Amazon Augmented AI (Amazon A2I) adds the benefit of human judgment to any machine learning\napplication. When an AI application can't evaluate data with a high degree of confidence,\nhuman reviewers can take over. This human review is called a human review workflow. To create\nand start a human review workflow, you need three resources: a worker task\ntemplate, a flow definition, and a human\nloop.
\nFor information about these resources and prerequisites for using Amazon A2I, see Get Started with\nAmazon Augmented AI in the Amazon SageMaker Developer Guide.
\nThis API reference includes information about API actions and data types that you can use\nto interact with Amazon A2I programmatically. Use this guide to:
\nStart a human loop with the StartHumanLoop operation when using\nAmazon A2I with a custom task type. To learn more about the\ndifference between custom and built-in task types, see Use Task Types . To learn\nhow to start a human loop using this API, see Create and Start a Human Loop for a Custom Task Type in the\nAmazon SageMaker Developer Guide.
Manage your human loops. You can list all human loops that you have created, describe\nindividual human loops, and stop and delete human loops. To learn more, see Monitor and Manage Your Human Loop in the Amazon SageMaker Developer Guide.
\nAmazon A2I integrates APIs from various AWS services to create and start human review\nworkflows for those services. To learn how Amazon A2I uses these APIs, see Use APIs in\nAmazon A2I in the Amazon SageMaker Developer Guide.
\n\n## Installing\n\nTo install this package, use the CLI of your favorite package manager:\n\n- `npm install @aws-sdk/client-sagemaker-a2i-runtime`\n- `yarn add @aws-sdk/client-sagemaker-a2i-runtime`\n- `pnpm add @aws-sdk/client-sagemaker-a2i-runtime`\n\n## Getting Started\n\n### Import\n\nThe AWS SDK is modulized by clients and commands.\nTo send a request, you only need to import the `SageMakerA2IRuntimeClient` and\nthe commands you need, for example `ListHumanLoopsCommand`:\n\n```js\n// ES5 example\nconst { SageMakerA2IRuntimeClient, ListHumanLoopsCommand } = require(\"@aws-sdk/client-sagemaker-a2i-runtime\");\n```\n\n```ts\n// ES6+ example\nimport { SageMakerA2IRuntimeClient, ListHumanLoopsCommand } from \"@aws-sdk/client-sagemaker-a2i-runtime\";\n```\n\n### Usage\n\nTo send a request:\n\n- Instantiate a client with configuration (e.g. credentials, region).\n - See [docs/CLIENTS](https://github.com/aws/aws-sdk-js-v3/blob/main/supplemental-docs/CLIENTS.md) for configuration details.\n - See [@aws-sdk/config](https://github.com/aws/aws-sdk-js-v3/blob/main/packages/config/README.md) for additional options.\n- Instantiate a command with input parameters.\n- Call the `send` operation on the client, providing the command object as input.\n\n```js\nconst client = new SageMakerA2IRuntimeClient({ region: \"REGION\" });\n\nconst params = { /** input parameters */ };\nconst command = new ListHumanLoopsCommand(params);\n```\n\n#### Async/await\n\nWe recommend using the [await](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Operators/await)\noperator to wait for the promise returned by send operation as follows:\n\n```js\n// async/await.\ntry {\n const data = await client.send(command);\n // process data.\n} catch (error) {\n // error handling.\n} finally {\n // finally.\n}\n```\n\n#### Promises\n\nYou can also use [Promise chaining](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Guide/Using_promises#chaining).\n\n```js\nclient\n .send(command)\n .then((data) => {\n // process data.\n })\n .catch((error) => {\n // error handling.\n })\n .finally(() => {\n // finally.\n });\n```\n\n#### Aggregated client\n\nThe aggregated client class is exported from the same package, but without the \"Client\" suffix.\n\n`SageMakerA2IRuntime` extends `SageMakerA2IRuntimeClient` and additionally supports all operations, waiters, and paginators as methods.\nThis style may be familiar to you from the AWS SDK for JavaScript v2.\n\nIf you are bundling the AWS SDK, we recommend using only the bare-bones client (`SageMakerA2IRuntimeClient`).\nMore details are in the blog post on\n[modular packages in AWS SDK for JavaScript](https://aws.amazon.com/blogs/developer/modular-packages-in-aws-sdk-for-javascript/).\n\n```ts\nimport { SageMakerA2IRuntime } from \"@aws-sdk/client-sagemaker-a2i-runtime\";\n\nconst client = new SageMakerA2IRuntime({ region: \"REGION\" });\n\n// async/await.\ntry {\n const data = await client.listHumanLoops(params);\n // process data.\n} catch (error) {\n // error handling.\n}\n\n// Promises.\nclient\n .listHumanLoops(params)\n .then((data) => {\n // process data.\n })\n .catch((error) => {\n // error handling.\n });\n\n// callbacks (not recommended).\nclient.listHumanLoops(params, (err, data) => {\n // process err and data.\n});\n```\n\n### Troubleshooting\n\nWhen the service returns an exception, the error will include the exception information,\nas well as response metadata (e.g. request id).\n\n```js\ntry {\n const data = await client.send(command);\n // process data.\n} catch (error) {\n const { requestId, cfId, extendedRequestId } = error.$metadata;\n console.log({ requestId, cfId, extendedRequestId });\n /**\n * The keys within exceptions are also parsed.\n * You can access them by specifying exception names:\n * if (error.name === 'SomeServiceException') {\n * const value = error.specialKeyInException;\n * }\n */\n}\n```\n\nSee also [docs/ERROR_HANDLING](https://github.com/aws/aws-sdk-js-v3/blob/main/supplemental-docs/ERROR_HANDLING.md).\n\n## Getting Help\n\nPlease use these community resources for getting help.\nWe use GitHub issues for tracking bugs and feature requests, but have limited bandwidth to address them.\n\n- Visit the [Developer Guide](https://docs.aws.amazon.com/sdk-for-javascript/v3/developer-guide/welcome.html)\n or [API Reference](https://docs.aws.amazon.com/AWSJavaScriptSDK/v3/latest/index.html).\n- Check out the blog posts tagged with [`aws-sdk-js`](https://aws.amazon.com/blogs/developer/tag/aws-sdk-js/)\n on AWS Developer Blog.\n- Ask a question on [StackOverflow](https://stackoverflow.com/questions/tagged/aws-sdk-js) and tag it with `aws-sdk-js`.\n- Join the AWS JavaScript community on [gitter](https://gitter.im/aws/aws-sdk-js-v3).\n- If it turns out that you may have found a bug, please [open an issue](https://github.com/aws/aws-sdk-js-v3/issues/new/choose).\n\nTo test your universal JavaScript code in Node.js, browser and react-native environments,\nvisit our [code samples repo](https://github.com/aws-samples/aws-sdk-js-tests).\n\n## Contributing\n\nThis client code is generated automatically. Any modifications will be overwritten the next time the `@aws-sdk/client-sagemaker-a2i-runtime` package is updated.\nTo contribute to client you can check our [generate clients scripts](https://github.com/aws/aws-sdk-js-v3/tree/main/scripts/generate-clients).\n\n## License\n\nThis SDK is distributed under the\n[Apache License, Version 2.0](http://www.apache.org/licenses/LICENSE-2.0),\nsee LICENSE for more information.\n\n## Client Commands (Operations List)\n\n