> The LLM generates documentation
so, not documentation? Why not write your own engine and detect the official docs? e.g. docs.rs would do this wonderfully
Also look into https://cht.sh/
Remember: incorrect (misleading) documentation is worse than no documentation.
What this might be better for is use-cases that don't require extreme precision. Imagine it for learning language or reading sophisticated academic literature. For example, https://archive.org/details/pdfy-TJ7HxrAly-MtUP4B/page/n111/...
Stuff like that is hard and every tool to make the complicated more legible I'd embrace.