Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG
This addresses a foundational architectural issue in retrieval systems for AI pipelines, though it appears incremental as a refinement of existing RAG approaches.
The paper tackles the problem that retrieval systems confuse finding relevant information with providing sufficient context for reasoning, and introduces the SINR framework that decouples these processes to enhance composability, scalability, and context fidelity without extra processing costs.
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.