How to Implement Azure Cognitive Services Text Analytics API in Java

Integrate Azure Cognitive Services Text Analytics API in Java

• First, ensure you have included the necessary dependencies in your project. The Azure Cognitive Services Text Analytics library should be added using Maven or Gradle.

 

• For Maven projects, add the dependency to your `pom.xml`:

  <dependency>
      <groupId>com.azure</groupId>
      <artifactId>azure-ai-textanalytics</artifactId>
      <version>5.2.0</version>
  </dependency>
  

 

• For Gradle projects, add this to your `build.gradle`:

  implementation 'com.azure:azure-ai-textanalytics:5.2.0'
  

Setup Authentication

• You'll need to authenticate with the Azure Text Analytics service using an API key. Here's how to set it up:

 

• Set up your `TextAnalyticsClient` using the `TextAnalyticsClientBuilder` and your API key:

  import com.azure.ai.textanalytics.*;
  import com.azure.core.credential.AzureKeyCredential;
  
  public class TextAnalyticsExample {
      public static void main(String[] args) {
          String endpoint = "https://<your-text-analytics-resource>.cognitiveservices.azure.com/";
          String apiKey = "<your-api-key>";
  
          TextAnalyticsClient client = new TextAnalyticsClientBuilder()
              .credential(new AzureKeyCredential(apiKey))
              .endpoint(endpoint)
              .buildClient();
      }
  }
  

Perform Text Analysis

• Now that the client is set up, you can perform various text analysis operations such as sentiment analysis, named entity recognition, and more.

 

• Here’s an example to determine the sentiment of a given text:

  import com.azure.ai.textanalytics.models.DocumentSentiment;
  
  public class SentimentAnalysisExample {
      public static void main(String[] args) {
          // Assume client is initialized as shown earlier
          
          String text = "The hotel was clean and the staff was friendly.";
  
          DocumentSentiment documentSentiment = client.analyzeSentiment(text);
          System.out.printf("Document sentiment: %s%n", documentSentiment.getSentiment());
          documentSentiment.getSentences().forEach(sentenceSentiment ->
              System.out.printf("Sentence sentiment: %s%n", sentenceSentiment.getSentiment()));
      }
  }
  

Handle Exceptions and Errors

• Implement error handling to manage potential issues like network errors or invalid input data.

 

• Use try-catch blocks to capture and respond to `TextAnalyticsException` or any other runtime exceptions:

  import com.azure.ai.textanalytics.models.TextAnalyticsException;
  
  public class SafeTextAnalyticsExample {
      public static void main(String[] args) {
          try {
              // Assume client and text are already initialized
              
              client.analyzeSentiment(text);
          } catch (TextAnalyticsException e) {
              System.out.printf("Error Message: %s%n", e.getMessage());
              System.out.printf("Error Code: %s%n", e.getErrorCode());
          } catch (Exception e) {
              System.out.println("Unexpected error occurred: " + e);
          }
      }
  }
  

Optimize for Production

• In a production environment, you should use Azure identity management for better security instead of just relying on API keys.

 

• Monitor the performance and handle batch requests for large-scale applications to maintain efficiency and adhere to API rate limits.

import com.azure.identity.DefaultAzureCredentialBuilder;

// Example of setting up client with managed identity
public class ManagedIdentityClientExample {
    public static void main(String[] args) {
        TextAnalyticsClient client = new TextAnalyticsClientBuilder()
            .credential(new DefaultAzureCredentialBuilder().build())
            .endpoint("https://<your-text-analytics-resource>.cognitiveservices.azure.com/")
            .buildClient();
    }
}