IKY

An AI Chatbot framework built in Python

Building a chatbot can sound daunting, but it’s totally doable. IKY is an AI powered conversational dialog interface built in Python. With IKY it’s easy to create Natural Language conversational scenarios with no coding efforts whatsoever. The smooth UI makes it effortless to create and train conversations to the bot and it continuously gets smarter as it learns from conversations it has with people. IKY can live on any channel of your choice (such as Messenger, Slack etc.) by integrating it’s API with that platform.

You don’t need to be an expert at artificial intelligence to create an awesome chatbot that has artificial intelligence. With this basic project you can create an artificial intelligence powered chatting machine in no time.There may be scores of bugs. So feel 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,

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

Free Software, Hell Yeah!

---

Made with ❤️ at God's Own Country.