Nlu and api

[shakhyar]

To start the server, run server.py.

Use test.py to run inference from server(here, your computer is the server, and the url is http://127.0.0.1:5000/

To use inference from browser, after running server.py, go to http://127.0.0.1:5000/api/token/your_query where token is just a random token for now, use anything, and your_query is your question.

Note: requirements.txt is a bit changed, you have to install a few more dependencies now.