| name | 0.3.5-understand-mmr005 |
| description | ["0.3.5"] |
| Non-text chunk processor | component that parses, extracts, and encodes non-text content from documents — handl |
understand-mmr005
CALL NUMBER: deep_retrieval_augmented_.mmr005
DEFINITION: Non-text chunk processor: component that parses, extracts, and encodes non-text content from documents — handling image pixels, table cells, code syntax, or audio waveforms into retrievable representations.
Invoke this skill to understand mmr005 down to its primitives. The RELATIVE ROOT below is the least-fixed-point closure of everything it bundles from — the full import cone, grouped by the lib each prim comes from. Projected from a prover-typed KB (MAP/SWI-Prolog consistency gate): every reference below resolves.
THE RELATIVE ROOT (the import cone, by lib)
CONSUMERS (what needs this)
mmr001, mmr006, mmr007, mmr008, mmr019, naive_rag
Projected from the retrieval augmented generation architecture patterns KB (207 concepts / 225 relations) — consistency-typed by MAP; the facet list after the colon IS the cross-lib dependency web.
(leaf — this is an actual skill.)