Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG

TL;DR

The paper proposes the SINR framework that separates semantic search from contextual assembly, improving retrieval systems' scalability and context fidelity by actively connecting precise search chunks with larger context without extra costs.

Contribution

It introduces a dual-layer architecture that decouples semantic matching from contextual assembly, enhancing retrieval system flexibility and performance.

Findings

Improved context fidelity in retrieval systems

Enhanced scalability and composability of retrieval architectures

Active connection between search chunks and context without additional costs

Abstract

Retrieval systems are essential to contemporary AI pipelines, although most confuse two separate processes: finding relevant information and giving enough context for reasoning. We introduce the Search-Is-Not-Retrieve (SINR) framework, a dual-layer architecture that distinguishes between fine-grained search representations and coarse-grained retrieval contexts. SINR enhances the composability, scalability, and context fidelity of retrieval systems by directly connecting small, semantically accurate search chunks to larger, contextually complete retrieve chunks, all without incurring extra processing costs. This design changes retrieval from a passive step to an active one, making the system architecture more like how people process information. We discuss the SINR framework's conceptual foundation, formal structure, implementation issues, and qualitative outcomes. This provides a practical foundation for the next generation of AI systems that use retrieval.