Exqutor: Extended Query Optimizer for Vector-augmented Analytical Queries

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Hyunjoon, Lim, Chaerim, An, Hyeonjun, Sen, Rathijit, Park, Kwanghyun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912986139983872
author Kim, Hyunjoon
Lim, Chaerim
An, Hyeonjun
Sen, Rathijit
Park, Kwanghyun
author_facet Kim, Hyunjoon
Lim, Chaerim
An, Hyeonjun
Sen, Rathijit
Park, Kwanghyun
contents Vector similarity search is becoming increasingly important for data science pipelines, particularly in Retrieval-Augmented Generation (RAG), where it enhances large language model inference by enabling efficient retrieval of relevant external knowledge. As RAG expands with table-augmented generation to incorporate structured data, workloads integrating table and vector search are becoming more prevalent. However, efficiently executing such queries remains challenging due to inaccurate cardinality estimation for vector search components, leading to suboptimal query plans. In this paper, we propose Exqutor, an extended query optimizer for vector-augmented analytical queries. Exqutor is a pluggable cardinality estimation framework designed to address this issue, leveraging exact cardinality query optimization techniques to enhance estimation accuracy when vector indexes (e.g., HNSW, IVF) are available. In scenarios lacking these indexes, we employ a sampling-based approach with adaptive sampling size adjustment, dynamically tuning the sample size to balance estimation accuracy and sampling overhead. This allows Exqutor to efficiently approximate vector search cardinalities while minimizing computational costs. We integrate our framework into pgvector, VBASE, and DuckDB, demonstrating performance improvements of up to four orders of magnitude on vector-augmented analytical queries.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09695
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exqutor: Extended Query Optimizer for Vector-augmented Analytical Queries
Kim, Hyunjoon
Lim, Chaerim
An, Hyeonjun
Sen, Rathijit
Park, Kwanghyun
Databases
Vector similarity search is becoming increasingly important for data science pipelines, particularly in Retrieval-Augmented Generation (RAG), where it enhances large language model inference by enabling efficient retrieval of relevant external knowledge. As RAG expands with table-augmented generation to incorporate structured data, workloads integrating table and vector search are becoming more prevalent. However, efficiently executing such queries remains challenging due to inaccurate cardinality estimation for vector search components, leading to suboptimal query plans. In this paper, we propose Exqutor, an extended query optimizer for vector-augmented analytical queries. Exqutor is a pluggable cardinality estimation framework designed to address this issue, leveraging exact cardinality query optimization techniques to enhance estimation accuracy when vector indexes (e.g., HNSW, IVF) are available. In scenarios lacking these indexes, we employ a sampling-based approach with adaptive sampling size adjustment, dynamically tuning the sample size to balance estimation accuracy and sampling overhead. This allows Exqutor to efficiently approximate vector search cardinalities while minimizing computational costs. We integrate our framework into pgvector, VBASE, and DuckDB, demonstrating performance improvements of up to four orders of magnitude on vector-augmented analytical queries.
title Exqutor: Extended Query Optimizer for Vector-augmented Analytical Queries
topic Databases
url https://arxiv.org/abs/2512.09695