AI
streaming

Express

You can use the AI SDK in an Express server to generate and stream text and objects to the client.

Examples

The examples start a simple HTTP server that listens on port 8080. You can e.g. test it using curl:

curl -X POST http://localhost:8080

The examples use the OpenAI gpt-4o model. Ensure that the OpenAI API key is set in the OPENAI_API_KEY environment variable.

Full example: github.com/vercel/ai/examples/express

Data Stream

You can use the pipeDataStreamToResponse method to pipe the stream data to the server response.

import { openai } from '@ai-sdk/openai';
import { streamText } from 'ai';
import express, { Request, Response } from 'express';


const app = express();


app.post('/', async (req: Request, res: Response) => {
  const result = streamText({
    model: openai('gpt-4o'),
    prompt: 'Invent a new holiday and describe its traditions.',
  });


  result.pipeDataStreamToResponse(res);
});


app.listen(8080, () => {
  console.log(`Example app listening on port ${8080}`);
});

Data Stream With Stream Data

pipeDataStreamToResponse can be used with StreamData to send additional data to the client.

import { openai } from '@ai-sdk/openai';
import { StreamData, streamText } from 'ai';
import express, { Request, Response } from 'express';


const app = express();


app.post('/', async (req: Request, res: Response) => {
  // use stream data (optional):
  const data = new StreamData();
  data.append('initialized call');


  const result = streamText({
    model: openai('gpt-4o'),
    prompt: 'Invent a new holiday and describe its traditions.',
    onFinish() {
      data.append('call completed');
      data.close();
    },
  });


  result.pipeDataStreamToResponse(res, { data });
});


app.listen(8080, () => {
  console.log(`Example app listening on port ${8080}`);
});

Text Stream

You can send a text stream to the client using pipeTextStreamToResponse.

import { openai } from '@ai-sdk/openai';
import { streamText } from 'ai';
import express, { Request, Response } from 'express';


const app = express();


app.post('/', async (req: Request, res: Response) => {
  const result = streamText({
    model: openai('gpt-4o'),
    prompt: 'Invent a new holiday and describe its traditions.',
  });


  result.pipeTextStreamToResponse(res);
});


app.listen(8080, () => {
  console.log(`Example app listening on port ${8080}`);
});