Stream Object | AI SDK 日本語

Note

This example uses React Server Components (RSC). If you want to client side rendering and hooks instead, check out the "streaming object generation" example with useObject.

Object generation can sometimes take a long time to complete, especially when you're generating a large schema. In such cases, it is useful to stream the object generation process to the client in real-time. This allows the client to display the generated object as it is being generated, rather than have users wait for it to complete before displaying the result.

This part of the page is interactive; see it on the original page.

Client

Let's create a simple React component that will call the generate function when a button is clicked. The function will generate a list of notifications as described in the schema.

'use client';

import { useState } from 'react';
import { generate } from './actions';
import { readStreamableValue } from '@ai-sdk/rsc';

// Allow streaming responses up to 30 seconds
export const maxDuration = 30;

export default function Home() {
  const [generation, setGeneration] = useState<string>('');

  return (
    <div>
      <button
        onClick={async () => {
          const { object } = await generate('Messages during finals week.');

          for await (const partialObject of readStreamableValue(object)) {
            if (partialObject) {
              setGeneration(
                JSON.stringify(partialObject.notifications, null, 2),
              );
            }
          }
        }}
      >
        Ask
      </button>

      <pre>{generation}</pre>
    </div>
  );
}

Server

Now let's implement the generate function. We'll use the streamText function with Output.object to stream the list of fictional notifications based on the schema we defined earlier.

'use server';

import { streamText, Output } from 'ai';
import { createStreamableValue } from '@ai-sdk/rsc';
import { z } from 'zod';

export async function generate(input: string) {
  'use server';

  const stream = createStreamableValue();

  (async () => {
    const { partialOutputStream } = streamText({
      model: 'openai/gpt-6-astra',
      instructions: 'You generate three notifications for a messages app.',
      prompt: input,
      output: Output.object({
        schema: z.object({
          notifications: z.array(
            z.object({
              name: z.string().describe('Name of a fictional person.'),
              message: z.string().describe('Do not use emojis or links.'),
              minutesAgo: z.number(),
            }),
          ),
        }),
      }),
    });

    for await (const partialObject of partialOutputStream) {
      stream.update(partialObject);
    }

    stream.done();
  })();

  return { object: stream.value };
}