gonb VS llm_client

I've had these strong feelings and the OP describes it really well. Despite being a polyglot programmer, I really struggle with Python, both in expression and performance (unless it's just config for GPUs).

Some of this frustration was recently an "Unpopular Opinion" on the Go Time Podcast regarding Python being great for "data exploration" but not for "data engineering": https://changelog.com/gotime/304#t=3196

I've been yearning for better interactive tooling and ML-related libraries bridge this gap and started using some even in just the last week:

* GoNB (Golang-support for Jupyter notebooks, also from a Googler) https://github.com/janpfeifer/gonb

* That uses Go-Plotly for graphs/UI: https://github.com/MetalBlueberry/go-plotly

* GoMLX (GoNB author is also on that project, many thanks Jan!) https://github.com/gomlx/gomlx

* Hidden at the end of OP is LangChainGo for LLMs, which I haven't used yet: https://github.com/tmc/langchaingo

Pick those up and let's make the Go community stronger together!

When I created a new Jupyter file in Go, I faced a challenge trying to replicate the development process I usually follow with Python. In Python and Jupyter Notebook I can conveniently run code in separate parts, saving previous values in memory and using cells to organize code. This flexibility was missing in Go, and it took me some time to figure out a solution. However, I came across a helpful tutorial that explained how to use caching with the Go Kernel, making the process smoother with gonb.

I needed one more thing to make myself feel at home, something I usually use with Python. When working with data, I often turned to the Jupyter VSCode extension for its convenience. To my relief, I discovered that a Go kernel existed, tailored perfectly for my needs.

Training library, with some pretty-printing. Including plots for GoNB Jupyter notebook.

Tutorial (and demo) here. Source code in github.com/janpfeifer/gonb.

I switched from python to rust for my AI stuff. Honestly, I don't care about the things people say rust is used for. I like it because the package manager, testing, and typings being built into the ecosystem by default makes it so easy to build. VS Python where it all can be done, but you need to then maintain all of those separate tools. The overhead of writing Rust is less than the overhead of dealing with the Python ecosystem. And then you have all the benefits of Rust everyone mentions more often... one other thing no one mentions is the feedback loop between a strongly typed language and copilots ability to more accurately generate code.

That being said, there is a real shortage of Rust software for Rust only projects. I ended up writing a wrapper for Llama.cpp and open ai API [0] because I needed it and couldn't find anything out there. Eventually, I do intend to implement Hugging Face's Candle library [1] (A rust version of Torch). There is something appealing about doing everything in a single lang especially as the monopoly of CUDA inevitably gets chipped away.

[0] https://github.com/ShelbyJenkins/llm_client