watson-developer-cloud

Watson Developer Cloud Node.js Client

Wrapper to use the Watson Developer Cloud services, a collection of REST APIs and SDKs that use cognitive computing to solve complex problems.

Table of Contents

• Watson Developer Cloud
  • Questions
  • Installation
  • Usage
  • Getting the Service Credentials
  • Alchemy Services
    • Alchemy Language
  • IBM Watson Services
    • Authorization
    • Concept Expansion
    • Concept Insights
    • Dialog
    • Document Conversion
    • Language Translation
    • Message Resonance
    • Natural Language Classifier
    • Personality Insights
    • Question and Answer
    • Relationship Extraction
    • Speech to Text
    • Text to Speech
    • Tradeoff Analytics
    • Visual Recognition
  • Running in Bluemix
  • Debug
  • Tests
  • Open Source @ IBM
  • License
  • Contributing

Questions

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

Installation

$ npm install watson-developer-cloud --save

Usage

The examples below assume that you already have service credentials. If not, you will have to create and bind the service in Bluemix.

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

Getting the Service Credentials

The credentials for the services are stored in the VCAP_SERVICES environment variable. To get them, you need to first create and bind the service to your application.

There are two ways to get the credentials. You can use Bluemix to access your app and view the VCAP_SERVICES there or you can run:

$ cf env <application-name>

Example output:

  System-Provided:
  {
  "VCAP_SERVICES": {
    "visual_recognition": [{
        "credentials": {
          "password": "<password>",
          "url": "<url>",
          "username": "<username>"
        },
      "label": "visual_recognition",
      "name": "visual-recognition-service",
      "plan": "free"
   }]
  }
  }

You need to copy username and password.

For Alchemy you only need an api_key, you can register for one here.

Alchemy APIs

Alchemy Language

Alchemy Language offers 12 API functions as part of its text analysis service, each of which uses sophisticated natural language processing techniques to analyze your content and add high-level semantic information.

Use the Sentiment Analysis endpoint to identify positive/negative sentiment within a sample text document.

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

var alchemy_language = watson.alchemy_language({
  api_key: '<api_key>'
});

var params = {
  text: 'IBM Watson won the Jeopardy television show hosted by Alex Trebek'
};

alchemy_language.sentiment(params, function (err, response) {
  if (err)
    console.log('error:', err);
  else
    console.log(JSON.stringify(response, null, 2));
});

IBM Watson Services

The Watson Developer Cloud offers a variety of services for building cognitive apps.

Authorization

The Authorization service can generates tokens, this are useful when it's too cumbersome to provide a username/password pair.
Tokens are valid for 1 hour and need to be send using the X-Watson-Authorization-Token header.

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

var authorization = watson.authorization({
  username: '<username>',
  password: '<password>',
  version: 'v1'
});

var params = {
  // URL of the resource you wish to access
  url: 'https://stream.watsonplatform.net/text-to-speech/api'
};

authorization.getToken(params, function (err, token) {
  if (!token) {
    console.log('error:', err);
  } else {
    // Use your token here
  }
});

Concept Expansion

Map euphemisms or colloquial terms to more commonly understood phrases using the Concept Expansion service.

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

var concept_expansion = watson.concept_expansion({
  username: '<username>',
  password: '<password>',
  version: 'v1'
});

var params = {
  seeds: ['motrin','tylenol','aspirin'],
  dataset: 'mtsamples',
  label: 'medications'
};

concept_expansion.expand(params, function (err, response) {
  if (err)
    console.log('error:', err);
  else
    console.log(JSON.stringify(response, null, 2));
});

Concept Insights

Use the Concept Insights service to identify words in the text that correspond to concepts in a Wikipedia graph.

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

var concept_insights = watson.concept_insights({
  username: '<username>',
  password: '<password>',
  version: 'v2'
});

var params = {
  graph: '/graphs/wikipedia/en20120601',
  text: 'IBM Watson won the Jeopardy television show hosted by Alex Trebek'
};

// Retrieve the concepts for input text
concept_insights.annotateText(params, function(err, res) {
  if (err)
    console.log(err);
  else {
    console.log(JSON.stringify(res, null, 2));
  }
});

Dialog

Use the Dialog service to list all the dialogs you have.

