Skip to content

Latest commit

 

History

History
 
 

README.md

This sample shows how to create a bot that uses Language Understanding (LUIS) with Application Insights to get telemetry around bot and your LUIS application's performance. This bot example uses applicationinsights, restify and dotenv.

Concepts introduced in this sample

LUIS enables you to build, train and publish a simple question and answer bot based on FAQ URLs, structured documents or editorial content in minutes.

The Application Insights enables you to discover actionable insights through application performance management and instant analytics.

In this sample, we demonstrate how to call LUIS to extract the intents from a user's message and use Application Insights to gather user-bot interaction telemetry.

To try this sample

  • Clone the repository
    git clone https://github.com/microsoft/botbuilder-samples.git
  • In a terminal, navigate to samples/javascript_nodejs/21.luis-with-appinsights
    cd samples/javascript_nodejs/21.luis-with-appinsights
  • [Optional] Update the .env file under samples/javascript_nodejs/21.luis-with-appinsights with your botFileSecret For Azure Bot Service bots, you can find the botFileSecret under application settings.
  • Install modules and start the bot
    npm i && npm start

Testing the bot using Bot Framework Emulator

Microsoft 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 from here

Connect to bot using Bot Framework Emulator V4

  • Launch Bot Framework Emulator
  • File -> Open Bot Configuration and navigate to samples/javascript_nodejs/21.luis-with-appinsights
  • Select luis-with-appinsights.bot file

Prerequisites

Set up LUIS

(Optional) Install LUDown

  • (Optional) Install the LUDown here to help describe language understanding components for your bot.

Install Application Insights

  • Follow instructions here to set up your Application Insights service.

LUIS

Language Understanding service (LUIS) allows your application to understand what a person wants in their own words. LUIS uses machine learning to allow developers to build applications that can receive user input in natural language and extract meaning from it.

Deploy this bot to Azure

You can use the MSBot Bot Builder CLI tool to clone and configure any services this sample depends on.

To install all Bot Builder tools -

Ensure you have Node.js version 8.5 or higher

npm i -g msbot chatdown ludown qnamaker luis-apis botdispatch luisgen

To clone this bot, run

msbot clone services -f deploymentScripts/msbotClone -n <BOT-NAME> -l <Azure-location> --subscriptionId <Azure-subscription-id> --appId <YOUR APP ID> --appSecret <YOUR APP SECRET PASSWORD>

NOTE: You can obtain your appId and appSecret at the Microsoft's Application Registration Portal

Further reading