Skip to content

Latest commit

 

History

History
 
 

48.qnamaker-active-learning-bot

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
Helpers
Helpers
 
 
bots
bots
 
 
deploymentTemplates
deploymentTemplates
 
 
.env
.env
 
 
.eslintrc.js
.eslintrc.js
 
 
README.md
README.md
 
 
index.js
index.js
 
 
package.json
package.json
 
 

README.md

Active learning in QnA Maker

This sample shows how to integrate Active Learning in a QnA Maker bot in NodeJS. Click here to know more about how to enable and use active learning .

Concepts introduced in this sample

The QnA Maker Service enables you to build, train and publish a simple question and answer bot based on FAQ URLs, structured documents or editorial content in minutes. In this sample, we demonstrate how to use the Active Learning to generate suggestions for knowledge base.

Prerequisites

This samples requires prerequisites in order to run.

Overview

This bot uses QnA Maker Service, an AI based cognitive service, to implement simple Question and Answer conversational patterns.

  • Node.js version 10.14 or higher

    # determine node version
node --version

Create a QnAMaker Application to enable QnA Knowledge Bases

QnA knowledge base setup and application configuration steps can be found here.

To try this sample

  • Clone the repository

    git clone https://github.com/microsoft/botbuilder-samples.git

  • In a terminal, navigate to samples/javascript_nodejs/48.qnamaker-activelearning-bot

    cd samples/javascript_nodejs/48.qnamaker-activelearning-bot

  • Install modules

    npm install

  • Setup QnAMaker

    The prerequisite outlined above contain the steps necessary to provision a QnA Knowledge Base on www.qnamaker.ai. QnA knowledge base setup and application configuration steps can be found here.

  • Start the bot

    npm start

Testing the bot using Bot Framework Emulator

Bot Framework Emulator is a desktop application that allows bot developers to test and debug their bots on localhost or running remotely through a tunnel.

  • Install the Bot Framework Emulator version 4.3.0 or greater from here

Connect to the bot using Bot Framework Emulator

  • Launch Bot Framework Emulator
  • File -> Open Bot
  • Enter a Bot URL of http://localhost:3978/api/messages

QnA Maker service

QnA Maker enables you to power a question and answer service from your semi-structured content.

One of the basic requirements in writing your own bot is to seed it with questions and answers. In many cases, the questions and answers already exist in content like FAQ URLs/documents, product manuals, etc. With QnA Maker, users can query your application in a natural, conversational manner. QnA Maker uses machine learning to extract relevant question-answer pairs from your content. It also uses powerful matching and ranking algorithms to provide the best possible match between the user query and the questions.

Try Active Learning

  • Once your QnA Maker service is up and you have published the sample KB, try the following queries to trigger the Train API on the bot.
  • Sample queries: "surface pro 4", "apps on your surface pro"

Deploy the bot to Azure

To learn more about deploying a bot to Azure, see Deploy your bot to Azure for a complete list of deployment instructions.

Further reading