Bridging OLAP and RAG: A Multidimensional Approach to the Design of Corpus Partitioning

TL;DR

This paper introduces the Dimensional Fact Model (DFM), a conceptual framework that combines semantic clustering and multidimensional partitioning to improve the design, robustness, and explainability of large-scale Retrieval-Augmented Generation (RAG) systems.

Contribution

It proposes the DFM as a novel approach to guide corpus partitioning in RAG, bridging OLAP multidimensional modeling with modern retrieval architectures.

Findings

DFM enables hierarchical routing and fallback strategies.

Transforms retrieval from a black-box similarity to a deterministic workflow.

Supports robust retrieval despite incomplete metadata.

Abstract

Retrieval-Augmented Generation (RAG) systems are increasingly deployed on large-scale document collections, often comprising millions of documents and tens of millions of text chunks. In industrial-scale retrieval platforms, scalability is typically addressed through horizontal sharding and a combination of Approximate Nearest-Neighbor search, hybrid indexing, and optimized metadata filtering. Although effective from an efficiency perspective, these mechanisms rely on bottom-up, similarity-driven organization and lack a conceptual rationale for corpus partitioning. In this paper, we claim that the design of large-scale RAG systems may benefit from the combination of two orthogonal strategies: semantic clustering, which optimizes locality in embedding space, and multidimensional partitioning, which governs where retrieval should occur based on conceptual dimensions such as time and organizational context. Although such dimensions are already implicitly present in current systems, they are used in an ad hoc and poorly structured manner. We propose the Dimensional Fact Model (DFM) as a conceptual framework to guide the design of multidimensional partitions for RAG corpora. The DFM provides a principled way to reason about facts, dimensions, hierarchies, and granularity in retrieval-oriented settings. This framework naturally supports hierarchical routing and controlled fallback strategies, ensuring that retrieval remains robust even in the presence of incomplete metadata, while transforming the search process from a 'black-box' similarity matching into a governable and deterministic workflow. This work is intended as a position paper; its goal is to bridge the gap between OLAP-style multidimensional modeling and modern RAG architectures, and to stimulate further research on principled, explainable, and governable retrieval strategies at scale.