# An In-Depth Study of Filter-Agnostic Vector Search on a PostgreSQL Database System: [Experiments and Analysis]

arXiv: https://arxiv.org/abs/2603.23710 · HTML: https://mlsanity.com/paper/2603.23710/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 18 of 18)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [YFCC100M: The New Data in Multimedia Research](https://mlsanity.com/paper/1503.01817/) (2015)
- [Embedding-based Retrieval in Facebook Search](https://mlsanity.com/paper/2006.11632/) (2020)
- [Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2205.03763/) (2022)
- [ACORN: Performant and Predicate-Agnostic Search Over Vector Embeddings and Structured Data](https://mlsanity.com/paper/2403.04871/) (2024)
- [Graph-Based Vector Search: An Experimental Evaluation of the State-of-the-Art](https://mlsanity.com/paper/2502.05575/) (2025)
- [UNIFY: Unified Index for Range Filtered Approximate Nearest Neighbors Search](https://mlsanity.com/paper/2412.02448/) (2024)
- [boldsymbolSteiner-Hardness: A Query Hardness Measure for Graph-Based ANN Indexes](https://mlsanity.com/paper/2408.13899/) (2024)
- [SIEVE: Effective Filtered Vector Search with Collection of Indexes](https://mlsanity.com/paper/2507.11907/) (2025)
- [Return of the Lernaean Hydra: Experimental Evaluation of Data Series Approximate Similarity Search](https://mlsanity.com/paper/2006.11459/) (2020)
- [NaviX: A Native Vector Index Design for Graph DBMSs With Robust Predicate-Agnostic Search Performance](https://mlsanity.com/paper/2506.23397/) (2025)
- [iRangeGraph: Improvising Range-dedicated Graphs for Range-filtering Nearest Neighbor Search](https://mlsanity.com/paper/2409.02571/) (2024)
- [Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2411.14754/) (2024)
- [DEG: Efficient Hybrid Vector Search Using the Dynamic Edge Navigation Graph](https://mlsanity.com/paper/2502.07343/) (2025)
- [DARTH: Declarative Recall Through Early Termination for Approximate Nearest Neighbor Search](https://mlsanity.com/paper/2505.19001/) (2025)
- [Cost-Effective, Low Latency Vector Search with Azure Cosmos DB](https://mlsanity.com/paper/2505.05885/) (2025)

## Built on by (most cited first, 1 of 1)

- [Stop Indexing at Full Precision: Revisiting Clustering for Vector Embeddings](https://mlsanity.com/paper/2608.14648/) (2026)

## Abstract (arXiv)

Filtered Vector Search (FVS) is critical for supporting semantic search and GenAI applications in modern database systems. However, existing research most often evaluates algorithms in specialized libraries, making optimistic assumptions that do not align with enterprise-grade database systems. Our work challenges this premise by demonstrating that in a production-grade database system, commonly made assumptions do not hold, leading to performance characteristics and algorithmic trade-offs that are fundamentally different from those observed in isolated library settings. This paper presents the first in-depth analysis of filter-agnostic FVS algorithms within a production PostgreSQL-compatible system. We systematically evaluate post-filtering and inline-filtering strategies across a wide range of selectivities and correlations. Our central finding is that the optimal algorithm is not dictated by the cost of distance computations alone, but that system-level overheads that come from both distance computations and filter operations (like page accesses and data retrieval) play a significant role. We demonstrate that graph-based approaches (such as NaviX/ACORN) can incur prohibitive numbers of filter checks and system-level overheads, compared with clustering-based indexes such as ScaNN, often canceling out their theoretical benefits in real-world database environments. Ultimately, our findings provide the database community with crucial insights and practical guidelines, demonstrating that the optimal choice for a filter-agnostic FVS algorithm is not absolute, but rather a system-aware decision contingent on the interplay between workload characteristics and the underlying costs of data access in a real-world database architecture.