Skip to main content

Jupyter magic command for having AI chat conversations in a notebook

Project description

https://mybinder.org/badge_logo.svg
!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!

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

jupyter_aichat-0.0.3.tar.gz (10.1 kB view details)

Uploaded Source

Built Distribution

jupyter_aichat-0.0.3-py2.py3-none-any.whl (11.5 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file jupyter_aichat-0.0.3.tar.gz.

File metadata

  • Download URL: jupyter_aichat-0.0.3.tar.gz
  • Upload date:
  • Size: 10.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-requests/2.28.2

File hashes

Hashes for jupyter_aichat-0.0.3.tar.gz
Algorithm Hash digest
SHA256 d82b5058a1f186935b0c6d9149f9c8f5b76fc5c6f362e186c661eb2fd7953519
MD5 5f771e404a028dc6b7cf0b7d4526c299
BLAKE2b-256 2c1ea8d3f6393cba9e07cc40f728174f200efcd1beffe833bedba6f092c82748

See more details on using hashes here.

File details

Details for the file jupyter_aichat-0.0.3-py2.py3-none-any.whl.

File metadata

File hashes

Hashes for jupyter_aichat-0.0.3-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 56849586f60e3fa90641efbb875c0a81d074bd69ffd3fee952d52a48cad29f45
MD5 fe977314cf2aae83f336296f199ee27c
BLAKE2b-256 360e331aa625540813d6128e5a6c89ed374cb5b15fed93886dde7be4d6554221

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page