TigerVector: Supporting Vector Search in Graph Databases for Advanced RAGs

TL;DR

TigerVector enhances graph databases by integrating vector search capabilities directly into TigerGraph, enabling advanced, scalable hybrid querying of structured and unstructured data with superior performance.

Contribution

The paper introduces TigerVector, a novel system that seamlessly combines vector search with graph querying within TigerGraph, extending its capabilities significantly.

Findings

Demonstrates hybrid search performance surpassing Neo4j, Amazon Neptune, and Milvus.

Shows scalability and efficiency of the MPP index framework.

Integrates vector search into GSQL for expressive graph queries.

Abstract

In this paper, we introduce TigerVector, a system that integrates vector search and graph query within TigerGraph, a Massively Parallel Processing (MPP) native graph database. We extend the vertex attribute type with the embedding type. To support fast vector search, we devise an MPP index framework that interoperates efficiently with the graph engine. The graph query language GSQL is enhanced to support vector type expressions and enable query compositions between vector search results and graph query blocks. These advancements elevate the expressive power and analytical capabilities of graph databases, enabling seamless fusion of unstructured and structured data in ways previously unattainable. Through extensive experiments, we demonstrate TigerVector's hybrid search capability, scalability, and superior performance compared to other graph databases (including Neo4j and Amazon Neptune) and a highly optimized specialized vector database (Milvus). TigerVector was integrated into TigerGraph v4.2, the latest release of TigerGraph, in December 2024.