llm-classifier VS harlequin

We do this for the null hypothesis - is uses an LLM to bootstrap a binary classifier - which handles null easily

https://github.com/lamini-ai/llm-classifier

LLMs introduced zero-shot learning, or “prompt engineering” which is drastically easier to use and more effective than labeling data.

You can also retrofit “prompt engineering” onto good old fashion ML like text classifiers. I wrote a library to do just that here: https://github.com/lamini-ai/llm-classifier

IMO, it’s a short matter of time before this takes over all of what used to be called “deep learning”.

Cool project! Always love seeing more people adopting DuckDB. One question, if the goal is privacy, why add the requirement for a browser into the mix? Why should people use this tool instead of https://harlequin.sh or some other tool that won't require a browser?

There are a bunch of these, like [1] and [2], probably a lot more.

--

1: https://harlequin.sh/

2: https://www.pgcli.com/

Harlequin is a TUI client for SQL databases known for its light-weight extensive support for SQL databases. It is a versatile tool for data exploration and analysis workflows. Harlequin provides an interactive SQL editor with features like autocomplete, syntax highlighting, and query history. It also has a results viewer that can display large result sets. However, Harlequin did not have a DataFusion adapter before. Thankfully, it was really easy to add one.

We think so too, as an example there is harlequin, a beautiful terminal based SQL IDE.

https://terminaltrove.com/harlequin/

https://harlequin.sh/