RAGdb: A Zero-Dependency, Embeddable Architecture for Multimodal Retrieval-Augmented Generation on the Edge

TL;DR

RAGdb introduces a portable, zero-dependency architecture for multimodal retrieval-augmented generation that operates efficiently on edge devices, reducing infrastructure complexity and enhancing privacy.

Contribution

It presents a monolithic, SQLite-based system with a deterministic hybrid scoring function, eliminating GPU reliance and enabling efficient, local-first RAG on edge hardware.

Findings

Achieves 100% Recall@1 for entity retrieval

31.6x faster incremental ingestion on a consumer laptop

Reduces disk footprint by 99.5% compared to Docker stacks

Abstract

Retrieval-Augmented Generation (RAG) has established itself as the standard paradigm for grounding Large Language Models (LLMs) in domain-specific, up-to-date data. However, the prevailing architecture for RAG has evolved into a complex, distributed stack requiring cloud-hosted vector databases, heavy deep learning frameworks (e.g., PyTorch, CUDA), and high-latency embedding inference servers. This ``infrastructure bloat'' creates a significant barrier to entry for edge computing, air-gapped environments, and privacy-constrained applications where data sovereignty is paramount. This paper introduces RAGdb, a novel monolithic architecture that consolidates automated multimodal ingestion, ONNX-based extraction, and hybrid vector retrieval into a single, portable SQLite container. We propose a deterministic Hybrid Scoring Function (HSF) that combines sublinear TF-IDF vectorization with exact substring boosting, eliminating the need for GPU inference at query time. Experimental evaluation on an Intel i7-1165G7 consumer laptop demonstrates that RAGdb achieves 100\% Recall@1 for entity retrieval and an ingestion efficiency gain of 31.6x during incremental updates compared to cold starts. Furthermore, the system reduces disk footprint by approximately 99.5\% compared to standard Docker-based RAG stacks, establishing the ``Single-File Knowledge Container'' as a viable primitive for decentralized, local-first AI. Keywords: Edge AI, Retrieval-Augmented Generation, Vector Search, Green AI, Serverless Architecture, Knowledge Graphs, Efficient Computing.