本页还没有译文
本页 9 段还没译成日本語,下面显示的是英文原文。experimental_startBatch
还没翻译译自英文(ai-sdk.dev)本页 9 段都还没译
Warning
Batch support is experimental and the API may change in patch releases.
Starts an asynchronous batch of text or image generation requests. For a complete guide to the batch lifecycle, see Batch.
import { experimental_startBatch as startBatch } from 'ai';
const batch = await startBatch({
requests: [
{
id: 'france',
type: 'text',
model: 'gpt-5.4-nano',
prompt: 'What is the capital of France?',
},
],
});Import
import { experimental_startBatch } from "ai"API Signature
Parameters
provider?(Experimental_BatchProvider): The provider to use. Defaults to the global provider, or the AI Gateway when no global provider is configured.requests(Array<Experimental_BatchRequest>): The independent requests to process. Each request must have a unique, non-empty id, a supported type, and type-specific properties such as model and prompt or messages for text requests.providerOptions?(ProviderOptions): Additional provider-specific options for the batch.webhookUrl?(string): URL to notify when the batch reaches a terminal state. Support and payloads are provider-specific.abortSignal?(AbortSignal): An optional abort signal to cancel the request that starts the batch.timeout?(number | { totalMs?: number }): Maximum time allowed for the batch creation request.headers?(Record<string, string | undefined>): Additional HTTP headers for the request.
Returns
version(2): Version of the serializable batch reference.id(string): Provider batch identifier.provider(string): Provider identifier for the batch.status('pending' | 'completed' | 'failed'): Initial normalized batch status.rawStatus?(string): The provider-specific batch status, when available.requestCounts?({ total: number; pending: number; completed: number; failed: number }): Provider-reported request counts.error?(Experimental_BatchError): Error details when the batch fails.createdAt?(string): Creation timestamp, when provided by the provider.expiresAt?(string): Expiration timestamp, when provided by the provider.providerMetadata?(ProviderMetadata): Provider-specific metadata for the batch.warnings(Warning[]): Warnings returned while starting the batch.
AI 翻译查看英文原文