Interface Tokenizer

  • All Implemented Interfaces:

    
    public interface Tokenizer
    
                        

    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.

    • Constructor Detail

    • Method Detail

      • estimateTokenCountInText

         abstract int estimateTokenCountInText(String text)

        Estimates the count of tokens in the given text.

        Parameters:
        text - the text.
        Returns:

        the estimated count of tokens.

      • estimateTokenCountInMessage

         abstract int estimateTokenCountInMessage(ChatMessage message)

        Estimates the count of tokens in the given message.

        Parameters:
        message - the message.
        Returns:

        the estimated count of tokens.

      • estimateTokenCountInMessages

         abstract int estimateTokenCountInMessages(Iterable<ChatMessage> messages)

        Estimates the count of tokens in the given messages.

        Parameters:
        messages - the messages.
        Returns:

        the estimated count of tokens.

      • estimateTokenCountInTools

         int estimateTokenCountInTools(Object objectWithTools)

        Estimates the count of tokens in Tool annotations of the given object.

        Parameters:
        objectWithTools - the object.
        Returns:

        the estimated count of tokens.

      • estimateTokenCountInTools

         int estimateTokenCountInTools(Iterable<Object> objectsWithTools)

        Estimates the count of tokens in Tool annotations of the given objects.

        Parameters:
        objectsWithTools - the objects.
        Returns:

        the estimated count of tokens.