# Evaluating Retrieval Quality in RAG Systems

> A lab‑tested playbook for measuring RAG retrieval: golden sets, Hit@k/MRR/NDCG, chunking choices, hybrid search, and re‑ranking.

Published: 2026-03-08  
Canonical: https://aimastermindlab.com/knowledge-base/evaluating-retrieval-quality-rag

---
Most RAG failures are retrieval failures. We built a lightweight harness and a golden dataset to measure improvements objectively.

Metrics: Hit@k (coverage), MRR (ranking), and NDCG (graded relevance). Track all three; they reveal different issues.

Chunking: 256–512 tokens with small overlap is a strong default; increase for legal/policy docs; decrease for FAQ‑like content.

Hybrid search: combine BM25 with vector similarity to capture names/numbers; then re‑rank top‑k using a cross‑encoder for precision.

Results: hybrid + re‑rank consistently outperformed pure vector search in our tests, especially on name/number queries.
---

Source: https://aimastermindlab.com/knowledge-base/evaluating-retrieval-quality-rag — AI Mastermind Lab (https://aimastermindlab.com)