ModelRefs / Modular RAG — AI Glossary

Modular RAG — AI Glossary

A RAG architecture composing swappable modules for indexing, retrieval, reranking, generation, and routing into customizable pipelines.

Overview

Gao et al. (2023) proposed modular RAG as a framework beyond naive/advanced RAG. Modules: search (web, knowledge graph, API), memory, fusion, routing, prediction, task adaptation. Enables specialized pipelines: agentic RAG with iterative retrieval, multi-modal RAG with image retrieval, or hybrid retrieval with sparse+dense.

Reference details

Topic	rag
Last reviewed	2026-06-24

Example: Composition, so a stage can be replaced

Retrieval quality is poor for one document type. In a modular pipeline you swap that type's retriever and leave everything else alone. In a monolithic one you change shared code and re-validate the whole system. The value is the seam, not any particular module.

Commonly confused with

Modular RAG is a framing, not an architecture you can install. It describes decomposing a pipeline into swappable stages — routing, memory, fusion, prediction. Nothing about the term specifies which modules, so it constrains a design far less than it appears to.

When to use it

Reach for it when:

Different content types genuinely need different handling
You are running retrieval strategies in parallel and fusing them
Stages need to be evaluated and replaced independently

Reach for something else when:

One corpus, one query type — modularity is overhead with no payoff
Before naive RAG works and is measured
Module count is being treated as a proxy for sophistication

Continue your research

Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Modular RAG — AI Glossary.

Frequently asked questions

What is Modular RAG?