Introduction to node-wit

node-wit is a powerful library that provides an interface to use Wit.ai, an NLP (Natural Language Processing) platform that makes it easy to build applications with highly interactive conversational capabilities. Using node-wit, developers can seamlessly integrate Wit.ai’s advanced natural language processing functionalities into their Node.js applications.

Getting Started with node-wit

const { Wit, log } = require('node-wit');
const client = new Wit({ accessToken: 'YOUR_WIT_AI_ACCESS_TOKEN' });

API Examples

Making Sense of User Input

node-wit can analyze the intent and entities from a given message:

client.message('What is the weather like in New York?', {})
  .then((data) => {
    console.log('Yay, got Wit.ai response: ' + JSON.stringify(data));
  })
  .catch(console.error);

Extracting Entities

You can extract specific entities from user messages, such as locations, dates, and more:

client.message('Schedule a meeting on next Monday', {})
  .then((data) => {
    const entities = data.entities;
    const datetime = entities['wit$datetime:datetime'] ? entities['wit$datetime:datetime'][0].value : 'Not found';
    console.log('The meeting is scheduled on: ' + datetime);
  })
  .catch(console.error);

Running Actions

Running custom actions defined in your Wit.ai app to handle more sophisticated conversations:

const actions = {
  send(request, response) {
    const { text, quickreplies } = response;
    console.log('sending...', JSON.stringify(response));
  },
  myAction(request) {
    return new Promise(function(resolve, reject) {
      console.log('executing myAction');
      return resolve();
    });
  },
};
const client = new Wit({ accessToken: 'YOUR_WIT_AI_ACCESS_TOKEN', actions });

Tracking Conversations

Using the conversation API to maintain the context of a conversation:

const sessionId = 'my-user-1234';

client.converse(sessionId, 'I want to order pizza', {})
  .then((data) => {
    console.log('Got Wit.ai response: ' + JSON.stringify(data));
  })
  .catch(console.error);

Complete App Example

Here’s a more complete example of a Node.js application using node-wit to create a simple chatbot:

const express = require('express');
const bodyParser = require('body-parser');
const { Wit, log } = require('node-wit');

const app = express();
const client = new Wit({ accessToken: 'YOUR_WIT_AI_ACCESS_TOKEN' });

app.use(bodyParser.json());

app.post('/webhook', (req, res) => {
  const { message, sessionId } = req.body;

  client.converse(sessionId, message, {})
    .then((data) => {
      res.json(data);
    })
    .catch((err) => {
      console.error(err);
      res.status(500).send('Something went wrong!');
    });
});

app.listen(3000, () => {
  console.log('Server is running on port 3000');
});

With node-wit, building conversational AI applications becomes straightforward and efficient.

Hash: ba56a19fdc7c835f3c0252f17cc65c7f870d9116744a21f545f788f78bc01980