content/cookbook/20-rsc/30-generate-object.mdx
You can use generateText with Output to generate structured data like JSON. By providing a schema that describes the structure of your desired object, the SDK will validate the generated output and ensure that it conforms to the specified structure.
The Output.object function requires you to provide a schema using zod, a library for defining schemas for JavaScript objects.
Let's create a simple React component that will call the getNotifications 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 { getNotifications } from './actions';
// 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 { notifications } = await getNotifications(
'Messages during finals week.',
);
setGeneration(JSON.stringify(notifications, null, 2));
}}
>
View Notifications
</button>
<pre>{generation}</pre>
</div>
);
}
Now let's implement the getNotifications function. We'll use the generateText function with Output.object to generate the list of notifications based on the schema we defined earlier.
'use server';
import { generateText, Output } from 'ai';
import { openai } from '@ai-sdk/openai';
import { z } from 'zod';
export async function getNotifications(input: string) {
'use server';
const { output: notifications } = await generateText({
model: openai('gpt-4.1'),
system: '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(),
}),
),
}),
}),
});
return { notifications };
}