@aws-sdk/client-lex-runtime-service

What is @aws-sdk/client-lex-runtime-service?

@aws-sdk/client-lex-runtime-service is an AWS SDK for JavaScript package that allows developers to interact with the Amazon Lex Runtime Service. This service enables you to build conversational interfaces using voice and text. The package provides methods to send user input to Amazon Lex and receive responses, manage session attributes, and more.

What are @aws-sdk/client-lex-runtime-service's main functionalities?

PostText

The PostText feature allows you to send user input text to Amazon Lex and receive a response. This is useful for text-based conversational interfaces.

{"import":"import { LexRuntimeServiceClient, PostTextCommand } from '@aws-sdk/client-lex-runtime-service';","client":"const client = new LexRuntimeServiceClient({ region: 'us-west-2' });","command":"const command = new PostTextCommand({ botName: 'BookTrip', botAlias: 'Prod', userId: 'user123', inputText: 'I want to book a hotel' });","response":"const response = await client.send(command);","log":"console.log(response);"}

PostContent

The PostContent feature allows you to send user input in audio format to Amazon Lex and receive a response. This is useful for voice-based conversational interfaces.

{"import":"import { LexRuntimeServiceClient, PostContentCommand } from '@aws-sdk/client-lex-runtime-service';","client":"const client = new LexRuntimeServiceClient({ region: 'us-west-2' });","command":"const command = new PostContentCommand({ botName: 'BookTrip', botAlias: 'Prod', userId: 'user123', contentType: 'audio/l16; rate=16000; channels=1', inputStream: audioStream });","response":"const response = await client.send(command);","log":"console.log(response);"}

GetSession

The GetSession feature allows you to retrieve session information for a user. This can be useful for managing and maintaining the state of a conversation.

{"import":"import { LexRuntimeServiceClient, GetSessionCommand } from '@aws-sdk/client-lex-runtime-service';","client":"const client = new LexRuntimeServiceClient({ region: 'us-west-2' });","command":"const command = new GetSessionCommand({ botName: 'BookTrip', botAlias: 'Prod', userId: 'user123' });","response":"const response = await client.send(command);","log":"console.log(response);"}

PutSession

The PutSession feature allows you to create or update a session for a user. This can be useful for setting session attributes and managing the flow of a conversation.

{"import":"import { LexRuntimeServiceClient, PutSessionCommand } from '@aws-sdk/client-lex-runtime-service';","client":"const client = new LexRuntimeServiceClient({ region: 'us-west-2' });","command":"const command = new PutSessionCommand({ botName: 'BookTrip', botAlias: 'Prod', userId: 'user123', sessionAttributes: { key: 'value' }, dialogAction: { type: 'ElicitIntent', intentName: 'BookHotel' } });","response":"const response = await client.send(command);","log":"console.log(response);"}

Other packages similar to @aws-sdk/client-lex-runtime-service

dialogflow

The dialogflow package allows you to interact with Google Dialogflow, a natural language understanding platform used to design and integrate conversational user interfaces. It offers similar functionalities to Amazon Lex, such as handling text and voice inputs, managing sessions, and more.

botframework

The botframework package is part of Microsoft's Bot Framework, which provides tools to build, test, and deploy chatbots. It supports multiple channels and offers features like natural language understanding, dialog management, and integration with various services.

rasa

Rasa is an open-source machine learning framework for automated text and voice-based conversations. It provides tools for intent recognition, entity extraction, and dialogue management, similar to Amazon Lex. Rasa allows for more customization and control over the conversational models.

README

@aws-sdk/client-lex-runtime-service

Description

AWS SDK for JavaScript LexRuntimeService Client for Node.js, Browser and React Native.

Amazon Lex provides both build and runtime endpoints. Each endpoint provides a set of operations (API). Your conversational bot uses the runtime API to understand user utterances (user input text or voice). For example, suppose a user says "I want pizza", your bot sends this input to Amazon Lex using the runtime API. Amazon Lex recognizes that the user request is for the OrderPizza intent (one of the intents defined in the bot). Then Amazon Lex engages in user conversation on behalf of the bot to elicit required information (slot values, such as pizza size and crust type), and then performs fulfillment activity (that you configured when you created the bot). You use the build-time API to create and manage your Amazon Lex bot. For a list of build-time operations, see the build-time API, .

Installing

To install this package, simply type add or install @aws-sdk/client-lex-runtime-service using your favorite package manager:

• npm install @aws-sdk/client-lex-runtime-service
• yarn add @aws-sdk/client-lex-runtime-service
• pnpm add @aws-sdk/client-lex-runtime-service

Getting Started

Import

The AWS SDK is modulized by clients and commands. To send a request, you only need to import the LexRuntimeServiceClient and the commands you need, for example GetSessionCommand:

// ES5 example
const { LexRuntimeServiceClient, GetSessionCommand } = require("@aws-sdk/client-lex-runtime-service");

// ES6+ example
import { LexRuntimeServiceClient, GetSessionCommand } from "@aws-sdk/client-lex-runtime-service";

Usage

To send a request, you:

• Initiate client with configuration (e.g. credentials, region).
• Initiate command with input parameters.
• Call send operation on client with command object as input.
• If you are using a custom http handler, you may call destroy() to close open connections.

