ahnsv / node-sdk

:comet: Node.js library to access IBM Watson services.

Watson APIs Node.js SDK

Node.js client library to use the Watson APIs.

Table of Contents

• Installation
• Getting the Service Credentials
• Usage
• Client-side usage
• Sending Request Headers
• Parsing HTTP Response
• Data collection opt-out
• Questions
• Examples
• IBM Watson Services
  • Authorization
  • Assistant
  • Discovery
  • Language Translator
  • Natural Language Classifier
  • Natural Language Understanding
  • Personality Insights
  • Speech to Text
  • Text to Speech
  • Tone Analyzer
  • Visual Recognition
• Composing Services
• Debug
• Tests
• License
• Contributing

Installation

npm install watson-developer-cloud

Getting the service credentials

Visual Recognition

The process for authenticating with Visual Recognition has changed:

• For new service instances, authenticate by using IAM. See IAM Authentication. Also set the service URL by passing in url in the service constructor.
• For service instances created before May 23, 2018, authenticate by providing the basic auth api_key for the service instance.

Basic Auth

You will need the username, password, and url for each service. Visual Recognition instances created before May 23, 2018 use api_key. Service credentials are different from your IBM Cloud account username and password.

To get your service credentials, follow these steps:

1. Log in to IBM Cloud at https://console.bluemix.net/catalog/?category=watson.
2. In the IBM Cloud Catalog, select the service you want to use.
3. Type a unique name for the service instance in the Service name field. For example, type my-service-name. Leave the default values for the other options.
4. Click Create.
5. From the service dashboard, click Service credentials.
6. Click View credentials under Actions.
7. Copy username, password (or api_key for Visual Recognition), and url.

IAM Authentication

When authenticating with IAM, you have the option of passing in:

• the IAM API key and, optionally, the IAM service URL
• an IAM access token

Be aware that passing in an access token means that you're assuming responsibility for maintaining that token's lifecycle. If you instead pass in an IAM API key, the SDK will manage it for you.

// in the constructor, letting the SDK manage the IAM token
const discovery = new DiscoveryV1({
  url: '<service_url>',
  version: '<version-date>',
  iam_apikey: '<iam_api_key>',
  iam_url: '<iam_url>', // optional - the default value is https://iam.ng.bluemix.net/identity/token
});

// in the constructor, assuming control of managing IAM token
const discovery = new DiscoveryV1({
  url: '<service_url>',
  version: '<version-date>',
  iam_access_token: '<access-token>'
});

// after instantiation, assuming control of managing IAM token
const discovery = new DiscoveryV1({
  url: '<service_url>',
  version: '<version-date>'
});

discovery.setAccessToken('<access-token>')

Usage

The examples below assume that you already have service credentials. If not, you will have to create a service in IBM Cloud.

If you are running your application in IBM Cloud, you don't need to specify the credentials; the library will get them for you by looking at the VCAP_SERVICES environment variable.

Credentials are checked for in the following order:

1. Hard-coded or programatic credentials passed to the service constructor

2. Environment variables:

• SERVICE_NAME_USERNAME and SERVICE_NAME_PASSWORD environment properties (or SERVICE_NAME_API_KEY when appropriate) and, optionally, SERVICE_NAME_URL
• If using IAM: SERVICE_NAME_IAM_APIKEY and optionally SERVICE_NAME_IAM_URL, or SERVICE_NAME_IAM_ACCESS_TOKEN

3. IBM-Cloud-supplied credentials (via the VCAP_SERVICES JSON-encoded environment property)

Client-side usage

See the examples/ folder for Browserify and Webpack client-side SDK examples (with server-side generation of auth tokens.)

Note: not all services currently support CORS, and therefore not all services can be used client-side. Of those that do, most require an auth token to be generated server-side via the Authorization Service.

Sending Request Headers

Custom headers can be passed with any request. Each method has an optional parameter headers which can be used to pass in these custom headers, which can override headers that we use as parameters.

For example, this is how you can pass in custom headers to Watson Assistant service. In this example, the 'custom' value for 'Accept-Language' will override the default header for 'Accept-Language', and the 'Custom-Header' while not overriding the default headers, will additionally be sent with the request.

var assistant = new watson.AssistantV1({
/* username, password, version, url, etc... */
});

assistant.message({
  workspace_id: 'something',
  input: {'text': 'Hello'},
  headers: {
    'Custom-Header': 'custom',
    'Accept-Language': 'custom'
  
  }
},  function(err, result, response) {
  if (err)
    console.log('error:', err);
  else
    console.log(JSON.stringify(result, null, 2));
});

Parsing HTTP Response

To retrieve the HTTP response, all methods can be called with a callback function with three parameters, with the third being the response. Users for example may retrieve the response headers with this usage pattern.

