Why it matters
Retrieval architectures shape RAG. Understanding shapes design.
Advertisement
The architecture
Dense: fast bi-encoder.
Sparse: BM25 + learned SPLADE.
Cross-encoder: reranking.
Late-interaction: ColBERT.
Advertisement
How it works end to end
Bi-encoder for scale.
Cross-encoder for precision.
Sparse for lexical.
Hybrid for best of both.