yogeshhk / gstfaqchatbot

Set of scripts to build a chatbot which will answer FAQ about Goods and Services Tax (GST) India.

GST FAQ Bot with Rasa-NLU

Set of scripts to build a chatbot which will answer FAQ about Goods and Services Tax (GST) India. Copyright (C) 2017 Yogesh H Kulkarni

License:

This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or any later version.

Scripts:

• app.py: Chatbot UI built using Flask, using templates/*.html
• engine.py: Chatbot core logic as well as knowledgebase.
• config.json: Rasa NLU settings for training as well as executing intent extraction
• run_training: Windows batch file to build trained modeling
• run_server: Windows batch file to execute Rasa-NLU server.

Dependencies:

• Needs Python 3.5

ToDos

• Add more training data
• Entity extraction not working as desired, find out more.
• Etc.

References

• Rasa-NLU installation
• Bhavani Ravi’s event-bot code, Youtube Video
• GST FAQs:
  • Government Documentation
  • GST India Documentation

Disclaimer:

• Author ([email protected]) gives no guarantee of the results of the program. It is just a fun script. Lot of improvements are still to be made. So, don’t depend on it at all.

gstfaqchatbot's Issues

Engine response functions

Hi, kindly clarify on the logic of the functions that return responses or how they work on engine.py.
I have tried making queries and the only response I get is for the first if statement where entities==None.
However, my server logs indicate that the entity and intent extraction was successful.

Thank you.

Update code to sync with RASA's latest interface

Code here was demonstration of article in Analytics Vidhya, written in 2017. Over time RASA APIs have changed. So need to update code accordingly.

Unable to launch Flash app on browser

Rasa NLU version:
0.10.6

Used backend / pipeline :
Spacy_sklearn

Operating system ):
OSX 10.13.3

Issue:
I am able to setup and train the model. In the trained model folder, I get 2 .pkl and 3 .json files as well.

Now when I try to open the browser and see the chat-bot, all I see is a static page saying "hello from Rasa NLU: 0.10.6".

I am using mac and earlier there were issues linking with SPACY’s en dictionary too (I had to download using python -m spacy download en ). Also there are some environment variable issues when using spacy so we need to initiate these 2 variables to initiate utf-8 locale :
export LC_ALL=en_US.UTF-8
export LANG=en_US.UTF-8

The FLASK app isnt opening at all. The webpage which opens (http://127.0.0.1:5000/) is just static and has this written : ‘hello from Rasa NLU: 0.10.6’ .

I used 5000 port as i got that from the output on terminal (from
python -m rasa_nlu.server -c config.json -e luis) :

INFO:main:Started http server on port 5000
2018-02-01 13:11:08+0530 [-] Log opened.
2018-02-01 13:11:08+0530 [-] Site starting on 5000
2018-02-01 13:11:08+0530 [-] Starting factory

Any help ?

Content of configuration file :

{
"pipeline": "spacy_sklearn",
"path" : "models/",
"data" : "data/gstfaq-data.json",
"num_threads":10
}