---
title: "Comment by Mihai_LeanZero on \"Why Your RAG Pipeline Needs a Reranker: Bi-Encoders vs. Cross-Encoders, and When It Matters\" | Hashnode"
description: "Really clean writeup of the bi-encoder/cross-encoder split -- the \"cost is linear in corpus size per query, forever\" framing is the right way to explain why nob"
url: "https://hashnode.com/posts/why-your-rag-pipeline-needs-a-reranker-bi-encoders-vs-cross-encoders-and-when-it-matters/6ab2b4d0836e3fa92222dd29/comment/6ab2c7985cf1757f8e970eea"
---

[Discussion](https://hashnode.com/posts/why-your-rag-pipeline-needs-a-reranker-bi-encoders-vs-cross-encoders-and-when-it-matters/6ab2b4d0836e3fa92222dd29)

Comment [Why Your RAG Pipeline Needs a Reranker: Bi-Encoders vs. Cross-Encoders, and When It Matters](https://hashnode.com/posts/why-your-rag-pipeline-needs-a-reranker-bi-encoders-vs-cross-encoders-and-when-it-matters/6ab2b4d0836e3fa92222dd29)

[Mihai\_LeanZero](https://hashnode.com/@mihaileanzero)

[Sep 22](https://hashnode.com/posts/why-your-rag-pipeline-needs-a-reranker-bi-encoders-vs-cross-encoders-and-when-it-matters/6ab2b4d0836e3fa92222dd29/comment/6ab2c7985cf1757f8e970eea)

Really clean writeup of the bi-encoder/cross-encoder split -- the "cost is linear in corpus size per query, forever" framing is the right way to explain why nobody just runs a cross-encoder over everything.

One thing I didn't see covered: what happens when the reranker call itself is slow or unavailable in production. Per your own diagram it's a synchronous stage sitting between retrieval and the LLM call, with its own latency and failure modes (loaded GPU, cold model server, network blip). Falling back to raw cosine order on a timeout keeps the request alive but silently degrades quality for however long the reranker is down; failing the request instead keeps quality guarantees but turns a reranker hiccup into a user-facing outage. Worth picking one of those on purpose before the first timeout shows up in prod rather than after.