Interface PromptModelInferenceConfiguration.Builder

    • Method Detail

      • maxTokens

        PromptModelInferenceConfiguration.Builder maxTokens​(Integer maxTokens)

        The maximum number of tokens to return in the response.

        Parameters:
        maxTokens - The maximum number of tokens to return in the response.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • stopSequences

        PromptModelInferenceConfiguration.Builder stopSequences​(Collection<String> stopSequences)

        A list of strings that define sequences after which the model will stop generating.

        Parameters:
        stopSequences - A list of strings that define sequences after which the model will stop generating.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • stopSequences

        PromptModelInferenceConfiguration.Builder stopSequences​(String... stopSequences)

        A list of strings that define sequences after which the model will stop generating.

        Parameters:
        stopSequences - A list of strings that define sequences after which the model will stop generating.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • temperature

        PromptModelInferenceConfiguration.Builder temperature​(Float temperature)

        Controls the randomness of the response. Choose a lower value for more predictable outputs and a higher value for more surprising outputs.

        Parameters:
        temperature - Controls the randomness of the response. Choose a lower value for more predictable outputs and a higher value for more surprising outputs.
        Returns:
        Returns a reference to this object so that method calls can be chained together.
      • topP

        PromptModelInferenceConfiguration.Builder topP​(Float topP)

        The percentage of most-likely candidates that the model considers for the next token.

        Parameters:
        topP - The percentage of most-likely candidates that the model considers for the next token.
        Returns:
        Returns a reference to this object so that method calls can be chained together.