OVH Chatbot - Node.js

OVH Chatbot Cover

The main goal of this tool is to help OVH clients in order to have faster responses when you have some problems with OVH services. For example for web hosting you can ask why your website is broken and then this chatbot will find a solution to fix that.

Setup

Visit INSTALL.md to setup and test on Slack or Facebook.

Project overview

bots --> Represent all the modules about the bot's answers and it's specific type with an intention already given.
config --> The configuration of tools and configuration variables are in this directory.
constants --> Represents the constants of the project.
controllers --> The controllers contain handler function of an express route.
diagnostics --> Contains all the modules for the diagnostics.
models --> Contains database models.
providers --> Tools used globally in all the project.
routes --> Route declarations of the API.
platforms --> Contains all the handlers to communicate with different platforms.
utils --> Contains all the utilities and API connector to make this chatbot works.
views --> Only to display a confirmations page when you logged in with your OVH account

Supported platforms

Facebook Messenger

This project handles callbacks for authentication, messages, delivery confirmation and postbacks. More details are available at the Facebook Documentations.

Slack

This project handles callbacks for authentication, messages and postback actions. More details are available at the Slack Documentations.

Web (OVH managers)

This project handles callbacks messages and postback actions. The authentication is handled by the managers.The bot only checks if the user is logged in or not.

Bot functions

The bot uses api.ai as a language processor.

Responses/Intents

To avoid confusions:

Intent: what the user ask to the bot.

Response: What the bot respond to an user.

All the intents needing processed responses can be found here.

The intents which doesn't need processed responses (aka: answers to basic questions) are stored in the api.ai database, have a look at the api.ai folder.

This intents and response are translated in: