Create Ml Endpoint
neptunedata_create_ml_endpoint | R Documentation |
Creates a new Neptune ML inference endpoint that lets you query one specific model that the model-training process constructed¶
Description¶
Creates a new Neptune ML inference endpoint that lets you query one specific model that the model-training process constructed. See Managing inference endpoints using the endpoints command.
When invoking this operation in a Neptune cluster that has IAM authentication enabled, the IAM user or role making the request must have a policy attached that allows the neptune-db:CreateMLEndpoint IAM action in that cluster.
Usage¶
neptunedata_create_ml_endpoint(id, mlModelTrainingJobId,
mlModelTransformJobId, update, neptuneIamRoleArn, modelName,
instanceType, instanceCount, volumeEncryptionKMSKey)
Arguments¶
id
A unique identifier for the new inference endpoint. The default is an autogenerated timestamped name.
mlModelTrainingJobId
The job Id of the completed model-training job that has created the model that the inference endpoint will point to. You must supply either the
mlModelTrainingJobId
or themlModelTransformJobId
.mlModelTransformJobId
The job Id of the completed model-transform job. You must supply either the
mlModelTrainingJobId
or themlModelTransformJobId
.update
If set to
true
,update
indicates that this is an update request. The default isfalse
. You must supply either themlModelTrainingJobId
or themlModelTransformJobId
.neptuneIamRoleArn
The ARN of an IAM role providing Neptune access to SageMaker and Amazon S3 resources. This must be listed in your DB cluster parameter group or an error will be thrown.
modelName
Model type for training. By default the Neptune ML model is automatically based on the
modelType
used in data processing, but you can specify a different model type here. The default isrgcn
for heterogeneous graphs andkge
for knowledge graphs. The only valid value for heterogeneous graphs isrgcn
. Valid values for knowledge graphs are:kge
,transe
,distmult
, androtate
.instanceType
The type of Neptune ML instance to use for online servicing. The default is
ml.m5.xlarge
. Choosing the ML instance for an inference endpoint depends on the task type, the graph size, and your budget.instanceCount
The minimum number of Amazon EC2 instances to deploy to an endpoint for prediction. The default is 1
volumeEncryptionKMSKey
The Amazon Key Management Service (Amazon 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.
Value¶
A list with the following syntax: