Code Monkey home page Code Monkey logo

dialogflow-visualisaton's Introduction

Conversation flow visualisation for Dialogflow

This project enhance visualisation ability to your dialogflow project. It will shown you the relation of an intent that you designed for the converstion. This is a Demo.

Getting Started

Dialogflow platform provide service to create chatbot in a few click. You can build a conversation logic by create an intent, define a training phase and define a reponse to what ever you want the bot to reply. but the conversation in real life it not only question and answer. We need to consider the context of converstion aswell. To make conversation more smooth you have to create conversation flow by define input/output context but let imagine if you have a hundread of intent with fully relationship It will be exhausted task to understand how the conversation flow is

Prerequisites

Create service accounts in google cloud platform for your project. download a key and setting your environment variable with name 'GOOGLE_APPLICATION_CREDENTIALS' on your local machine

export GOOGLE_APPLICATION_CREDENTIALS='your-key-file.json'

Installing

Install all dependency

npm install

In /src/config folder replace 'proj-id' and 'code' with your project id and language code repectively

{
    "projectId": "proj-id"
    "languageCode": "code"
}

Start visulisation server

npm run build && npm run start

Open your browser with 8080 port

http://localhost:8080/

After open the browser. On the header you will see your project ID on the left and main menu on the right.

  • Intent - This section shows intents which have a relation (inputcontext and outputcontext) with other
  • Individual intent - This section shows stand alone intents (no relation with others)
  • Read me This section shows the information about icon or meaning of the edge color

image

Intent section will show the graph about relation of an intents. it's directional graph

image

At the bottom, there is a control panel make you able to move left/right zoom in/out

Once you hover the node it will show you below

  • Training pharse - This is your training phrase. we limited number of the phrase to 3 pharses.
  • Response Message - This is your Text Response Message (not include text in payload)
  • Number of payload - This is you number of payload that you create on platform

Once you hover the edge it will show you below

  • Context name - This is context name. the edge will start from the parent intent to follow-up intent
  • LifespanCount - This is a number of lifespan for this context

Next section is individual intent This section will show the intent in yourproject which has/have no relation with other intents

image

Last section is readme section. This will provide information about the symbol, color that we use in visualisation

image

Running the tests

You can execute our unit test by using below command

npm t

if all unit test passed will show result as below

or with coverage version

npm run testWithCoverage

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.