A composable pipeline architecture for search that chains discrete stages: filter candidates, sort by relevance, reduce duplicates, enrich with context, and apply business logic. Unlike single-query search, multi-stage retrieval lets you express complex information needs as a sequence of operations, similar to how SQL chains WHERE, ORDER BY, GROUP BY, and JOIN.
Each stage in the pipeline receives a result set from the prior stage and applies a transformation: a feature search stage performs vector similarity lookup, a filter stage applies metadata predicates, a rerank stage re-scores results using a cross-encoder, and an enrichment stage appends additional fields. Stages are configured declaratively and executed in sequence.