Java client library to use the Watson Developer Cloud services, a collection of REST APIs and SDKs that use cognitive computing to solve complex problems.
- Installation
- Usage
- Getting the Service Credentials
- Questions
- IBM Watson Services
- Alchemy Language
- Alchemy Vision
- Alchemy Data News
- Concept Expansion
- Concept Insights
- Dialog
- Document Conversion
- Language Translation
- Natural Language Classifier
- Personality Insights
- Relationship Extraction
- Retrieve and Rank
- Speech to Text
- Text to Speech
- Tone Analyzer
- Tradeoff Analytics
- Visual Insights
- Visual Recognition
- Android
- Running in Bluemix
- Eclipse and Intellij
- License
- Contributing
<dependency>
<groupId>com.ibm.watson.developer_cloud</groupId>
<artifactId>java-sdk</artifactId>
<version>2.9.0</version>
</dependency>'com.ibm.watson.developer_cloud:java-sdk:2.9.0'Now, you are ready to see some examples.
The examples below assume that you already have service credentials. If not, you will have to create a service in Bluemix.
If you are running your application in Bluemix, you don't need to specify the
credentials; the library will get them for you by looking at the VCAP_SERVICES environment variable.
You will need the username and password (api_key for AlchemyAPI) credentials for each service. Service credentials are different from your Bluemix account username and password.
To get your service credentials, follow these steps:
-
Log in to Bluemix at https://bluemix.net.
-
Create an instance of the service:
- In the Bluemix Catalog, select the service you want to use.
- Under Add Service, 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. - Click Create.
-
Copy your credentials:
- On the left side of the page, click Service Credentials to view your service credentials.
- Copy
usernameandpassword(api_keyfor AlchemyAPI).
Once you have credentials, copy config.properties.example to src/test/resources/config.properties, and fill them in as necessary.
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.
The Watson Developer Cloud offers a variety of services for building cognitive applications.
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.
AlchemyLanguage service = new AlchemyLanguage();
service.setApiKey("<api_key>");
Map<String,Object> params = new HashMap<String, Object>();
params.put(AlchemyLanguage.TEXT, "IBM Watson won the Jeopardy television show hosted by Alex Trebek");
DocumentSentiment sentiment = service.getSentiment(params);
System.out.println(sentiment);Alchemy Vision uses deep learning innovations to understand a picture's content and context. It sees complex visual scenes in their entirety —without needing any textual clues— leveraging a holistic approach to understand the objects, faces, and words in an image.
Example: Extract keywords from an image.
AlchemyVision service = new AlchemyVision();
service.setApiKey("<api_key>");
File image = new File("src/test/resources/alchemy/obama.jpg");
Boolean forceShowAll = false;
Boolean knowledgeGraph = false;
ImageKeywords keywords = service.getImageKeywords(image, forceShowAll, knowledgeGraph);
System.out.println(keywords);Alchemy Data News indexes 250k to 300k English language news and blog articles every day with historical search available for the past 60 days. Example: Get 7 documents between Friday 28th August 2015 and Friday 4th September 2015.
AlchemyDataNews service = new AlchemyDataNews();
service.setApiKey("<api_key>");
Map<String, Object> params = new HashMap<String, Object>();
String[] fields =
new String[] {"enriched.url.title", "enriched.url.url", "enriched.url.author",
"enriched.url.publicationDate", "enriched.url.enrichedTitle.entities",
"enriched.url.enrichedTitle.docSentiment"};
params.put(AlchemyDataNews.RETURN, StringUtils.join(fields, ","));
params.put(AlchemyDataNews.START, "1440720000");
params.put(AlchemyDataNews.END, "1441407600");
params.put(AlchemyDataNews.COUNT, 7);
DocumentsResult result = service.getNewsDocuments(params);
System.out.println(result);Map euphemisms or colloquial terms to more commonly understood phrases using the Concept Expansion service. Example: Create a job, wait for it to finish, and then retrieve results.
ConceptExpansion service = new ConceptExpansion();
service.setUsernameAndPassword("<username>", "<password>");
String[] seeds = new String[] {"nyc", "dc", "london", "big cities"};
String label = "demo";
Job job = service.createJob(label, seeds);
while (service.getJobStatus(job) == Job.Status.AWAITING_WORK
|| service.getJobStatus(job) == Job.Status.IN_FLIGHT) {
try {
Thread.sleep(4000);
} catch (final InterruptedException e) {
e.printStackTrace();
}
}
System.out.println(service.getJobResult(job));Use the Concept Insights service to identify words in the text that correspond to concepts in a Wikipedia graph.
ConceptInsights service = new ConceptInsights();
service.setUsernameAndPassword("<username>", "<password>");
Annotations annotations = service.annotateText(Graph.WIKIPEDIA,
"IBM Watson won the Jeopardy television show hosted by Alex Trebek");
System.out.println(annotations);Returns the dialog list using the Dialog service.
