langchain.js
    Preparing search index...

    Interface ChatGroqInput

    interface ChatGroqInput {
        apiKey?: string;
        baseUrl?: string;
        defaultHeaders?: Record<string, string>;
        defaultQuery?: Record<string, string>;
        fetch?: (...args: any) => any;
        frequencyPenalty?: number;
        httpAgent?: any;
        logitBias?: Record<string, number>;
        logprobs?: boolean;
        maxTokens?: number;
        model: string;
        n?: number;
        presencePenalty?: number;
        stop?: null | string | string[];
        stopSequences?: string[];
        streaming?: boolean;
        streamUsage?: boolean;
        temperature?: number;
        timeout?: number;
        topLogprobs?: number;
        topP?: number;
        user?: string;
    }

    Hierarchy (View Summary)

    Index

    Properties

    apiKey? baseUrl? defaultHeaders? defaultQuery? fetch? frequencyPenalty? httpAgent? logitBias? logprobs? maxTokens? model n? presencePenalty? stop? stopSequences? streaming? streamUsage? temperature? timeout? topLogprobs? topP? user?

    Properties

    apiKey?: string

    The Groq API key to use for requests.

    process.env.GROQ_API_KEY
    baseUrl?: string

    Override the default base URL for the API

    defaultHeaders?: Record<string, string>

    Default headers included with every request

    defaultQuery?: Record<string, string>

    Default query parameters included with every request

    fetch?: (...args: any) => any

    Custom fetch function implementation

    frequencyPenalty?: number

    Penalizes repeated tokens according to frequency

    httpAgent?: any

    HTTP agent used to manage connections

    logitBias?: Record<string, number>

    Dictionary used to adjust the probability of specific tokens being generated

    logprobs?: boolean

    Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

    maxTokens?: number

    The maximum number of tokens that the model can process in a single response. This limits ensures computational efficiency and resource management.

    model: string

    The name of the model to use.

    n?: number

    Number of completions to generate for each prompt

    presencePenalty?: number

    Penalizes repeated tokens

    stop?: null | string | string[]

    Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. Alias for stopSequences

    stopSequences?: string[]

    Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

    streaming?: boolean

    Whether or not to stream responses.

    streamUsage?: boolean

    Whether or not to include token usage data in streamed chunks.

    true
    temperature?: number

    The temperature to use for sampling.

    0.7
    timeout?: number

    The maximum amount of time (in milliseconds) the client will wait for a response

    topLogprobs?: number

    An integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

    topP?: number

    Total probability mass of tokens to consider at each step

    user?: string

    Unique string identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

    Settings

    Member Visibility

    On This Page

    Properties