BM25 plus embeddings, then a cross-encoder over the top-k. The two stages buy different things and most teams cannot say which one they added. Hybrid search buys recall because lexical and vector retrieval fail on different queries; reranking buys precision because a cross-encoder reads the query and the document together. Here is what each one measurably adds, and how to tell when the reranker is buying you a rounding error.
Fixed-size, semantic, and structure-aware chunking measured against real retrieval failures. The uncomfortable finding: your chunking choice barely moves whether the answer reaches the model, and hugely moves how much junk you pay for to get it there. Also, your chunk size is probably a library default nobody chose.