Here is an example of how to access the response headers for Watson Assistant:

var assistant = new watson.AssistantV1({
/* username, password, version, url, etc... */
});

assistant.message(params,  function(err, result, response) {
  if (err)
    console.log('error:', err);
  else
    console.log(response.headers);
});

Data collection opt-out

By default, all requests are logged. This can be disabled of by setting the X-Watson-Learning-Opt-Out header when creating the service instance:

var myInstance = new watson.WhateverServiceV1({
  /* username, password, version, url, etc... */
  headers: {
    "X-Watson-Learning-Opt-Out": true
  }
});

Documentation

You can find links to the documentation at https://console.bluemix.net/developer/watson/documentation. Find the service that you're interested in, click API reference, and then select the Node tab.

There are also auto-generated JSDocs available at http://watson-developer-cloud.github.io/node-sdk/master/

Questions

If you are having difficulties using the APIs or have a question about the Watson services, please ask a question at dW Answers or Stack Overflow.

Examples

The examples folder has basic and advanced examples.

Authorization

The Authorization service can generate auth tokens for situations where providing the service username/password is undesirable.

Tokens are valid for 1 hour and may be sent using the X-Watson-Authorization-Token header or the watson-token query param.

Note that the token is supplied URL-encoded, and will not be accepted if it is double-encoded in a querystring.

var watson = require('watson-developer-cloud');

var authorization = new watson.AuthorizationV1({
  username: '<Text to Speech username>',
  password: '<Text to Speech password>',
  url: 'https://stream.watsonplatform.net/authorization/api', // Speech tokens
});

authorization.getToken({
  url: 'https://stream.watsonplatform.net/text-to-speech/api'
},
function (err, token) {
  if (!token) {
    console.log('error:', err);
  } else {
    // Use your token here
  }
});

Assistant

Use the Assistant service to determine the intent of a message.

Note: you must first create a workspace via Bluemix. See the documentation for details.

var AssistantV1 = require('watson-developer-cloud/assistant/v1');

var assistant = new AssistantV1({
  username: '<username>',
  password: '<password>',
  url: 'https://gateway.watsonplatform.net/assistant/api/',
  version: '2018-02-16'
});

assistant.message(
  {
    input: { text: "What's the weather?" },
    workspace_id: '<workspace id>'
  },
  function(err, response) {
    if (err) {
      console.error(err);
    } else {
      console.log(JSON.stringify(response, null, 2));
    }
  }
);

Conversation

This service has been renamed to Assistant.

Discovery

Use the Discovery Service to search and analyze structured and unstructured data.

var DiscoveryV1 = require('watson-developer-cloud/discovery/v1');

var discovery = new DiscoveryV1({
  username: '<username>',
  password: '<password>',
  url: 'https://gateway.watsonplatform.net/discovery/api/',
  version: '2017-09-01'
});

discovery.query(
  {
    environment_id: '<environment_id>',
    collection_id: '<collection_id>',
    query: 'my_query'
  },
  function(err, response) {
    if (err) {
      console.error(err);
    } else {
      console.log(JSON.stringify(response, null, 2));
    }
  }
);

Language Translator

Translate text from one language to another or idenfity a language using the Language Translator service.

var LanguageTranslatorV2 = require('watson-developer-cloud/language-translator/v2');

var languageTranslator = new LanguageTranslatorV2({
  username: '<username>',
  password: '<password>',
  url: 'https://gateway.watsonplatform.net/language-translator/api/'
});

languageTranslator.translate(
  {
    text: 'A sentence must have a verb',
    source: 'en',
    target: 'es'
  },
  function(err, translation) {
    if (err)  {
      console.log('error:', err);
    } else  {
      console.log(JSON.stringify(translation, null, 2));
  }
);

languageTranslator.identify(
  {
    text:
      'The language translator service takes text input and identifies the language used.'
  },
  function(err, language) {
    if (err)  {
      console.log('error:', err);
    } else {
      console.log(JSON.stringify(language, null, 2));
    }
  }
);

Natural Language Classifier

Use Natural Language Classifier service to create a classifier instance by providing a set of representative strings and a set of one or more correct classes for each as training. Then use the trained classifier to classify your new question for best matching answers or to retrieve next actions for your application.

var NaturalLanguageClassifierV1 = require('watson-developer-cloud/natural-language-classifier/v1');

var classifier = new NaturalLanguageClassifierV1({
  username: '<username>',
  password: '<password>',
  url: 'https://gateway.watsonplatform.net/natural-language-classifier/api/'
});

classifier.classify(
  {
    text: 'Is it sunny?',
    classifier_id: '<classifier-id>'
  },
  function(err, response) {
    if (err) {
      console.log('error:', err);
    } else {
      console.log(JSON.stringify(response, null, 2));
    }
  }
);

See this example to learn how to create a classifier.

