Social Share

Complete On-Premise and Fully Customisable Chat Bot - Part 1 - Overview

Hey Folks !! Welcome back!

For long time I was searching for the solution to make a in-house chatbot that operates with in the organisation and no compromise on the data security using the NLP cloud services or the Bot agents.

Luckily I got to know about the combination of the BOTKIT and the RASA NLU can make this solution. I went on searching and searching for the solution for the long time and I could find the pieces here and there and completed the solution.

I write this to help other folks to make this solution easier rather than searching a lot.

The solution goes on as follows.

Components are as follows :

  1. Front-End UI
  2. Botkit server / Agent server
  3. RASA NLU server 
  4. Business Logic Server
  5. DataSource 
  6. External Api if any
Now seeing in detail what these components will do.

Front-end UI :

This is the component where the user interacts with. This can be on any technology like the Angular webapp or android app ...etc

Borkit Server / Agent Server:

This is the place where the actual botkit server lies. Agent is made using the Botkit and it receives the user meassage.


RASA NLU server is the natural language processor. It acts as the middle ware for the Botkit and helps in parsing and classify the natural language of the user to the Intents and Entities which in-turn becomes the input for the Business logic server to respond back with the respective message back to the user.

Business Logic Server:

Business logic server can be on any server technology like PHP, spring boot, Node js etc. We follow the Node js here in this blog. This server will receive the intents as the input and the response will be formed by this server based on the business logic. This also uses the database and the external API to form the response.

Any one to build this solution the following technology stack is needed.
  1. Python basics like PIP installer and command execution knowledge to run the RASA NLU.
  2. Knowledge in JSON and Websocket protocol
  3. Node js 
  4. Any front end technology. (Here we rely on Angular)
  5. Prior knowledge or work experience in chat bot is plus point
Believe me this blog is going to be as simple that the beginner can even can build the Chat bot from scratch that runs within the premise and no dependency on the cloud services.

We will start with building our Agent using the BOTKIT framework. 


Latest Technology Videos

Popular Posts