clients/client-sagemaker-a2i-runtime/README.md
AWS SDK for JavaScript SageMakerA2IRuntime Client for Node.js, Browser and React Native.
<p>Amazon Augmented AI (Amazon A2I) adds the benefit of human judgment to any machine learning application. When an AI application can't evaluate data with a high degree of confidence, human reviewers can take over. This human review is called a human review workflow. To create and start a human review workflow, you need three resources: a <i>worker task template</i>, a <i>flow definition</i>, and a <i>human loop</i>.</p> <p>For information about these resources and prerequisites for using Amazon A2I, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/a2i-getting-started.html">Get Started with Amazon Augmented AI</a> in the Amazon SageMaker Developer Guide.</p> <p>This API reference includes information about API actions and data types that you can use to interact with Amazon A2I programmatically. Use this guide to:</p> <ul> <li> <p>Start a human loop with the <code>StartHumanLoop</code> operation when using Amazon A2I with a <i>custom task type</i>. To learn more about the difference between custom and built-in task types, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/a2i-task-types-general.html">Use Task Types </a>. To learn how to start a human loop using this API, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/a2i-start-human-loop.html#a2i-instructions-starthumanloop">Create and Start a Human Loop for a Custom Task Type </a> in the Amazon SageMaker Developer Guide.</p> </li> <li> <p>Manage your human loops. You can list all human loops that you have created, describe individual human loops, and stop and delete human loops. To learn more, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/a2i-monitor-humanloop-results.html">Monitor and Manage Your Human Loop </a> in the Amazon SageMaker Developer Guide.</p> </li> </ul> <p>Amazon A2I integrates APIs from various AWS services to create and start human review workflows for those services. To learn how Amazon A2I uses these APIs, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/a2i-api-references.html">Use APIs in Amazon A2I</a> in the Amazon SageMaker Developer Guide.</p>To install this package, use the CLI of your favorite package manager:
npm install @aws-sdk/client-sagemaker-a2i-runtimeyarn add @aws-sdk/client-sagemaker-a2i-runtimepnpm add @aws-sdk/client-sagemaker-a2i-runtimeThe AWS SDK is modulized by clients and commands.
To send a request, you only need to import the SageMakerA2IRuntimeClient and
the commands you need, for example ListHumanLoopsCommand:
// ES5 example
const { SageMakerA2IRuntimeClient, ListHumanLoopsCommand } = require("@aws-sdk/client-sagemaker-a2i-runtime");
// ES6+ example
import { SageMakerA2IRuntimeClient, ListHumanLoopsCommand } from "@aws-sdk/client-sagemaker-a2i-runtime";
To send a request:
send operation on the client, providing the command object as input.const client = new SageMakerA2IRuntimeClient({ region: "REGION" });
const params = { /** input parameters */ };
const command = new ListHumanLoopsCommand(params);
We recommend using the await operator to wait for the promise returned by send operation as follows:
// async/await.
try {
const data = await client.send(command);
// process data.
} catch (error) {
// error handling.
} finally {
// finally.
}
You can also use Promise chaining.
client
.send(command)
.then((data) => {
// process data.
})
.catch((error) => {
// error handling.
})
.finally(() => {
// finally.
});
The aggregated client class is exported from the same package, but without the "Client" suffix.
SageMakerA2IRuntime extends SageMakerA2IRuntimeClient and additionally supports all operations, waiters, and paginators as methods.
This style may be familiar to you from the AWS SDK for JavaScript v2.
If you are bundling the AWS SDK, we recommend using only the bare-bones client (SageMakerA2IRuntimeClient).
More details are in the blog post on
modular packages in AWS SDK for JavaScript.
import { SageMakerA2IRuntime } from "@aws-sdk/client-sagemaker-a2i-runtime";
const client = new SageMakerA2IRuntime({ region: "REGION" });
// async/await.
try {
const data = await client.listHumanLoops(params);
// process data.
} catch (error) {
// error handling.
}
// Promises.
client
.listHumanLoops(params)
.then((data) => {
// process data.
})
.catch((error) => {
// error handling.
});
// callbacks (not recommended).
client.listHumanLoops(params, (err, data) => {
// process err and data.
});
When the service returns an exception, the error will include the exception information, as well as response metadata (e.g. request id).
try {
const data = await client.send(command);
// process data.
} catch (error) {
const { requestId, cfId, extendedRequestId } = error.$metadata;
console.log({ requestId, cfId, extendedRequestId });
/**
* The keys within exceptions are also parsed.
* You can access them by specifying exception names:
* if (error.name === 'SomeServiceException') {
* const value = error.specialKeyInException;
* }
*/
}
See also docs/ERROR_HANDLING.
Please use these community resources for getting help. We use GitHub issues for tracking bugs and feature requests, but have limited bandwidth to address them.
aws-sdk-js
on AWS Developer Blog.aws-sdk-js.To test your universal JavaScript code in Node.js, browser and react-native environments, visit our code samples repo.
This client code is generated automatically. Any modifications will be overwritten the next time the @aws-sdk/client-sagemaker-a2i-runtime package is updated.
To contribute to client you can check our generate clients scripts.
This SDK is distributed under the Apache License, Version 2.0, see LICENSE for more information.
Command API Reference / Input / Output
</details> <details> <summary> DescribeHumanLoop </summary>Command API Reference / Input / Output
</details> <details> <summary> ListHumanLoops </summary>Command API Reference / Input / Output
</details> <details> <summary> StartHumanLoop </summary> </details> <details> <summary> StopHumanLoop </summary> </details>