located. This must point to a valid existing Amazon S3 location that contains, at a minimum, a training script, a transform script, and a model-hpo-configuration.json file."
        },
        "transformEntryPointScript": {
          "type": "string",
          "description": "The name of the entry point in your module of a script that should be run after the best model from the hyperparameter search has been identified, to compute the model artifacts necessary for model deployment. It should be able to run with no command-line arguments. The default is transform.py."
        }
      },
      "required": [
        "sourceS3DirectoryPath"
      ]
    }
  }
}