Package com.chatmotorapi.api.functional

Class MotorLargeTranslationRequest

java.lang.Object
com.chatmotorapi.api.functional.MotorLargeTranslationRequest
public class MotorLargeTranslationRequest
extends Object
Handles the creation and execution of translation requests using the ChatMotor API. This class is designed to translate text documents using OpenAI's advanced translation models configured through the ChatMotor. The model to be used in requests can be specified with the .aiModel setter directly on the MotorSummaryRequest builder. If .aiModel is not called, the default model used is System.getenv("MOTOR_CHAT_MODEL"). If the environment variable is not set, the model used is MotorDefaultsModels.MOTOR_CHAT_MODEL

The userInputStreaming(boolean userInputStreaming) option:
When setting up the MotorLargeTranslationRequest, you can choose between two implementations for handling large translation requests:
  • Input Streaming: If useInputStreaming is set to true, the streaming implementation using Sax Parser and TagSoup is used. This method is more efficient for large files, as it processes data in a stream, reducing memory consumption. However, it may be less robust in this beta version.
  • In-Memory Processing: If useInputStreaming is set to false (default), the Jsoup implementation is used, which loads files entirely into memory before processing. This approach is simpler and more reliable but can be less efficient for very large files.

You can add a ProgressListener to the request to track progress using .progressListener(ProgressListener progressListener). See the User Guide for more info.

Usage example: 


 String documentPath = "/path/to/my_document.html";
 String responseFilePath = "/path/to/my_document_translated.html";
 
 // We assume that the env var MOTOR_API_KEY is set.
 ChatMotor chatMotor = ChatMotor.builder()
        .build();
 
 MotorLargeTranslationRequest motorLargeTranslationRequest = MotorLargeTranslationRequest.builder()
        .chatMotor(chatMotor)
        .filePath(documentPath)
        .languageCode("fr")
      .useInputStreaming(true)
        .build();
  
 MotorLargeResponse motorLargeResponse = motorLargeTranslationRequest.execute();
 
 if (motorLargeResponse.isResponseOk()) {
     System.out.println("responseFilePath: " + responseFilePath);     
     try (InputStream in = largeReponse.getInputStream()) {
         Files.copy(in, Paths.get(responseFilePath), StandardCopyOption.REPLACE_EXISTING);
     } 
 }
 else {
     // Treat errors
     // See the MotorLargeResponse class for more details.
 }

This class uses a builder pattern to ensure a flexible and secure way to configure each translation request.

  • Method Details

    • chatMotor

      public ChatMotor chatMotor()
      Gets the ChatMotor to be used in the request.
      Returns:
      the

    • aiOptions

      public MotorAiOptions aiOptions()
      Gets the AI options to be used in the request.
      Returns:
      the AI options to be used in the request

    • aiModel

      public String aiModel()
      Gets the AI model to be used in the request.
      Returns:
      the AI model to be used in the request

    • filePath

      public String filePath()
      Gets the file path to be used in the request.
      Returns:
      the file path to be used in the request

    • languageCode

      public String languageCode()
      Gets the language code to be used in the request.
      Returns:
      the language code to be used in the request

    • inputChunkSize

      public ChunkSize inputChunkSize()
      Returns the input chunk size
      Returns:
      the input chunk size

    • useInputStreaming

      public boolean useInputStreaming()
      Returns whether streaming of input file is enabled for the request
      Returns:
      true if streaming of input file is enabled, false otherwise

    • progressListener

      public ProgressListener progressListener()
      Gets the ProgressListener to be used in the request.
      Returns:
      the ProgressListener instance

    • builder

      public static MotorLargeTranslationRequest.Builder builder()
      Returns a new builder instance for creating a MotorLargeTranslationRequest.
      Returns:
      a new MotorLargeTranslationRequest builder

    • execute

      public MotorLargeResponse execute() throws MotorExecutionException
      Executes the process of generating a translation from a specified file using a GPT model. This method initializes a session with necessary configurations, reads the text file, and creates a summary. based on the text content.
      Returns:
      the MotorLargeResponse instance.
      Throws:
      MotorExecutionException - if there is an error reading the file.

    • executeAsStream

      public MotorStreamStatus executeAsStream​(MotorResponseListener motorResponseListener)
      Executes the process of generating a translation from a specified file using a GPT model.
      The configured request is executed as a stream.
      This is valid only of request with a text format with less that 4096 tokens, aka less than 1MB.
      Parameters:
      motorResponseListener - The listener that will handle the streamed data chunks.
      Returns:
      An instance of MotorStreamStatus that contains information about the outcome of the streaming operation.