SQUASH: Serverless and Distributed Quantization-based Attributed Vector Similarity Search

2025-02-03

AI Summary

To address the challenges of low efficiency, high cost, and poor elasticity in high-dimensional vector similarity search under serverless environments—particularly for hybrid queries combining vectors and scalar attributes—this paper proposes the first fully serverless hybrid vector search system. Our approach introduces three core innovations: (1) optimized scalar quantization (OSQ) coupled with segment-based compressed storage; (2) multi-level early-termination pruning and a tree-structured parallel FaaS invocation protocol; and (3) container state retention with a joint attribute-vector filtering execution model. Experimental evaluation demonstrates that, compared to existing serverless solutions, our system achieves significantly higher throughput, reduces query latency by 42%, and lowers operational cost by 37%. Moreover, it outperforms conventional server-based deployments in both elasticity and resource utilization.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Scalability of ML Systems
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Vector similarity search presents significant challenges in terms of scalability for large and high-dimensional datasets, as well as in providing native support for hybrid queries. Serverless computing and cloud functions offer attractive benefits such as elasticity and cost-effectiveness, but are difficult to apply to data-intensive workloads. Jointly addressing these two main challenges, we present SQUASH, the first fully serverless vector search solution with rich support for hybrid queries. It features OSQ, an optimized and highly parallelizable quantization-based approach for vectors and attributes. Its segment-based storage mechanism enables significant compression in resource-constrained settings and offers efficient dimensional extraction operations. SQUASH performs a single distributed pass to guarantee the return of sufficiently many vectors satisfying the filter predicate, achieving high accuracy and avoiding redundant computation for vectors which fail the predicate. A multi-level search workflow is introduced to prune most vectors early to minimize the load on Function-as-a-Service (FaaS) instances. SQUASH is designed to identify and utilize retention of relevant data in re-used runtime containers, which eliminates redundant I/O and reduces costs. Finally, we demonstrate a new tree-based method for rapid FaaS invocation, enabling the bi-directional flow of data via request/response payloads. Experiments comparing SQUASH with state-of-the-art serverless vector search solutions and server-based baselines on vector search benchmarks confirm significant performance improvements at a lower cost.

Problem

• Vector Similarity Search
• Big Complex Data
• Serverless Computing

Innovation

• SQUASH
• OSQ
• Hierarchical Search