Home > SQL Server > Chatbot for future conversation – Installation

Chatbot for future conversation – Installation


We all must have come across this word recently. It is part of AI application where most of giant internet companies using to chat with customer or providing this platform as a service (reference).

example:

1. LUIS.ai  –  Microsoft
2. Wit.ai  – Facebook
3. Api.ai  – Google
4. Watson Assistant- IBM

Now adding my perspective towards data privacy. I don’t like companies saving my information and analyze and used against me in terms of marketing. But, good news is that Europe has introduced General Data Protection Regulation (GDPR) in 2018 to protect consumer’s data. They started this new path in internet world to protect customer data before data breach occured. I would recommend this types of law to implemented in other countries.

So, keeping that in my mind. I look for alternative solution in golden world Open Source tools.

The purpose of this blog is to setup the RASA NLU and bug fix system after installation.

Tools – installation

  1. Python 3.x – https://www.python.org/downloads/
  2. pip install rasa_nlu
  3. Check or install “Common Tools for Visual C++ 2015 or 2017”
  4. pip install rasa_nlu[spacy] — https://spacy.io/
  5. python -m spacy download en_core_web_md
  6. python -m spacy link en_core_web_md en
  7. When install dependency package all at once or when needed.
    1. pip install colorlog — https://pypi.org/project/colorlog/
    2. pip install pypiwin32 — https://pypi.org/project/pypiwin32/

Now, the system is ready to train data and setup chatbot.

Getting started

We can create chatbot for any domain of our choice. But, we need initial data to train our system with NPL and ML using Python modules or other tools or services.

Sample Data

Data is important for chatbot. It is like teaching baby. You can download sample demo data from this link https://raw.githubusercontent.com/RasaH/rasa_nlu/master/data/examples/rasa/demo-rasa.json

In the next blog post I will talk about data training, client and Server interface to do simple chatbot.

 

 

Advertisements
Categories: SQL Server
  1. No comments yet.
  1. No trackbacks yet.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: