I've tried a number of notebook AIs, jupyter ai, hex, deepnote, einblick. The one that worked best for me was einblick probably because it's data-aware. For AIs that don't support that you need to be overly specific when writing prompts, which is annoying, and you keep having to rename/reference the correct dataframes and variables (even more annoying).
Jupyter AI
11–20 of 37 posts
Re: Jupyter AI
#12So I’ve just gotten a ggml version of llama2 chat running on my computer, would starting the included Flask OpenAI API clone allow for integration with Jupiter AI while staying local on my machine? Or are the code helpers all trained differently than the general chat models?
Edit: it’s running via a llama.cpp server
Re: Jupyter AI
#13For every development like this, you have the other side of the coin like the article also on the front page about Zoom using AI without any opt-out. Playing with fire indeed.
Re: Jupyter AI
#14I've tried a number of notebook AIs, jupyter ai, hex, deepnote, einblick. The one that worked best for me was einblick probably because it's data-aware. For AIs that don't support that you need to be overly specific when writing prompts, which is annoying, and you keep having to rename/reference the correct dataframes and variables (even more annoying).
Can you expand on this "data awareness"? What does it mean, and what are its benefits?
Re: Jupyter AI
#15Bummer there's no support for local models. Llama 2 would run trivially on most Jupyter installs.
Re: Jupyter AI
#16I want jupyter notebook style cells overlaid on an LLM, not and LLM overlaid over my notebook
Re: Jupyter AI
#17This is probably the more helpful page as it shows what you can do: https://jupyter-ai.readthedocs.io/en/latest/users/index.html... This is a nice feature! Not huge, but it's great DevEx (MLEngEx...?)
Thanks for the link although for some reason I keep getting:
Incorrect API key provided error on jupyter for chatgpt. I'm on a paid account so not sure why...
Re: Jupyter AI
#18Stop with the chatbots. Ai is much more useful to automatically handle things we did not before.
Re: Jupyter AI
#19This looks useful, but not quite what I hoped. GPT4 with Code Interpreter is a fun, frustrating experience where you’re writing a dialog about writing some code, sort of like pair programming or a code interview. Compared to a notebook, it’s terrible. The sandbox environment resets if you take a break. There’s also a quota, and if you hit that it forces taking a break, causing a reset. In a notebook, you could rerun…
You might find it interesting to try my open source ai coding tool “aider”.
It lets you pair program with gpt-4 like you are describing. But the source code lives in your local git repo. You can start a new project or work with an existing repo. You can fluidly switch back and forth between a coding chat where you ask gpt to edit the code and your own editor to make edits yourself.
Re: Jupyter AI
#20I've tried a number of notebook AIs, jupyter ai, hex, deepnote, einblick. The one that worked best for me was einblick probably because it's data-aware. For AIs that don't support that you need to be overly specific when writing prompts, which is annoying, and you keep having to rename/reference the correct dataframes and variables (even more annoying).
Would love to exchange notes on this if you're up for it!
For louie.ai, we've been going for data-aware from the get-go, and more broadly, doing a LLM-first tool design rethink. In the large, as I look around, it feels super early for the dev community figuring out core genAI notebook tool uses, flows, & assumptions. Likewise, zooming-in on individual feature experiments, current tools feel rough & underpowered relative to what we already know is possible.
We've been forced to question a lot as we've been learning from going operational and experimenting with design. Again, if up for it, would love to chat & exchange notes!