Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
Document<Markup> -> List<HierarchicalChunk>
Parse structured documents like Org-mode or Markdown by header levels to produce semantically grouped chunks that preserve parent context.
Problem it solves
Naively chunking text by character count breaks logical sections, ruining retrieval context.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.