DialogService service = new DialogService();
service.setUsernameAndPassword("<username>", "<password>");
List<Dialog> dialogs = service.getDialogs();
System.out.println(dialogs);The Document Conversion service allows to convert pdf, word, and html documents into formats useful to other Watson Cognitive services. Target formats include normalized html, plain text, and sets of potential answers for Watson question answering. You can convert documents synchronously one at a time, or asynchronously in batches
Returns the document list using the Document Conversion service.
DocumentConversion service = new DocumentConversion("2015-12-01");
service.setUsernameAndPassword("<username>", "<password>");
File doc = new File("src/test/resources/document_conversion/word-document-heading-input.doc");
Answers htmlToAnswers = service.convertDocumentToAnswer(doc);
System.out.println(htmlToAnswers);Select a domain, then identify or select the language of text, and then translate the text from one supported language to another.
Example: Translate 'hello' from English to Spanish using the Language Translation service.
LanguageTranslation service = new LanguageTranslation();
service.setUsernameAndPassword("<username>", "<password>");
TranslationResult translationResult = service.translate("hello", "en", "es");
System.out.println(translationResult);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.
NaturalLanguageClassifier service = new NaturalLanguageClassifier();
service.setUsernameAndPassword("<username>", "<password>");
Classification classification = service.classify("<classifier-id>", "Is it sunny?");
System.out.println(classification);Note: You will need to create and train a classifier in order to be able to classify phrases.
Use linguistic analytics to infer personality and social characteristics, including Big Five, Needs, and Values, from text.
Example: Analyze text and get a personality profile using the Personality Insights service.
PersonalityInsights service = new PersonalityInsights();
service.setUsernameAndPassword("<username>", "<password>");
// Demo content from Moby Dick by Hermann Melville (Chapter 1)
String text = "Call me Ishmael. Some years ago-never mind how long precisely-having "
+ "little or no money in my purse, and nothing particular to interest me on shore, "
+ "I thought I would sail about a little and see the watery part of the world. "
+ "It is a way I have of driving off the spleen and regulating the circulation. "
+ "Whenever I find myself growing grim about the mouth; whenever it is a damp, "
+ "drizzly November in my soul; whenever I find myself involuntarily pausing before "
+ "coffin warehouses, and bringing up the rear of every funeral I meet; and especially "
+ "whenever my hypos get such an upper hand of me, that it requires a strong moral "
+ "principle to prevent me from deliberately stepping into the street, and methodically "
+ "knocking people's hats off-then, I account it high time to get to sea as soon as I can. "
+ "This is my substitute for pistol and ball. With a philosophical flourish Cato throws himself "
+ "upon his sword; I quietly take to the ship. There is nothing surprising in this. "
+ "If they but knew it, almost all men in their degree, some time or other, cherish "
+ "very nearly the same feelings towards the ocean with me. There now is your insular "
+ "city of the Manhattoes, belted round by wharves as Indian isles by coral reefs-commerce surrounds "
+ "it with her surf. Right and left, the streets take you waterward.";
Profile profile = service.getProfile(text);
System.out.println(profile);Note: Don't forget to update the text variable! Also, if you experience
authentication errors, remember that the Personality Insights service is not
a free service.
Analyze an English news article and get the relationships between sentence components (nouns, verbs, subjects, objects, etc.) by using the Relationship Extraction service.
RelationshipExtraction service = new RelationshipExtraction();
service.setUsernameAndPassword("<username>", "<password>");
service.setDataset(Dataset.ENGLISH_NEWS);
String response = service.extract("IBM Watson Developer Cloud");
System.out.println(response);The Retrieve and Rank service helps users find the most relevant information for their query by using a combination of search and machine learning to find “signals” in the data.
RetrieveAndRank service = new RetrieveAndRank();
service.setUsernameAndPassword("<username>", "<password>");
// 1 create the Solr Cluster
SolrClusterOptions options = new SolrClusterOptions("my-cluster-name", 1);
SolrCluster cluster = service.createSolrCluster(options);
System.out.println("Solr cluster: " + cluster);
// 2 wait until the Solr Cluster is available
while (cluster.getStatus() == Status.NOT_AVAILABLE) {
Thread.sleep(10000); // sleep 10 seconds
cluster = service.getSolrCluster(cluster.getId());
System.out.println("Solr cluster status: " + cluster.getStatus());
}
// 3 list Solr Clusters
System.out.println("Solr clusters: " + service.getSolrClusters());Retrieve and Rank is built on top of Apache Solr. Look at this example to learn how to use Solrj.
Use the Speech to Text service to recognize the text from a .wav file.
SpeechToText service = new SpeechToText();
service.setUsernameAndPassword("<username>", "<password>");
File audio = new File("src/test/resources/sample1.wav");
SpeechResults transcript = service.recognize(audio, HttpMediaType.AUDIO_WAV);
System.out.println(transcript);Speech to Text supports WebSocket, the url is:
wss://stream.watsonplatform.net/speech-to-text/api/v1/recognize
We recommend you use this java client.
