Skip to content

A python chatbot framework with Natural Language Understanding and Artificial Intelligence.

License

Notifications You must be signed in to change notification settings

yudchang/ai-chatbot-framework

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Jarvis

An AI Chatbot framework build in Python

JARVIS is an AI based conversational dialog interface built in Python. It can be used to create Natural language conversation scenarios with zero coding effort.The simple web UI makes it very easy to create and train your conversations. Jarvis's API can be used to integrate with any channel of your choice such as Messenger,Slack etc. This is a very basic project so you can satrt building on it.It may contain lots of bugs,please free to contribute via pull requests.

Demo

Please visit my website to see my personal chatbot in action

Installation

  • add your dev/production configurations in config.py
class Production(Config):
    # MongoDB Database Details
    DB_HOST = "mongodb://127.0.0.1:27017/"
    DB_USERNAME = ""
    DB_PASSWORD = ""

    # Web Server details
    WEB_SERVER_PORT = 80

class Development(Config):
    DEBUG = True
  • Then use pip to install all required python packages
pip install -r requirments.txt
  • Run setup script for setting up some default intents
$ python setup.py

That's it.

Docker

will be added soon.

docker-compose.yml

will be added soon

running

  • Development
$ python run.py
  • Production
$ APPLICATION_ENV="Production" gunicorn -k gevent --bind 0.0.0.0:8080 run:app

Creating and Training your stories

Navigate to http://localhost:8080

NLTK

See NLTK documentation

SKlearn

See SKLearn documentation

CRFsuite

See CRFsuite documentation

See python CRfSuite

Todos

  • Write Unit Tests
  • Improve intent classification accuracy
  • Add parameter types
  • Migrate UI to React JS

License

Free Software, Hell Yeah!

About

A python chatbot framework with Natural Language Understanding and Artificial Intelligence.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 44.6%
  • JavaScript 36.8%
  • HTML 14.7%
  • CSS 3.9%