Beyond Similarity Search: A Unified Data Layer for Production RAG Systems
On the map: Retrieval-augmented generation → RAG pipeline design and evaluation
Abstract (arXiv)
Retrieval-Augmented Generation (RAG) systems have become the standard architecture for grounding large language models in organizational knowledge. Yet production deployments consistently expose a gap between clean prototype performance and real-world reliability. This paper identifies three root causes of that gap: data staleness, tenant data leakage, and query composition explosion. All three trace back to the conventional split-system data layer. We propose and evaluate a unified data layer built on PostgreSQL with native vector search (pgvector) and HNSW indexing. Controlled benchmarks on 50,000 documents show 92% latency reduction for date-filtered queries, 74% for tenant-scoped queries, zero synchronization inconsistency, and complete elimination of cross-tenant data leakage with 93% less synchronization code. We additionally discuss a recommended hybrid tier architecture
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation. First posted on arXiv 5 May 2026.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024RAG Does Not Work for Enterprises
- 2025RAG-Stack: Co-Optimizing RAG Quality and Performance From the Vector Database Perspective
- 2025Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG
- 2024Retrieval Augmented Generation Systems: Automatic Dataset Creation, Evaluation and Boolean Agent Setup
- 2025Advancing Retrieval-Augmented Generation for Structured Enterprise and Internal Data
- 2026CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale
- 2024Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems
- 2025RAGO: Systematic Performance Optimization for Retrieval-Augmented Generation Serving