Use the Text to Speech service to get the available voices to synthesize.
TextToSpeech service = new TextToSpeech();
service.setUsernameAndPassword("<username>", "<password>");
List<Voice> voices = service.getVoices();
System.out.println(voices);Use the Tone Analyzer service to get the tone of your email.
ToneAnalyzer service = new ToneAnalyzer(ToneAnalyzer.VERSION_DATE_2016_02_11);
service.setUsernameAndPassword("<username>", "<password>");
String text =
"I know the times are difficult! Our sales have been "
+ "disappointing for the past three quarters for our data analytics "
+ "product suite. We have a competitive data analytics product "
+ "suite in the industry. But we need to do our job selling it! "
+ "We need to acknowledge and fix our sales challenges. "
+ "We can’t blame the economy for our lack of execution! "
+ "We are missing critical sales opportunities. "
+ "Our product is in no way inferior to the competitor products. "
+ "Our clients are hungry for analytical tools to improve their "
+ "business outcomes. Economy has nothing to do with it.";
// Call the service and get the tone
ToneAnalysis tone = service.getTone(text);
System.out.println(tone);Use the Tradeoff Analytics service to find the best phone that minimizes price and weight and maximizes screen size.
TradeoffAnalytics service = new TradeoffAnalytics();
service.setUsernameAndPassword("<username>", "<password>");
Problem problem = new Problem("phone");
String price = "price";
String ram = "ram";
String screen = "screen";
// Define the objectives
List<Column> columns = new ArrayList<Column>();
problem.setColumns(columns);
columns.add(new NumericColumn().withRange(0, 100).withKey(price).withGoal(Goal.MIN).withObjective(true));
columns.add(new NumericColumn().withKey(screen).withGoal(Goal.MAX).withObjective(true));
columns.add(new NumericColumn().withKey(ram).withGoal(Goal.MAX));
// Define the options to choose
List<Option> options = new ArrayList<Option>();
problem.setOptions(options);
HashMap<String, Object> galaxySpecs = new HashMap<String, Object>();
galaxySpecs.put(price, 50);
galaxySpecs.put(ram, 45);
galaxySpecs.put(screen, 5);
options.add(new Option("1", "Galaxy S4").withValues(galaxySpecs));
HashMap<String, Object> iphoneSpecs = new HashMap<String, Object>();
iphoneSpecs.put(price, 99);
iphoneSpecs.put(ram, 40);
iphoneSpecs.put(screen, 4);
options.add(new Option("2", "iPhone 5").withValues(iphoneSpecs));
HashMap<String, Object> optimusSpecs = new HashMap<String, Object>();
optimusSpecs.put(price, 10);
optimusSpecs.put(ram, 300);
optimusSpecs.put(screen, 5);
options.add(new Option("3", "LG Optimus G").withValues(optimusSpecs));
// Call the service and get the resolution
Dilemma dilemma = service.dilemmas(problem);
System.out.println(dilemma);Use the Visual Insights to get insight into the themes present in a collection of images based on their visual appearance/content.
VisualInsights service = new VisualInsights();
service.setUsernameAndPassword("<username>", "<password>");
File images = new File("src/test/resources/visual_insights/images.zip");
Summary summary = service.getSummary(images);
System.out.println(summary);Use the Visual Recognition service to recognize the following picture.
VisualRecognition service = new VisualRecognition();
service.setUsernameAndPassword("<username>", "<password>");
File image = new File("src/test/resources/visual_recognition/car.png");
VisualRecognitionImages recognizedImage = service.recognize(image);
System.out.println(recognizedImage);The library supports Android 2.3 and above. For Java, the minimum requirement is 1.7.
It depends on OkHttp and gson.
When running in Bluemix, the library will automatically get the credentials from VCAP_SERVICES.
If you have more than one plan, you can use BluemixUtils to get the service credentials for an specific plan.
PersonalityInsights service = new PersonalityInsights();
String apiKey = BluemixUtils.getAPIKey(service.getName(), BluemixUtils.PLAN_STANDARD);
service.setApiKey(apiKey);To build and test the project you can use Gradle (version 1.x): or Apache Maven.
Gradle:
$ cd java-sdk
$ gradle jar # build jar file (build/libs/watson-developer-cloud-2.9.0.jar)
$ gradle test # run testsor Maven:
$ cd java-sdk
$ mvn installIf you want to work on the code in an IDE instead of a text editor you can easily create project files with gradle:
$ gradle idea # Intellij IDEA
$ gradle eclipse # Eclipseor maven:
$ mvn idea:idea # Intellij IDEA
$ mvn eclipse:eclipse # EclipseFind more open source projects on the IBM Github Page
This library is licensed under Apache 2.0. Full license text is available in LICENSE.
See CONTRIBUTING.md.