Invoke Endpoint Async
sagemaker_runtime.invoke_endpoint_async
ActionAmazon Web Servicesconnection required
Calls the AWS sagemaker_runtime API (SigV4).
After you deploy a model into production using Amazon SageMaker AI hosting services, your client applications use this API to get inferences from the model hosted at the specified endpoint in an asynchronous manner.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- API key
- Providers
- Amazon SageMaker Runtime
- Secret shape
- {"access_key_id", "secret_access_key"}
- Config it needs
- region
- Resolved by
- config.connection_id, else node.connection_id
Configuration
2 fields, 1 required. A dotted path is a nested object and name[] an array of objects — the editor renders the same tree.
| Field | Type | Required | Default | Constraints | Example |
|---|---|---|---|---|---|
region AWS region (overrides the connection). | string | No | — | — | — |
endpoint_name The name of the endpoint that you specified when you created the endpoint using the Create | string | Yes | — | — | — |
Output
One shape.
result
| Field | Type | Example |
|---|---|---|
InferenceId | string | — |
OutputLocation | string | — |
FailureLocation | string | — |
{
"FailureLocation": "",
"InferenceId": "",
"OutputLocation": ""
}Related Amazon SageMaker Runtime nodes
See Invoke Endpoint Async run in a workflow.
In a technical demo we add the Amazon SageMaker Runtime connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.