Check out JetML.com (I'm the founder). Happy to help get you started with a demo if you want to reach out nick@jetml.com.

I have only tested jetmlgpt using Jupyter notebooks.

JupyterLite How to docs: https://jupyterlite.readthedocs.io/en/latest/howto/index.htm...

"Create a custom kernel" https://jupyterlite.readthedocs.io/en/latest/howto/extension... :

> We recommend checking out how to create a server extension first

It may also be possible to just pip install the plain python package with micropip, or include it in a `jupyterlite build`; From https://github.com/jupyterlite/jupyterlite/issues/237#issuec... re: 'micropip':

  %pip install $@
  # __import__('piplite').install($@)

There's also micromamba, for mamba-forge packages (which are build with empack (emscripten) into WASM)

Hey, kudos on getting this out. I just opened sourced a similar tool for the JetML platform.

https://github.com/jetml/jetmlgpt

Would love to collaborate!

I've been using chatgpt/gpt4 in a ways.

-Created a jupyter extension for code completion, auto commenting, and an error handling assistant. -Automated my email to auto draft responses to important emails. -Automated my email to auto summarize important received emails. -I've manually used it to create lots of documents including correspondence, marketing material, and code generation.

What practical applications (other than selfie portraits) can text-to-image ML models like Stable Diffusion actually power?

I wanted to find out. Specifically, I wanted to find out what I could make when combining these latest models with JetML, my data science platform.

So I made an AI weather app for my favorite Oregon destinations. Find the code on JetML's GitHub to experiment with it.

Happy to sell automl.io domain to anyone interested :)