Write Action
sagemaker_a2i_runtime.call
ActionAmazon Web Servicesconnection required
Calls the AWS sagemaker_a2i_runtime API (SigV4).
Run one of 3 write actions on SageMaker A2I Runtime.
Connection
- Required
- Yes — the node will not save without one
- Auth type
- API key
- Providers
- Amazon Augmented AI Runtime
- Secret shape
- {"access_key_id", "secret_access_key"}
- Config it needs
- region
- Resolved by
- config.connection_id, else node.connection_id
Configuration
3 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 | — | — | — |
action Which write action to run. | string | Yes | — | one of "DeleteHumanLoop", "StartHumanLoop", "StopHumanLoop" | — |
request The action's input, as AWS documents it. | object | No | — | — | — |
Output
One shape.
result
The AWS response for the operation you named, as returned.
Extra keys beyond the ones listed can appear.
{}Notes
- This performs a real change in the account. Dry runs stub it, like every other external node.
Related Amazon Augmented AI Runtime nodes
See Write Action run in a workflow.
In a technical demo we add the Amazon Augmented AI Runtime connection, drop the node on the canvas and let Workflow Health pre-flight it before the first real run.