Engineering Team Cuts RAG Pipeline Latency 40% With Bayesian Search and Hybrid Retrieval

A development team overhauled their Retrieval-Augmented Generation (RAG) pipeline after standard production deployments proved inadequate for legal, API, and support document types. The team replaced fixed 512-token chunking with document-specific strategies — including recursive, semantic, and agentic chunking — achieving recall@10 scores between 91% and 97% across content types. They combined vector search with BM25 keyword search using Reciprocal Rank Fusion, then applied a cross-encoder reranker to narrow 50 candidates down to 5, improving relevance correlation from 0.75 to 0.92. A query transformation layer was also introduced to handle poorly formed user queries before retrieval begins. Together, these changes reduced end-to-end query latency by 40% while significantly improving retrieval accuracy at scale.