Exqutor: Extended Query Optimizer for Vector-augmented Analytical Queries
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| 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 |