This bot would show telemtry logging in application insights, and review in powerbi.
This bot has been created using yo botbuilder
command line. And, selected Javascript
as language along with Core Bot
template.
This sample requires prerequisites in order to run.
This bot uses LUIS, an AI based cognitive service, to implement language understanding.
-
Node.js version 10.14.1 or higher
# determine node version node --version
- make a note of instrumentation key
- for powerbi portion, necessary key details need be generated as here
- create bot channels registration
- make a note of appid/ password
- update the bot channels registration with correct appinsights key value
- LUIS language model setup, training, and application configuration steps can be found here.
- For this project, the json definition for luis app is kept here.
- Make sure to create a luis app, and name it as
FlightBooking
, and import the definition as in said JSON file. - Basically, the JSON file have two major intents
GetWeather
andBookFlight
. - The
GetWeather
intent would be utilized to make a further qna maker service call. - The
BookFlight
intent would be utilized to just for intent understanding in the flight booking flow.
- name the kb as
weatherkb
- set the source FAQ URL as
https://public.wmo.int/en/about-us/FAQs/faqs-weather
- make sure earlier created application insights is configured for qna maker service app
-
Install modules
npm install
-
Setup LUIS
The prerequisite outlined above contain the steps necessary to provision a language understanding model on www.luis.ai. Refer to Create a LUIS Application to enable language understanding above for directions to setup and configure LUIS.
-
Start the bot
npm start
-
Or, have the app run in debug mode [in VS Code]
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
- Launch Bot Framework Emulator
- File -> Open Bot
- Enter a Bot URL of
http://localhost:3978/api/messages
To learn more about deploying a bot to Azure, see Deploy your bot to Azure for a complete list of deployment instructions.