Pocket RAG: On-Device RAG for First Aid Guidance in Offline Mobile Environment

TL;DR

This paper introduces a lightweight, on-device retrieval-augmented generation system for mobile devices that provides reliable first aid guidance offline, achieving high accuracy and significantly faster response times.

Contribution

The paper presents a novel mobile-friendly RAG system with optimized pipeline components enabling effective offline first aid guidance on small devices.

Findings

94.5% accuracy for physical first aid

97.0% accuracy for psychological first aid

4x reduction in response time

Abstract

In disaster scenarios or remote areas, first responders often lose network connectivity when providing first aid. In such situations, server-based AI systems fail to provide critical guidance. To address this issue, we present a lightweight, mobile-based retrieval-augmented generation system for small language models (SLMs) that can run directly on Android devices. Our system integrates a mobile-friendly optimized pipeline featuring Hybrid RAG, selective compression, batched prompt decoding, and quantization caching. Despite the model's small size, our RAG-based system achieves 94.5\% accuracy for physical first aid and 97.0\% for psychological first aid. Additionally, we reduce response time from 14.2s to 3.7s, achieving a nearly 4x speedup. These results prove that our system is practical and can deliver reliable first aid guidance even without internet connectivity.