Interface ChatModelConfig

public interface ChatModelConfig

  • Method Summary

    Modifier and Type
    Method
    Description
    Optional<String>
    deploymentName()
    This property will override the quarkus.langchain4j.azure-openai.deployment-name specifically for chat models if it is set.
    Optional<String>
    domainName()
    This property will override the quarkus.langchain4j.azure-openai.domain-name specifically for chat models if it is set.
    Optional<String>
    endpoint()
    This property will override the quarkus.langchain4j.azure-openai.endpoint specifically for chat models if it is set.
    Double
    frequencyPenalty()
    Number between -2.0 and 2.0.
    Optional<Boolean>
    logRequests()
    Whether chat model requests should be logged
    Optional<Boolean>
    logResponses()
    Whether chat model responses should be logged
    Optional<Integer>
    maxTokens()
    The maximum number of tokens to generate in the completion.
    Double
    presencePenalty()
    Number between -2.0 and 2.0.
    Optional<String>
    resourceName()
    This property will override the quarkus.langchain4j.azure-openai.resource-name specifically for chat models if it is set.
    Optional<String>
    responseFormat()
    The response format the model should use.
    Double
    temperature()
    What sampling temperature to use, with values between 0 and 2.
    Double
    topP()
    An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with topP probability mass. 0.1 means only the tokens comprising the top 10% probability mass are considered.

  • Method Details

    • resourceName

      @WithDefault("<dummy>") Optional<String> resourceName()
      This property will override the quarkus.langchain4j.azure-openai.resource-name specifically for chat models if it is set.

    • domainName

      @WithDefault("<dummy>") Optional<String> domainName()
      This property will override the quarkus.langchain4j.azure-openai.domain-name specifically for chat models if it is set.

    • deploymentName

      @WithDefault("<dummy>") Optional<String> deploymentName()
      This property will override the quarkus.langchain4j.azure-openai.deployment-name specifically for chat models if it is set.

    • endpoint

      @WithDefault("<dummy>") Optional<String> endpoint()
      This property will override the quarkus.langchain4j.azure-openai.endpoint specifically for chat models if it is set.

    • temperature

      @WithDefault("1.0") Double temperature()
      What sampling temperature to use, with values between 0 and 2. Higher values means the model will take more risks. A value of 0.9 is good for more creative applications, while 0 (argmax sampling) is good for ones with a well-defined answer. It is recommended to alter this or topP, but not both.

    • topP

      @WithDefault("1.0") Double topP()
      An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with topP probability mass. 0.1 means only the tokens comprising the top 10% probability mass are considered. It is recommended to alter this or temperature, but not both.

    • maxTokens

      Optional<Integer> maxTokens()
      The maximum number of tokens to generate in the completion. The token count of your prompt plus max_tokens can't exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).

    • presencePenalty

      @WithDefault("0") Double presencePenalty()
      Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

    • frequencyPenalty

      @WithDefault("0") Double frequencyPenalty()
      Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

    • logRequests

      @ConfigDocDefault("false") Optional<Boolean> logRequests()
      Whether chat model requests should be logged

    • logResponses

      @ConfigDocDefault("false") Optional<Boolean> logResponses()
      Whether chat model responses should be logged

    • responseFormat

      Optional<String> responseFormat()
      The response format the model should use. Some models are not compatible with some response formats, make sure to review OpenAI documentation.