Open access
Sep 2026
Chunk Size and Retrieval Depth Optimization in a Minimal Retrieval-Augmented Generation Pipeline
This study tested how both settings change the results of a simple RAG pipeline, finding retrieval recall was best at 256-token chunks, while context precision fell steadily from 0.428 to 0.172 as chunks grew.
Sajjad Ahmad, Jasim Hussain, Hamza Najeeb et al.
· International Journal of Inn... · 0 citations