npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

@botonic/plugin-hubtype-babel

v0.30.0

Published

Use Hubtype Babel to predict Intents.

Downloads

126

Readme

Botonic Plugin Hubtype Babel

What Does This Plugin Do?

This plugin allows you to integrate Hubtype Babel in your Botonic project. It works like any other AI/NLU services plugin, like Dialogflow, Watson, etc.

Once installed within your project, this plugin sends all text inputs that users are sending to your bot and queries Hubtype Babel API. The plugin retrieves the call results to enhance the input object. You can then use this data in your routes and actions.

Here is an example of an input object received from a user:

{
    "type": "text",
    "data": "Where is my order?"
}

Example of the same input object after being processed by this plugin:

{
    "type": "text",
    "data": "I want to talk with an agent"
    "intent": "help"
    "confidence": 0.9987
    "intents": [
      {
        "intent": "help",
        "confidence": 0.9987
      },
      {
        "intent": "greeting",
        "confidence": 0.0010
      },
      {
        "intent": "insult",
        "confidence": 0.0003
      }
    ],
    "hasSense": true,
    "entities": []  // Currently not supported
}

Setup

  1. Install the plugin from npm (or yarn):
npm i --save @botonic/plugin-hubtype-babel
  1. Add it to the src/plugins.js file defining the projectId of the Project you want to use:
export const plugins = [
  {
    id: 'hubtype-babel',
    resolve: require('@botonic/plugin-hubtype-babel'),
    options: {
      projectId: '6800762a-03b5-419e-be97-67feac7bc5b9',
    },
  },
]

Use

You can use it in your routes like any other NLP plugins:

export const routes = [{ intent: 'order-location', action: OrderLocation }]

Or you can use it in your actions:

import React from 'react'
import { Text } from '@botonic/react'

export default class OrderLocation extends React.Component {
  static async botonicInit({ input }) {
    if (
      input.intents &&
      input.intents.length > 0 &&
      input.intents[0].score > 0.6
    )
      return { response: input.intents[0].attributeArrays.ANSWER_TEXT }
  }
  render() {
    return this.props.response ? (
      <Text>{this.props.response}</Text>
    ) : (
      <Text>I don't know what you're talking about</Text>
    )
  }
}

Plugin Options

  • projectId: Id of the project used to predict the intent.
  • [includeHasSense]: Whether to include if the input text has sense or not.
    • Default: False.
  • [automaticBotMessagePrefix]: Prefix of an automatic bot message added to the input text. If a message has this prefix, inference will not be executed.
    • Default: '[Automatic Bot Message]'.
  • [host]: Host uri where to request inference.
    • Default: https://api.hubtype.com.
  • [authToken]: Authorization Token to being able to run inference. Only needed when using the plugin locally.