Exactly. The order matters: improve recall first with dense + lexical retrieval, then improve precision with reranking, and only then consider context compression.
Compressing noisy candidates too early just makes the wrong context smaller, not better.
Kartik N V J K
The framing that vector search finds candidates while reranking decides relevance is the mental model that fixed my retrieval quality. Hybrid dense plus lexical mainly buys you recall on exact terms and rare tokens that embeddings smear together, and the reranker is what stops that wider net from dumping noise into the prompt. I'd add that context compression only pays off after reranking is solid, otherwise you're compressing documents that shouldn't have made the cut.