Streaming

LangFlux supports streaming back to your front end application when the final node is a Chain or OpenAI Function Agent.

1. Install socket.io-client to your front-end application

yarn add socket.io-client

or using npm

npm install socket.io-client

Refer official docs for more installation options.

1. Import it

import socketIOClient from 'socket.io-client'

1. Establish connection

const socket = socketIOClient("http://localhost:3000") //flowise url

1. Listen to connection

import { useState } from 'react'

const [socketIOClientId, setSocketIOClientId] = useState('');

socket.on('connect', () => {
  setSocketIOClientId(socket.id)
});

1. Send query with socketIOClientId

async function query(data) {
    const response = await fetch(
        "http://localhost:3000/api/v1/prediction/<chatflow-id>",
        {
            method: "POST",
            body: data
        }
    );
    const result = await response.json();
    return result;
}

query({
  "question": "Hey, how are you?",
  "socketIOClientId": socketIOClientId
}).then((response) => {
    console.log(response);
});

1. Listen to token stream

socket.on('start', () => {
  console.log('start');
});

socket.on('token', (token) => {
  console.log('token:', token);
});

socket.on('sourceDocuments', (sourceDocuments) => {
  console.log('sourceDocuments:', sourceDocuments);
});

socket.on('end', () => {
  console.log('end');
});

1. Disconnect connection

socket.disconnect();