/Jethiya-A.I

Jethiya A.I

Primary LanguagePythonMIT LicenseMIT

Jethiya A.I

An A.I bot that talks like Jethalal :)

PRs Welcome GitHub followers PyPI license

A Deep Neural Network that has been trained to chat and reply using TMKOC iconic dialogues.

📥 Installation

OS X & Linux:

pip3 install -r requirements.txt
python3 test.py

Windows:

pip3 install -r requirements.txt
python3 test.py

Usage example

Just install all the dependencies and run the app.py but for development purposes and testing, we recommend the following:

python chat.py # For chatting to the bot.

python test.py # For testing the bot over testCases

For more examples and usage, please refer to the Wiki

📦 Development setup

Describe how to install all development dependencies and how to run an automated test-suite of some kind. Potentially do this for multiple platforms.

pip3 install -r requirements.txt
python3 test.py

Training the model

Though testing will test the model as well as train it. But if you want to train the model only (maybe on a pecific parameters). You can skip testing and directly run. python bot.py -e 2400 -v 1000

🔹Release History

  • tmkoc best version 5.1

    • New commands and updated intents
    • Used for Main Release [both Web & Android]
  • tmkoc best version 4.0

    • Stable but limited commands, quite impressive version so far. (improved early access)
    • Classes and custom func parameters introduced.
  • tmkoc best version 3.0

    • will use for early access to get feedbacks.
    • Classes and custom test cases implemented.
    • babuchakEngine optimized.

✅ To-Do

  • Optimize the engine by hyperparameter tuning
  • Add more dialogues in intents
  • Add gif support for android

🔭 Meta

Kanishk Sharma – kanishksh4rma@protonmail.com

           

Distributed under the MIT license. See LICENSE for more information.

🏅 Contributing

  1. Fork it (https://github.com/kanishksh4rma/Jethiya-A.I/fork)
  2. Create your feature branch (git checkout -b feature/intents)
  3. Commit your changes (git commit -am 'Add some intents')
  4. Push to the branch (git push origin feature/intents)
  5. Create a new Pull Request

ForTheBadge built-with-love forthebadge made-with-python