Vectorizing the spacetag index — eight retrieval decisions, resolved

design-decision · sourced

Semantic + faceted search over ~256 spacetags (a controlled capability/action vocabulary plus NL summary, verdict, and numeric scores). Eight Phase-0 research questions — hybrid retrieval, embedding model, what to embed, similarity & norm, rerank, storage, dedup, evaluation — each resolved with a one-line reason and a stable interface that survives the eventual backend swap.

~256spacetags indexed~1.5 MBfull vector setsub-msbrute-force scan≥10kmigration trigger

Findings