Metadata-Version: 2.1
Name: jupyter_aichat
Version: 0.0.3
Summary: Jupyter magic command for having AI chat conversations in a notebook
Author-email: Antti Kaihola <13725+akaihola@users.noreply.github.com>
Description-Content-Type: text/x-rst
Requires-Dist: IPython
Requires-Dist: openai
Requires-Dist: setuptools
Requires-Dist: tiktoken
Project-URL: Home, https://github.com/akaihola/jupyter_aichat

================
 jupyter-aichat
================

.. image:: https://mybinder.org/badge_logo.svg
 :target: https://mybinder.org/v2/gh/akaihola/jupyter-aichat/main?labpath=example.ipynb

::

    !pip install jupyter-aichat

::

    Collecting jupyter_aichat
      Downloading jupyter_aichat-0.0.1-py2.py3-none-any.whl (3.9 kB)
    Installing collected packages: jupyter_aichat
    Successfully installed jupyter_aichat-0.0.1

::

    %load_ext jupyter_aichat

::

    %%ai
    I've created an AI chat user interface for Jupyter notebooks.
    It adds the `%ai` and `%%ai` magic commands for writing messages,
    renders response messages in the notebook,
    and keeps the whole conversation in memory.

That sounds really interesting! Can you tell me more about how it works and what kind
of AI it uses?

::

    %%ai
    The user just types `%ai "<message>"` or `%%ai` followed by a multi-line message.
    It asks for the ChatGPT API key before sending the first message.
    Both sent messages and received messages are kept in memory
    and the whole message history is submitted every time the magic command is used.
    The response from ChatGPT is rendered as Markdown.

That sounds really convenient! And what exactly is ChatGPT and how does it generate
responses?

::

    %ai "I think you know that best yourself :)"

As an AI language model, I don't know everything about what specific tools or
algorithms you've used in the creation of your AI chat user interface. However,
generally speaking, GPT (Generative Pre-trained Transformer) is a type of language
model that uses deep learning to generate human-like text. ChatGPT is a variant of GPT
specifically designed for chatbots and conversational agents, and it has been trained
on vast amounts of existing human conversations to learn how to simulate natural
language interactions. When a user inputs a message, ChatGPT uses this training to
generate an appropriate response based on the context of the conversation.

::

    %%ai
    Thanks for the summary!
    I'm publishing this on GitHub and putting this very discussion as the README.

That sounds like a great idea! Having a clear explanation of how the chat interface
works and the technology it uses will help make it more accessible to potential users.
Good luck with your project!

