docling-sdg icon indicating copy to clipboard operation
docling-sdg copied to clipboard

Introduce more flexibility for QA generation output persistence

Open anastasds opened this issue 9 months ago • 1 comments

Right now, the output file for QA generation is specified in GenerationOptions, as used in QA gen here.

When using this to write a demo notebook in #11 and wanting to output multiple datasets from multiple documents in a 1:1 fashion, encapsulating the output method into GenerateOptions requires more complexity than allowing generate_from_chunks and friends to take a parameter specifying where to output, which is some usability friction.

A more general question is visiting which options should be in the *Options classes passed to constructors and which should be method parameters. Things like api_key definitely make sense where they are, but maybe others - temperature is another example - should probably have the existing defaults but also be overwritable in function calls.

anastasds avatar Mar 25 '25 20:03 anastasds

See also #41. It might make sense to address both this and #41 in the same PR and sort out all the output persistence issues at the same time.

jwm4 avatar Aug 02 '25 19:08 jwm4