The library might be great. But from the examples shown, there is zero reason to use it as all of these can be done easily without giving your data to OpenAI.
I could be wrong, but my assumption is the only thing that is actually being sent to openai is the shape of your data, not the data itself. The text query gets converted to whatever normal filtering/aggregating mechanism exist within pandas.
the larger question I have is... if you're already advanced enough to use pandas, do you really need/want this?
the larger question I have is... if you're already advanced enough to use pandas, do you really need/want this?