// a client can be shared by different commands.
const client = new LexRuntimeServiceClient({ region: "REGION" });

const params = {
  /** input parameters */
};
const command = new GetSessionCommand(params);

Async/await

We recommend using 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.
}

Async-await is clean, concise, intuitive, easy to debug and has better error handling as compared to using Promise chains or callbacks.

Promises

You can also use Promise chaining to execute send operation.

client.send(command).then(
  (data) => {
    // process data.
  },
  (error) => {
    // error handling.
  }
);

Promises can also be called using .catch() and .finally() as follows:

client
  .send(command)
  .then((data) => {
    // process data.
  })
  .catch((error) => {
    // error handling.
  })
  .finally(() => {
    // finally.
  });

Callbacks

We do not recommend using callbacks because of callback hell, but they are supported by the send operation.

// callbacks.
client.send(command, (err, data) => {
  // process err and data.
});

v2 compatible style

The client can also send requests using v2 compatible style. However, it results in a bigger bundle size and may be dropped in next major version. More details in the blog post on modular packages in AWS SDK for JavaScript

import * as AWS from "@aws-sdk/client-lex-runtime-service";
const client = new AWS.LexRuntimeService({ region: "REGION" });

// async/await.
try {
  const data = await client.getSession(params);
  // process data.
} catch (error) {
  // error handling.
}

// Promises.
client
  .getSession(params)
  .then((data) => {
    // process data.
  })
  .catch((error) => {
    // error handling.
  });

// callbacks.
client.getSession(params, (err, data) => {
  // process err and data.
});

Troubleshooting

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;
   * }
   */
}

Getting Help

Please use these community resources for getting help. We use the GitHub issues for tracking bugs and feature requests, but have limited bandwidth to address them.

• Visit Developer Guide or API Reference.
• Check out the blog posts tagged with aws-sdk-js on AWS Developer Blog.
• Ask a question on StackOverflow and tag it with aws-sdk-js.
• Join the AWS JavaScript community on gitter.
• If it turns out that you may have found a bug, please open an issue.

To test your universal JavaScript code in Node.js, browser and react-native environments, visit our code samples repo.

Contributing

This client code is generated automatically. Any modifications will be overwritten the next time the @aws-sdk/client-lex-runtime-service package is updated. To contribute to client you can check our generate clients scripts.

License

This SDK is distributed under the Apache License, Version 2.0, see LICENSE for more information.

Client Commands (Operations List)

DeleteSession

Command API Reference / Input / Output

GetSession

Command API Reference / Input / Output

PostContent

Command API Reference / Input / Output

PostText

Command API Reference / Input / Output

PutSession

Command API Reference / Input / Output

Changelog

3.714.0 (2024-12-17)

Bug Fixes

• xhr-http-handler: fix abort signal sharing for multiple requests (#6740) (5d7500f)

Features

• client-account: Update endpoint configuration. (104dcc7)
• client-backup: Add Support for Backup Indexing (e03d20d)
• client-backupsearch: Add support for searching backups (d9ef47c)
• client-batch: This feature allows AWS Batch on Amazon EKS to support configuration of Pod Annotations, overriding Namespace on which the Batch job's Pod runs on, and allows Subpath and Persistent Volume claim to be set for AWS Batch on Amazon EKS jobs. (00737e5)
• client-cleanroomsml: Add support for SQL compute configuration for StartAudienceGenerationJob API. (119c1d2)
• client-cloudfront: Adds support for OriginReadTimeout and OriginKeepaliveTimeout to create CloudFront Distributions with VPC Origins. (a4d166e)
• client-codepipeline: AWS CodePipeline V2 type pipelines now support Managed Compute Rule. (9287267)
• client-ecs: Added support for enableFaultInjection task definition parameter which can be used to enable Fault Injection feature on ECS tasks. (5e299dd)
• client-m2: This release adds support for AWS Mainframe Modernization(M2) Service to allow specifying network type(ipv4, dual) for the environment instances. For dual network type, m2 environment applications will serve both IPv4 and IPv6 requests, whereas for ipv4 it will serve only IPv4 requests. (c8d1a9a)
• client-synthetics: Add support to toggle outbound IPv6 traffic on canaries connected to dualstack subnets. This behavior can be controlled via the new Ipv6AllowedForDualStack parameter of the VpcConfig input object in CreateCanary and UpdateCanary APIs. (bc1080b)
• clients: profile setting for clients (#6728) (afd9eea)
• clients: update client endpoints as of 2024-12-17 (38482d0)