统一数据层解决RAG系统生产落地三大痛点
Beyond Similarity Search: A Unified Data Layer for Production RAG Systems
- 用PostgreSQL+pgvector构建统一数据层，整合向量搜索与HNSW索引
- 5万文档测试显示查询延迟降92%，跨租户泄露归零，同步代码减少93%
- 适合追求生产级稳定性的企业级RAG系统开发者
检索增强生成（RAG）系统已成为将大语言模型与组织知识结合的标准架构。然而生产部署中始终存在原型性能与实际可靠性之间的差距。本文识别出三个根本原因：数据过时、租户间数据泄露、查询组合爆炸。三者均源于传统的分离式数据层。我们提出并评估了一种基于PostgreSQL与原生向量搜索（pgvector）及HNSW索引的统一数据层。在5万篇文档上的受控基准测试显示，带日期过滤的查询延迟降低92%，租户范围查询降低74%，实现零同步不一致，跨租户数据泄露完全消除，且同步代码量减少93%。此外还讨论了推荐的混合分层架构。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。