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

A development team rebuilt their Retrieval-Augmented Generation (RAG) pipeline from scratch after standard production deployments revealed major performance gaps across 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% depending on content type. 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, adding only 50ms of latency while improving recall by 15%. Query transformation was also introduced to handle poorly worded user inputs before retrieval begins. The combined optimizations reduced end-to-end query latency by 40% compared to the baseline demo-style RAG setup.