Skip to content

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

Notifications You must be signed in to change notification settings

asmith26/ai-chatbot-framework

 
 

Repository files navigation

IKY

An AI Chatbot framework built in Python

IKY 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. Iky'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 start building on it.It may contain lots of bugs,please free to contribute via pull requests.

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

Docker

docker build -t "ai-chat-bot" .
docker run --name=chabot-node-1  -e="APPLICATION_ENV=Production" -v ./:/app-container -p 8001:8080 -it ai-chat-bot gunicorn --bind 0.0.0.0:8080 run:app
docker exec -it chabot-node-1 python /app-container/setup.py

OR

Docker Compose ( Recommended)

docker-compose build
docker-compose up -d

without docker

  • Then use pip to install all required python packages
pip install -r requirements.txt
  • Run setup script for setting up some default intents
$ python setup.py
  • Development
$ python run.py
  • Production
$ APPLICATION_ENV="Production" gunicorn -k gevent --bind 0.0.0.0:8001 run:app

That's it.

Creating and Training your stories

Navigate to http://localhost:8001

Tutorial

Checkout this basic tutorial on youtube,

IMAGE ALT TEXT HERE

Please visit my website to see my personal chatbot in action

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

MIT

Free Software, Hell Yeah!


Made with ❤️ at God's Own Country.

About

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

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 48.6%
  • JavaScript 33.8%
  • HTML 13.7%
  • CSS 3.8%
  • Shell 0.1%