Applied AI·Embeddings and retrieval
you embed queries and documents separately so the index can be built ahead of time, then let a slower model read the pair together for the few you actually rank.
Bi-encoder vs cross-encoder
Draft summary, pending review
A bi-encoder embeds query and document separately, enabling precomputed indexes; a cross-encoder reads them together and scores the pair, more accurate but unindexable. Retrieval uses bi-encoders, reranking uses cross-encoders. That sentence explains the whole retrieval-then-rerank architecture.