Nest.js
You can use the AI SDK in a Nest.js server to generate and stream text and objects to the client.
Examples
The examples show how to implement a Nest.js controller that uses the AI SDK to stream text and objects to the client.
Full example: github.com/vercel/ai/examples/nest
UI Message Stream
You can use the pipeUIMessageStreamToResponse helper to pipe the stream data to the server response.
app.controller.ts
import { Controller, Post, Res } from '@nestjs/common';import { pipeUIMessageStreamToResponse, streamText, toUIMessageStream,} from 'ai';import { Response } from 'express';
@Controller()export class AppController { @Post('/') async root(@Res() res: Response) { const result = streamText({ model: 'openai/gpt-4o', prompt: 'Invent a new holiday and describe its traditions.', });
pipeUIMessageStreamToResponse({ response: res, stream: toUIMessageStream({ stream: result.stream }), }); }}Sending Custom Data
createUIMessageStream and pipeUIMessageStreamToResponse can be used to send custom data to the client.
app.controller.ts
import { Controller, Post, Res } from '@nestjs/common';import { createUIMessageStream, streamText, pipeUIMessageStreamToResponse, toUIMessageStream,} from 'ai';import { Response } from 'express';
@Controller()export class AppController { @Post('/stream-data') async streamData(@Res() response: Response) { const stream = createUIMessageStream({ execute: ({ writer }) => { // write some data writer.write({ type: 'start' });
writer.write({ type: 'data-custom', data: { custom: 'Hello, world!', }, });
const result = streamText({ model: 'openai/gpt-4o', prompt: 'Invent a new holiday and describe its traditions.', }); writer.merge( toUIMessageStream({ stream: result.stream, sendStart: false, onError: error => { // Error messages are masked by default for security reasons. // If you want to expose the error message to the client, you can do so here: return error instanceof Error ? error.message : String(error); }, }), ); }, }); pipeUIMessageStreamToResponse({ stream, response }); }}Text Stream
You can use the pipeTextStreamToResponse helper with toTextStream to pipe a text stream to the response.
app.controller.ts
import { Controller, Post, Res } from '@nestjs/common';import { pipeTextStreamToResponse, streamText, toTextStream } from 'ai';import { Response } from 'express';
@Controller()export class AppController { @Post() async example(@Res() res: Response) { const result = streamText({ model: 'openai/gpt-4o', prompt: 'Invent a new holiday and describe its traditions.', });
pipeTextStreamToResponse({ response: res, stream: toTextStream({ stream: result.stream }), }); }}Troubleshooting
- Streaming not working when proxied