Interface OpenAIChatInput

interface OpenAIChatInput {
    apiKey?: string;
    audio?: ChatCompletionAudioParam;
    frequencyPenalty: number;
    logitBias?: Record<string, number>;
    logprobs?: boolean;
    maxTokens?: number;
    modalities?: ChatCompletionModality[];
    model: string;
    modelKwargs?: Record<string, any>;
    modelName: string;
    n: number;
    openAIApiKey?: string;
    prefixMessages?: ChatCompletionMessageParam[];
    presencePenalty: number;
    stop?: string[];
    stopSequences?: string[];
    streamUsage?: boolean;
    streaming: boolean;
    supportsStrictToolCalling?: boolean;
    temperature: number;
    timeout?: number;
    topLogprobs?: number;
    topP: number;
    user?: string;
}

Hierarchy (view full)

Implemented by

Properties

apiKey? audio? frequencyPenalty logitBias? logprobs? maxTokens? modalities? model modelKwargs? modelName n openAIApiKey? prefixMessages? presencePenalty stop? stopSequences? streamUsage? streaming supportsStrictToolCalling? temperature timeout? topLogprobs? topP user?

Properties

OptionalapiKey

apiKey?: string

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

Optionalaudio

audio?: ChatCompletionAudioParam

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

frequencyPenalty

frequencyPenalty: number

Penalizes repeated tokens according to frequency

OptionallogitBias

logitBias?: Record<string, number>

Dictionary used to adjust the probability of specific tokens being generated

Optionallogprobs

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.

OptionalmaxTokens

maxTokens?: number

Maximum number of tokens to generate in the completion. -1 returns as many tokens as possible given the prompt and the model's maximum context size.

Optionalmodalities

modalities?: ChatCompletionModality[]

Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

["text", "audio"]

model

model: string

Model name to use

OptionalmodelKwargs

modelKwargs?: Record<string, any>

Holds any additional parameters that are valid to pass to openai.createCompletion that are not explicitly specified on this class.

modelName

modelName: string

Model name to use Alias for model

n

n: number

Number of completions to generate for each prompt

OptionalopenAIApiKey

openAIApiKey?: string

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

OptionalprefixMessages

prefixMessages?: ChatCompletionMessageParam[]

ChatGPT messages to pass as a prefix to the prompt

presencePenalty

presencePenalty: number

Penalizes repeated tokens

Optionalstop

stop?: string[]

List of stop words to use when generating Alias for stopSequences

OptionalstopSequences

stopSequences?: string[]

List of stop words to use when generating

OptionalstreamUsage

streamUsage?: boolean

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

Default

true

streaming

streaming: boolean

Whether to stream the results or not. Enabling disables tokenUsage reporting

OptionalsupportsStrictToolCalling

supportsStrictToolCalling?: boolean

Whether the model supports the strict argument when passing in tools. If undefined the strict argument will not be passed to OpenAI.

temperature

temperature: number

Sampling temperature to use

Optionaltimeout

timeout?: number

Timeout to use when making requests to OpenAI.

OptionaltopLogprobs

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

topP: number

Total probability mass of tokens to consider at each step

Optionaluser

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