Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Reranking
Three Ways Production RAG Fails: Fragmented Context, Drift and Misuse
Three ways production RAG fails: fragmented context from chunking, drift as the knowledge base grows, and misuse despite good retrieval, with layer-level fixes.
11 min readReranking in RAG: Cross-Encoders vs LLM Judges and Their Latency
How a second-stage reranker fixes candidate ordering in RAG, comparing cross-encoders with LLM judges, latency costs, failure modes and how to evaluate them.
14 min readAdvanced RAG on Milvus: Hybrid Search, HyDE, Query Rewriting and Reranking
Build a Milvus RAG pipeline step by step: dense and BM25 vectors, RRF hybrid search, metadata filters, query rewriting, HyDE, decomposition and cross-encoder reranking.
18 min readDebugging RAG Retrieval: Recall@K, BM25, Hybrid Fusion and Reranking
A small experiment on a RAG pipeline that ranked the right chunk fourth, showing how chunking, BM25, rank fusion and reranking change Recall@3 and MRR.
11 min readFrom Naive to Production RAG on SEC 10-K Filings: Chunking, Hybrid Search
Why a textbook RAG pipeline failed on 300-page 10-Ks, and the fixes: section-aware chunks, hybrid retrieval, cross-encoder reranking, validation and metadata citations.
8 min readWhy Reranking Is the Cheapest Big Win in a RAG Pipeline
Retrieve 50, rerank to 5: how cross-encoder reranking fixes ordering in a RAG pipeline, the gains and latency to expect, when to skip it, and what to ship.
8 min readWhy RAG Still Gives Wrong Answers: Hybrid Search, Reranking and Recall@K
Clean chunks don't guarantee good answers. See where vector retrieval fails and how fusion, a cross-encoder reranker, HyDE and Recall@K measurement fix it.
6 min readHybrid Retrieval for RAG: BM25, Rank Fusion and Reranking Beat Vectors
Pure vector search misses exact terms. BM25 plus embeddings, Reciprocal Rank Fusion and a cross-encoder reranker took this RAG setup to 91% retrieval accuracy.
6 min readTen Quiet Retrieval Bugs in Production RAG, and How Each One Gets Fixed
From chunk size and overlap to hybrid search, RRF, reranking, embedding choice and CI evals: ten retrieval mistakes behind wrong RAG answers and their fixes.
16 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.