langchain.js
    Preparing search index...

    Interface ChatZhipuAIParams

    Interface defining the input to the ZhipuAIChatInput class.

    interface ChatZhipuAIParams {
        apiKey?: string;
        doSample?: boolean;
        maxTokens?: number;
        messages?: ZhipuMessage[];
        model: ModelName;
        modelName: ModelName;
        requestId?: string;
        stop?: string[];
        streaming?: boolean;
        temperature?: number;
        topP?: number;
        zhipuAIApiKey?: string;
    }

    Implemented by

    Index

    Properties

    apiKey? doSample? maxTokens? messages? model modelName requestId? stop? streaming? temperature? topP? zhipuAIApiKey?

    Properties

    apiKey?: string

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

    doSample?: boolean

    turn on sampling strategy when do_sample is true, do_sample is false, temperature、top_p will not take effect

    maxTokens?: number

    max value is 8192，defaults to 1024

    messages?: ZhipuMessage[]

    Messages to pass as a prefix to the prompt

    model: ModelName
    "glm-3-turbo"
    modelName: ModelName

    "glm-3-turbo" Alias for model

    requestId?: string

    Unique identifier for the request. Defaults to a random UUID.

    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 0.95

    topP?: number

    Total probability mass of tokens to consider at each step. Range from 0 to 1 Defaults to 0.7

    zhipuAIApiKey?: string

    API key to use when making requests. Defaults to the value of ZHIPUAI_API_KEY environment variable. Alias for apiKey

    Settings

    Member Visibility

    On This Page

    Properties