Interface ChatOpenAICallOptions

interface ChatOpenAICallOptions {
    audio?: ChatCompletionAudioParam;
    callbacks?: Callbacks;
    configurable?: Record<string, any>;
    function_call?: FunctionCallOption;
    functions?: FunctionDefinition[];
    maxConcurrency?: number;
    metadata?: Record<string, unknown>;
    modalities?: ChatCompletionModality[];
    options?: OpenAICoreRequestOptions<Record<string, unknown>>;
    parallel_tool_calls?: boolean;
    prediction?: ChatCompletionPredictionContent;
    promptIndex?: number;
    recursionLimit?: number;
    response_format?: ChatOpenAIResponseFormat;
    runId?: string;
    runName?: string;
    seed?: number;
    signal?: AbortSignal;
    stop?: string[];
    stream_options?: {
        include_usage: boolean;
    };
    strict?: boolean;
    tags?: string[];
    timeout?: number;
    tool_choice?: OpenAIToolChoice;
    tools?: ChatOpenAIToolType[];
}

Hierarchy (view full)

Properties

audio? callbacks? configurable? function_call? functions? maxConcurrency? metadata? modalities? options? parallel_tool_calls? prediction? promptIndex? recursionLimit? response_format? runId? runName? seed? signal? stop? stream_options? strict? tags? timeout? tool_choice? tools?

Properties

Optionalaudio

audio?: ChatCompletionAudioParam

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

Optionalcallbacks

callbacks?: Callbacks

Callbacks for this call and any sub-calls (eg. a Chain calling an LLM). Tags are passed to all callbacks, metadata is passed to handle*Start callbacks.

Optionalconfigurable

configurable?: Record<string, any>

Runtime values for attributes previously made configurable on this Runnable, or sub-Runnables.

Optionalfunction_call

function_call?: FunctionCallOption

Optionalfunctions

functions?: FunctionDefinition[]

OptionalmaxConcurrency

maxConcurrency?: number

Maximum number of parallel calls to make.

Optionalmetadata

metadata?: Record<string, unknown>

Metadata for this call and any sub-calls (eg. a Chain calling an LLM). Keys should be strings, values should be JSON-serializable.

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"]

Optionaloptions

options?: OpenAICoreRequestOptions<Record<string, unknown>>

Additional options to pass to the underlying axios request.

Optionalparallel_tool_calls

parallel_tool_calls?: boolean

Whether or not to restrict the ability to call multiple tools in one response.

Optionalprediction

prediction?: ChatCompletionPredictionContent

Static predicted output content, such as the content of a text file that is being regenerated. Learn more.

OptionalpromptIndex

promptIndex?: number

OptionalrecursionLimit

recursionLimit?: number

Maximum number of times a call can recurse. If not provided, defaults to 25.

Optionalresponse_format

response_format?: ChatOpenAIResponseFormat

OptionalrunId

runId?: string

Unique identifier for the tracer run for this call. If not provided, a new UUID will be generated.

OptionalrunName

runName?: string

Name for the tracer run for this call. Defaults to the name of the class.

Optionalseed

seed?: number

Optionalsignal

signal?: AbortSignal

Abort signal for this call. If provided, the call will be aborted when the signal is aborted.

See

https://developer.mozilla.org/en-US/docs/Web/API/AbortSignal

Optionalstop

stop?: string[]

Stop tokens to use for this call. If not provided, the default stop tokens for the model will be used.

Optionalstream_options

stream_options?: {
    include_usage: boolean;
}

Additional options to pass to streamed completions. If provided takes precedence over "streamUsage" set at initialization time.

Type declaration

  • include_usage: boolean

    Whether or not to include token usage in the stream. If set to true, this will include an additional chunk at the end of the stream with the token usage.

Optionalstrict

strict?: boolean

If true, model output is guaranteed to exactly match the JSON Schema provided in the tool definition. If true, the input schema will also be validated according to https://platform.openai.com/docs/guides/structured-outputs/supported-schemas.

If false, input schema will not be validated and model output will not be validated.

If undefined, strict argument will not be passed to the model.

Version

0.2.6

Optionaltags

tags?: string[]

Tags for this call and any sub-calls (eg. a Chain calling an LLM). You can use these to filter calls.

Optionaltimeout

timeout?: number

Timeout for this call in milliseconds.

Optionaltool_choice

tool_choice?: OpenAIToolChoice

Optionaltools

tools?: ChatOpenAIToolType[]

Settings

Member Visibility

On This Page

Properties