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

var dialog = watson.dialog({
  username: '<username>',
  password: '<password>',
  version: 'v1'
});

dialog.getDialogs({}, function (err, dialogs) {
  if (err)
    console.log('error:', err);
  else
    console.log(JSON.stringify(dialogs, null, 2));
});

Document Conversion

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

var document_conversion = watson.document_conversion({
  username: '<username>',
  password: '<password>',
  version: 'v1-experimental'
});

// convert a single document
document_conversion.convert({
  // (JSON) ANSWER_UNITS, NORMALIZED_HTML, or NORMALIZED_TEXT
  file: fs.createReadStream('sample-docx.docx'),
  conversion_target: document_conversion.conversion_target.ANSWER_UNITS
}, function (err, response) {
  if (err) {
    console.error(err);
  } else {
    console.log(JSON.stringify(response, null, 2));
  }
});

Language Translation

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

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

var language_translation = watson.language_translation({
  username: '<username>',
  password: '<password>',
  version: 'v2'
});

language_translation.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));
});

language_translation.identify({
  text: 'The language translation 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));
});

Message Resonance

Get resonance information for individual words in a sentence from the Message Resonance service.

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

var message_resonance = watson.message_resonance({
  username: '<username>',
  password: '<password>',
  version:'v1'
});

message_resonance.resonance({
  text: 'IBM Watson Developer Cloud', dataset: 1 },
  function(err, response) {
    if (err)
      console.log('error:', err);
    else
      console.log(JSON.stringify(response, 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 watson = require('watson-developer-cloud');

var natural_language_classifier = watson.natural_language_classifier({
  url: 'https://gateway.watsonplatform.net/natural-language-classifier/api',
  username: '<username>',
  password: '<password>',
  version: 'v1'
});

natural_language_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.

Personality Insights

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

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

var personality_insights = watson.personality_insights({
  username: '<username>',
  password: '<password>',
  version: 'v2'
});

personality_insights.profile({
  text: 'Enter more than 100 unique words here...',
  language: 'en' },
  function (err, response) {
    if (err)
      console.log('error:', err);
    else
      console.log(JSON.stringify(response, null, 2));
});

Note: Don't forget to update the text variable!

Question and Answer

Ask a healthcare-related question of the Question and Answer service.

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

var question_and_answer_healthcare = watson.question_and_answer({
  username: '<username>',
  password: '<password>',
  version: 'v1',
  dataset: 'healthcare' /* The dataset can be specified when creating
                         * the service or when calling it */
});

question_and_answer_healthcare.ask({
  text: 'What is HIV?'}, function (err, response) {
    if (err)
      console.log('error:', err);
    else
      console.log(JSON.stringify(response, null, 2));
});

Relationship Extraction

Analyze an English news article and get the relationships between sentence components (nouns, verbs, subjects, objects, etc.) by using the Relationship Extraction service.

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

var relationship_extraction = watson.relationship_extraction({
  username: '<username>',
  password: '<password>',
  version: 'v1'
});

relationship_extraction.extract({
  text: 'IBM Watson developer cloud',
  dataset: 'ie-en-news' },
  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 watson = require('watson-developer-cloud');
var fs = require('fs');

var speech_to_text = watson.speech_to_text({
  username: '<username>',
  password: '<password>',
  version: 'v1',
  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'
};

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

Text to Speech

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

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

var text_to_speech = watson.text_to_speech({
  username: '<username>',
  password: '<password>',
  version: 'v1',
  url: 'https://stream.watsonplatform.net/text-to-speech/api'
});

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

// Pipe the synthesized text to a file
text_to_speech.synthesize(params).pipe(fs.createWriteStream('output.wav'));

Tradeoff Analytics

Use the Tradeoff Analytics service to find the best phone that minimizes price and weight and maximizes screen size.

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

var tradeoff_analytics = watson.tradeoff_analytics({
  username: '<username>',
  password: '<password>',
  version: 'v1'
});

// From file
var params = require('./resources/problem.json');

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

Visual Recognition

Use the Visual Recognition service to recognize the following picture.

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

var visual_recognition = watson.visual_recognition({
  username: '<username>',
  password: '<password>',
  version: 'v1'
});

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

visual_recognition.recognize(params, function(err, res) {
  if (err)
    console.log(err);
  else
    console.log(JSON.stringify(res, 'labels', 2));
});

Running in Bluemix

By default, the wrapper tries to use the Bluemix VCAP_SERVICES environment variable to get the credentials for a given service. You can avoid this by using: use_vcap_services.

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

var concept_expansion = watson.concept_expansion({
  version: 'v1',
  use_vcap_services: false
});

This example fails because you did not provide a username and password and the wrapper will not look into Bluemix for these values.

Unauthenticated requests

By default, the wrapper 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 dialog = watson.dialog({
  version: 'v1',
  use_unauthenticated: true
});

Debug

This wrapper 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.