让SQL查询动态调节向量，提升检索精度与灵活性
flexvec: SQL Vector Retrieval with Programmatic Embedding Modulation
- 在查询时对嵌入矩阵和得分数组进行编程式运算
- 24万数据块下19毫秒完成三步组合调制
- 适合需要精细控制检索过程的AI应用开发者
随着AI代理成为检索API的主要使用者，我们有机会将更多检索流程暴露给调用方。flexvec是一种检索内核，将嵌入矩阵和得分数组作为可编程接口，允许在选择前对二者进行算术操作。我们将查询时对这一表面的操作称为程序化嵌入调制（PEM）。本文描述了一组此类操作，并通过查询物化器将其集成到SQL接口中，支持可组合的查询原语。在包含24万段落的生产级语料上，三个组合调制操作在桌面CPU上无需近似索引即可在19毫秒内完成；在一百万段落规模下，耗时82毫秒。
原文摘要 · Abstract (English)
As AI agents become the primary consumers of retrieval APIs, there is an opportunity to expose more of the retrieval pipeline to the caller. flexvec is a retrieval kernel that exposes the embedding matrix and score array as a programmable surface, allowing arithmetic operations on both before selection. We refer to composing operations on this surface at query time as Programmatic Embedding Modulation (PEM). This paper describes a set of such operations and integrates them into a SQL interface via a query materializer that facilitates composable query primitives. On a production corpus of 240,000 chunks, three composed modulations execute in 19 ms end-to-end on a desktop CPU without approximate indexing. At one million chunks, the same operations execute in 82 ms.
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。