https://github.com/coolmunzi/restaurant_bot

This project is a whatsapp based restaurant finder chatbot with rasa 2.2 backend and Zomato API to fetch restaurants.
https://github.com/coolmunzi/restaurant_bot

chatbot chatbot-application ngrok nlp nlp-machine-learning python rasa-chatbot rasa-nlu rasa-server rasa2 restaurant-finder-chatbot twilio twilio-api twilio-whatsapp whatsapp zomato-api

Last synced: 25 days ago
JSON representation

This project is a whatsapp based restaurant finder chatbot with rasa 2.2 backend and Zomato API to fetch restaurants.

• Host: GitHub
• URL: https://github.com/coolmunzi/restaurant_bot
• Owner: coolmunzi
• Created: 2021-01-01T12:36:49.000Z (over 5 years ago)
• Default Branch: main
• Last Pushed: 2021-01-01T13:25:20.000Z (over 5 years ago)
• Last Synced: 2025-01-21T00:50:51.222Z (over 1 year ago)
• Topics: chatbot, chatbot-application, ngrok, nlp, nlp-machine-learning, python, rasa-chatbot, rasa-nlu, rasa-server, rasa2, restaurant-finder-chatbot, twilio, twilio-api, twilio-whatsapp, whatsapp, zomato-api
• Language: Python
• Homepage:
• Size: 4.13 MB
• Stars: 1
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
 About the project 


A restaurant finder chatbot that is based on Rasa 2.2 backend and consumes Zomato API to find the restaurant for a user given location.

Chatbot requires 2 inputs from user: location and cuisine to find the restaurants using Zomato API. Chatbot is connected to Whatsapp via Twilio, 

hence a user can find restaurants via Whatsapp. 

 Screens 


  

    

    

    

  

 

 Technolgy stack used 


1. [Rasa 2.2](https://rasa.com/) - Chatbot backend framework

2. [Twilio API](https://www.twilio.com/) - To connect to Whatsapp using REST based API 

3. [Ngrok](https://ngrok.com/) - To generate public ip address and connect to the local rasa server

4. [Zomato API](https://developers.zomato.com/api) - API to query the Zomato's restaurant database

 Prerequisites 


1. Install [rasa 2.2](https://rasa.com/docs/rasa/installation/)

2. Generate [Zomato API key](https://developers.zomato.com/api)

3. Create account in Twilio and start the [whatsapp sandbox](https://www.twilio.com/console/sms/whatsapp/learn).

4. Install [ngrok](https://ngrok.com/download) in the local machine and add your authorization token. 

 

 Installation & Usage


1. Clone the repo using following command 

    

        $ git clone https://github.com/coolmunzi/restaurant_bot.git

2. Create a virtual environment and change the directory to the cloned repo

3. Change your directory to the cloned repo and create a Python virtual environment

   

4. Add twilio credentials in credentials.yml file:

         

         twilio: 

           account_sid: "{Add your account sid}"

           auth_token: "{Add your Authorization token}"

           twilio_number: "whatsapp:+{Add your twilio number}" 

5. Add your zomato api key in zomatoApi.py file inside script folder.

         

         headers = {'user-key': '{Put your Zomato API key here}',

           'Accept': 'application/json'}

6. Train the rasa model:

         

         $ rasa train

7. Start the  rasa server from terminal:

         $ rasa run -m models --enable-api --cors "*" --debug

8. Start rasa actions server in another terminal:

         

         $ rasa run actions

9. Start ngrok from terminal

         

         $ ./ngrok http 5005

10. Copy the forwarding ip address generated by ngrok and paste the same in _'WHEN A MESSAGE COMES IN'_ field inside Whatsapp Sandbox settings in Programmable Messaging Settings as highlighted in the below image.

![alt text](./images/twilio_setting.png)

   The end point should be in the format as shown below:

         

         {Ngrok generated ip address}/webhooks/twilio/webhook