ProdiaLanguageModel

Namespace: Vercel.AI.Prodia

public sealed class ProdiaLanguageModel : ILanguageModel

Prodia image-to-image job exposed as a language model. The last user message supplies the text and the optional input image. The result holds the returned text and images.

Inheritance: object

Implements: ILanguageModel

View source

Constructors

ProdiaLanguageModel(ProdiaProvider, string, Func<DateTimeOffset>?)

public ProdiaLanguageModel(ProdiaProvider provider, string modelId, Func<DateTimeOffset>? clock = null)

Creates a model. <code class=“paramref”>clock</code> sets the response timestamp.

Parameters

Name	Type	Description
provider	ProdiaProvider
modelId	string
clock	Func<DateTimeOffset>

View source

Properties

ModelId

public string ModelId { get; }

Model id.

Value: string

View source

Provider

public string Provider { get; }

Provider id, such as openai.

Value: string

View source

SpecificationVersion

public string SpecificationVersion { get; }

Always V4.

Value: string

View source

Methods

DoGenerateAsync(LanguageModelCallOptions, CancellationToken)

public Task<LanguageModelGenerateResult> DoGenerateAsync(LanguageModelCallOptions options, CancellationToken cancellationToken)

Generates a complete result.

Parameters

Name	Type	Description
options	LanguageModelCallOptions
cancellationToken	CancellationToken

Returns: Task<LanguageModelGenerateResult>

View source

DoStreamAsync(LanguageModelCallOptions, CancellationToken)

public Task<LanguageModelStreamResult> DoStreamAsync(LanguageModelCallOptions options, CancellationToken cancellationToken)

Runs CancellationToken) and replays the result as stream parts. Generated images are not streamed.

Parameters

Name	Type	Description
options	LanguageModelCallOptions
cancellationToken	CancellationToken

Returns: Task<LanguageModelStreamResult>

View source