/faq-bot

Server to perform NLU and NLP on incoming WhatsApp messages

Primary LanguagePythonMIT LicenseMIT

faq-bot

Server to perform NLU and NLP on incoming WhatsApp messages

Tools & Technologies used

  • Python 3.8.13
  • Rasa

Steps to run locally

  1. Clone this repo 
    git clone https://github.com/hanzala-sohrab/faq-bot.git
  2. Change directory 
    cd faq-bot
  3. Create a virtual environment and activate it 
    python3.8 -m venv venv && source venv/bin/activate
  4. Install required libraries 
    pip3.8 install -r requirements.txt
  5. Train the model (this step is required if any change is made to any of the yml files) 
    rasa train
  6. Start the server 
    rasa run

Demo

  • Getting college info like name, address, branches, placement stats, etc.
2022-04-28_04-54-19.mp4
  • Getting faculty information
2022-04-28_05-02-41.mp4

Rasa architecture

image

  • The diagram above provides an overview of the Rasa Open Source architecture. The two primary components are Natural Language Understanding (NLU) and dialogue management.

  • NLU is the part that handles intent classification, entity extraction, and response retrieval. It's shown below as the NLU Pipeline because it processes user utterances using an NLU model that is generated by the trained pipeline.

  • The dialogue management component decides the next action in a conversation based on the context. This is displayed as the Dialogue Policies in the diagram.

References