DefaultSettingsMiddleware

Namespace: Vercel.AI

public sealed class DefaultSettingsMiddleware : LanguageModelMiddleware, ILanguageModelMiddleware

Fills sampling settings when the caller left them unset. Maps to defaultSettingsMiddleware.

Inheritance: object → LanguageModelMiddleware

Implements: ILanguageModelMiddleware

View source

Constructors

DefaultSettingsMiddleware(double?, int?)

public DefaultSettingsMiddleware(double? temperature = null, int? maxOutputTokens = null)

Creates middleware with default sampling settings.

Parameters

Name	Type	Description
temperature	double?
maxOutputTokens	int?

View source

Properties

MaxOutputTokens

public int? MaxOutputTokens { get; }

Default max output tokens.

Value: int?

View source

Temperature

public double? Temperature { get; }

Default temperature.

Value: double?

View source

Methods

WrapGenerateAsync(LanguageModelCallOptions, Func<LanguageModelCallOptions, CancellationToken, Task<LanguageModelGenerateResult>>, CancellationToken)

public override Task<LanguageModelGenerateResult> WrapGenerateAsync(LanguageModelCallOptions options, Func<LanguageModelCallOptions, CancellationToken, Task<LanguageModelGenerateResult>> next, CancellationToken cancellationToken)

Wraps a generate call.

Parameters

Name	Type	Description
options	LanguageModelCallOptions
next	Func<LanguageModelCallOptions, CancellationToken, Task<LanguageModelGenerateResult>>
cancellationToken	CancellationToken

Returns: Task<LanguageModelGenerateResult>

View source

WrapStreamAsync(LanguageModelCallOptions, Func<LanguageModelCallOptions, CancellationToken, Task<LanguageModelStreamResult>>, CancellationToken)

public override Task<LanguageModelStreamResult> WrapStreamAsync(LanguageModelCallOptions options, Func<LanguageModelCallOptions, CancellationToken, Task<LanguageModelStreamResult>> next, CancellationToken cancellationToken)

Wraps a stream call.

Parameters

Name	Type	Description
options	LanguageModelCallOptions
next	Func<LanguageModelCallOptions, CancellationToken, Task<LanguageModelStreamResult>>
cancellationToken	CancellationToken

Returns: Task<LanguageModelStreamResult>

View source