flexvec: SQL Vector Retrieval with Programmatic Embedding Modulation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 18 references that are in the map. First posted on arXiv 23 Mar 2026.
Builds on
10 of 18 references.
References · 10
- 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
- 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,178
- 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 517
- 2022Matryoshka Representation Learningcited by 282
- 2024Nomic Embed: Training a Reproducible Long Context Text Embeddercited by 265
- 2020Declarative Experimentation in Information Retrieval using PyTerriercited by 30
- 2025Survey of Filtered Approximate Nearest Neighbor Search over the Vector-Scalar Hybrid Datacited by 5
- 2026IMRNNs: An Efficient Method for Interpretable Dense Retrieval via Embedding Modulationcited by 3
- 2026DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrievalcited by 2
- 2025RAGdb: A Zero-Dependency, Embeddable Architecture for Multimodal Retrieval-Augmented Generation on the Edgecited by 1
Built on by
Not cited yet.