Author(s) :   Dr. Asoke Nath¹, Sanchayita Ghosh², Bhaskar Joyti Mitra³, Aritra Patra⁴

Abstract : Retrieval-Augmented Generation (RAG) systems rely on high-dimensional vector similarity search to retrieve relevant documents for large language models. However, classical nearest-neighbor methods face scalability limits due to the “curse of dimensionality” and the computational cost of comparing massive vector sets. The authors propose a hybrid quantum-classical pipeline that leverages quantum computing for similarity evaluation. Experimental results on synthetic data demonstrate that the swap-test similarity estimates closely match classical dot products, and that clustering dramatically reduces search overhead. The present studies show the feasibility of quantum-enhanced retrieval: the quantum similarity scores approximate classical results within statistical error. We discuss accuracy, runtime trade-offs, and the challenges of state preparation in the Noisy Intermediate-Scale Quantum (NISQ) era.

Keywords: quantum computing; vector similarity search; nearest neighbors; quantum algorithms; quantum machine learnin;

DOI: 10.61161/ijarcsms.v13i6.1

Pages : 1-9

*Authors are invited to submit papers through E-mail at editor.ijarcsms@gmail.com