langchain.js
    Preparing search index...

    Interface ChatMoonshotParams

    Interface defining the input to the MoonshotChatInput class.

    interface ChatMoonshotParams {
        apiKey?: string;
        frequencyPenalty?: number;
        maxTokens?: number;
        messages?: MoonshotMessage[];
        model: ModelName;
        modelName: ModelName;
        n?: number;
        presencePenalty?: number;
        stop?: string[];
        streaming?: boolean;
        temperature?: number;
        topP?: number;
    }

    Implemented by

    Index

    Properties

    apiKey? frequencyPenalty? maxTokens? messages? model modelName n? presencePenalty? stop? streaming? temperature? topP?

    Properties

    apiKey?: string

    API key to use when making requests. Defaults to the value of MOONSHOT_API_KEY environment variable.

    frequencyPenalty?: number

    Frequency penalty, a number between -2.0 and 2.0. Positive values penalize the newly generated words based on their existing frequency in the text, making the model less likely to repeat the same words verbatim. The default value is 0

    maxTokens?: number

    Different models have different maximum values. For example, the maximum value of moonshot-v1-8k is 8192. Defaults to 1024

    messages?: MoonshotMessage[]

    Messages to pass as a prefix to the prompt

    model: ModelName
    "moonshot-v1-8k"
    modelName: ModelName

    "moonshot-v1-8k" Alias for model

    n?: number

    The default value is 1 and cannot be greater than 5. In particular, when temperature is very small and close to 0, we can only return 1 result. If n is already set and > 1, Moonshot will return an invalid input parameter (invalid_request_error).

    presencePenalty?: number

    There is a penalty, a number between -2.0 and 2.0. Positive values penalize the newly generated words based on whether they appear in the text, increasing the likelihood that the model will discuss new topics. The default value is 0

    stop?: string[]
    streaming?: boolean

    Whether to stream the results or not. Defaults to false.

    temperature?: number

    Amount of randomness injected into the response. Ranges from 0 to 1 (0 is not included). Use temp closer to 0 for analytical / multiple choice, and temp closer to 1 for creative and generative tasks. Defaults to 0, recommended 0.3

    topP?: number

    Total probability mass of tokens to consider at each step. Range from 0 to 1. Defaults to 1

    Settings

    Member Visibility

    On This Page

    Properties