Package dev.langchain4j.model.language

Interface TokenCountEstimator

All Known Implementing Classes:
AzureOpenAiLanguageModel, AzureOpenAiStreamingLanguageModel, OpenAiLanguageModel, OpenAiStreamingLanguageModel
public interface TokenCountEstimator
Represents an interface for estimating the count of tokens in various text types such as a text, prompt, text segment, etc. This can be useful when it's necessary to know in advance the cost of processing a specified text by the LLM.

  • Method Summary

    Modifier and Type
    Method
    Description
    default int
    estimateTokenCount(TextSegment textSegment)
    Estimates the count of tokens in the given text segment.
    default int
    estimateTokenCount(Prompt prompt)
    Estimates the count of tokens in the given prompt.
    int
    estimateTokenCount(String text)
    Estimates the count of tokens in the given text.

  • Method Details

    • estimateTokenCount

      int estimateTokenCount(String text)
      Estimates the count of tokens in the given text.
      Parameters:
      text - the text.
      Returns:
      the estimated count of tokens.

    • estimateTokenCount

      default int estimateTokenCount(Prompt prompt)
      Estimates the count of tokens in the given prompt.
      Parameters:
      prompt - the prompt.
      Returns:
      the estimated count of tokens.

    • estimateTokenCount

      default int estimateTokenCount(TextSegment textSegment)
      Estimates the count of tokens in the given text segment.

      The metadata will not be included in the estimate.

      Parameters:
      textSegment - the text segment.
      Returns:
      the estimated count of tokens.