Introduction

Wellness chatbot — is an information logging chatbot. It is built on top of Python with the help of Rasa Open Source framework. It is an open source machine learning framework for automated text and voice-based conversations. Understand messages, hold conversations, and connect to messaging channels and APIs. Out of the box it supports integration with Messenger, Slack, Twilio & custom website.

  • Natural Language Processing Based
  • Works with Python 3.6.x & Python 3.7.x
  • Rasa Open Source 2.4.3
  • Tensorflow & Spacy
  • Easily integrate with Web

Installation

It is recommended to use Python 3.6 or Python 3.7 with rasa framework. Below are the steps to run this project.

  • - Clone master branch of this repository & open root directory in terminal.
  • - Create & activate virtual env with python. After that install rasa opensource
    • $ python3.7 -m venv ./venv
$ source ./venv/bin/activate
$ pip install rasa
  • - With the setup done you can now run rasa commands described below.
  • - You need to generate trained model first. In backend directory & run rasa train.
    • $ cd backend
$ rasa train
  • - Trained model can be found at backend>models> directory.
  • - After training is done, for custom actions to work run actions server.
  • - Finally, in a seperate terminal tab run rasa nlu model server.
    • $ rasa run actions --cors "*" --debug
$ rasa run -m models --enable-api --cors "*" --debug

Training & Running Chatbot

Training rasa model

Running rasa actions server

Running bot in terminal - flow 1 - affirmed for exercise

Running bot in terminal - flow 2 - denied for exercise

Running bot in terminal - flow 3 - going out of scope & coming back

Running bot in terminal - flow 4 - going out of scope & terminating process