Exqutor: Extended Query Optimizer for Vector-augmented Analytical Queries

TL;DR

Exqutor is a pluggable query optimizer that improves the efficiency and accuracy of vector-augmented analytical queries by employing exact and sampling-based cardinality estimation techniques.

Contribution

It introduces a novel cardinality estimation framework for vector search components, enhancing query planning in vector-augmented workloads.

Findings

Performance improvements up to 10,000x on vector-augmented queries.

Effective adaptive sampling reduces estimation overhead.

Enhanced query plan accuracy with the proposed framework.

Abstract

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.