Natural Language Understanding

Use Natural Language Understanding is a collection of natural language processing APIs that help you understand sentiment, keywords, entities, high-level concepts and more.

var fs = require('fs');
var NaturalLanguageUnderstandingV1 = require('watson-developer-cloud/natural-language-understanding/v1.js');

var nlu = new NaturalLanguageUnderstandingV1({
  username: '<username>',
  password: '<password>',
  version: '2018-04-05',
  url: 'https://gateway.watsonplatform.net/natural-language-understanding/api/'
});

nlu.analyze(
  {
    html: file_data, // Buffer or String
    features: {
      concepts: {},
      keywords: {}
    }
  },
  function(err, response) {
    if (err) {
      console.log('error:', err);
    } else {
      console.log(JSON.stringify(response, null, 2));
    }
  }
);

Personality Insights

Analyze text in English and get a personality profile by using the Personality Insights service.

var PersonalityInsightsV3 = require('watson-developer-cloud/personality-insights/v3');

var personalityInsights = new PersonalityInsightsV3({
  username: '<username>',
  password: '<password>',
  version: '2016-10-19',
  url: 'https://gateway.watsonplatform.net/personality-insights/api/'
});

personalityInsights.profile(
  {
    content: 'Enter more than 100 unique words here...',
    content_type: 'text/plain',
    consumption_preferences: true
  },
  function(err, response) {
    if (err) {
      console.log('error:', err);
    } else {
      console.log(JSON.stringify(response, null, 2));
    }
  }
);

Speech to Text

Use the Speech to Text service to recognize the text from a .wav file.

var SpeechToTextV1 = require('watson-developer-cloud/speech-to-text/v1');
var fs = require('fs');

var speechToText = new SpeechToTextV1({
  username: '<username>',
  password: '<password>',
  url: 'https://stream.watsonplatform.net/speech-to-text/api/'
});

var params = {
  // From file
  audio: fs.createReadStream('./resources/speech.wav'),
  content_type: 'audio/l16; rate=44100'
};

speechToText.recognize(params, function(err, res) {
  if (err)
    console.log(err);
  else
    console.log(JSON.stringify(res, null, 2));
});

// or streaming
fs.createReadStream('./resources/speech.wav')
  .pipe(speechToText.createRecognizeStream({ content_type: 'audio/l16; rate=44100' }))
  .pipe(fs.createWriteStream('./transcription.txt'));

Text to Speech

Use the Text to Speech service to synthesize text into a .wav file.

var TextToSpeechV1 = require('watson-developer-cloud/text-to-speech/v1');
var fs = require('fs');

var textToSpeech = new TextToSpeechV1({
  username: '<username>',
  password: '<password>',
  url: 'https://stream.watsonplatform.net/text-to-speech/api/'
});

var params = {
  text: 'Hello from IBM Watson',
  voice: 'en-US_AllisonVoice', // Optional voice
  accept: 'audio/wav'
};

// Synthesize speech, correct the wav header, then save to disk
// (wav header requires a file length, but this is unknown until after the header is already generated and sent)
textToSpeech
  .synthesize(params, function(err, audio) {
    if (err) {
      console.log(err);
      return;
    }
    textToSpeech.repairWavHeader(audio);
    fs.writeFileSync('audio.wav', audio);
    console.log('audio.wav written with a corrected wav header');
});

Tone Analyzer

Use the Tone Analyzer service to analyze the emotion, writing and social tones of a text.

var ToneAnalyzerV3 = require('watson-developer-cloud/tone-analyzer/v3');

var toneAnalyzer = new ToneAnalyzerV3({
  username: '<username>',
  password: '<password>',
  version: '2016-05-19',
  url: 'https://gateway.watsonplatform.net/tone-analyzer/api/'
});

toneAnalyzer.tone(
  {
    tone_input: 'Greetings from Watson Developer Cloud!',
    content_type: 'text/plain'
  },
  function(err, tone) {
    if (err) {
      console.log(err);
    } else {
      console.log(JSON.stringify(tone, null, 2));
    }
  }
);

Visual Recognition

Use the Visual Recognition service to recognize the following picture.

var VisualRecognitionV3 = require('watson-developer-cloud/visual-recognition/v3');
var fs = require('fs');

var visualRecognition = new VisualRecognitionV3({
  url: '<service_url>',
  version: '2018-03-19',
  iam_apikey: '<iam_api_key>',
});

var params = {
  images_file: fs.createReadStream('./resources/car.png')
};

visualRecognition.classify(params, function(err, res) {
  if (err) {
    console.log(err);
  } else {
    console.log(JSON.stringify(res, null, 2));
  }
});

Composing services

Integration of Tone Analyzer with Conversation

Sample code for integrating Tone Analyzer and Conversation is provided in the examples directory.

Unauthenticated requests

By default, the library tries to use Basic Auth and will ask for api_key or username and password and send an Authorization: Basic XXXXXXX. You can avoid this by using:

use_unauthenticated.

var watson = require('watson-developer-cloud');

var assistant = new watson.AssistantV1({
  use_unauthenticated: true
});

Debug

This library relies on the request npm module writted by request to call the Watson Services. To debug the apps, add 'request' to the NODE_DEBUG environment variable:

$ NODE_DEBUG='request' node app.js

where app.js is your Node.js file.

Tests

Running all the tests:

$ npm test

Running a specific test:

$ mocha -g '<test name>'

Open Source @ IBM

Find more open source projects on the IBM Github Page.

License

This library is licensed under Apache 2.0. Full license text is available in COPYING.

Contributing

See CONTRIBUTING.