TigerVector: Supporting Vector Search in Graph Databases for Advanced RAGs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912940606619648 |
|---|---|
| author | Liu, Shige Zeng, Zhifang Chen, Li Ainihaer, Adil Ramasami, Arun Chen, Songting Xu, Yu Wu, Mingxi Wang, Jianguo |
| author_facet | Liu, Shige Zeng, Zhifang Chen, Li Ainihaer, Adil Ramasami, Arun Chen, Songting Xu, Yu Wu, Mingxi Wang, Jianguo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_11216 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TigerVector: Supporting Vector Search in Graph Databases for Advanced RAGs Liu, Shige Zeng, Zhifang Chen, Li Ainihaer, Adil Ramasami, Arun Chen, Songting Xu, Yu Wu, Mingxi Wang, Jianguo Databases H.2 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. |
| title | TigerVector: Supporting Vector Search in Graph Databases for Advanced RAGs |
| topic | Databases H.2 |
| url | https://arxiv.org/abs/2501.11216 |