GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications
Summary: GaussDB-Vector is a persistent, distributed vector database combining low-latency scalable search with real-time updates, HA, and hybrid filtering. Its I/O-optimized graph-index storage and buffering, plus PQ and SIMD/GPU/NPU acceleration, deliver 1–5× speedups. (summarized by gpt-5.6-luna on Jul 24 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Ji Sun (Tsinghua University)
- 2. Guoliang Li (Tsinghua University)
- 3. James Pan (Tsinghua University)
- 4. Jiang Wang (Huawei)
- 5. Yongqing Xie (Huawei)
- 6. Ruicheng Liu (Huawei)
- 7. Wen Nie (Huawei)
BibTeX Citation
@article{sun_vldb25,
title = {{GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications}},
author = {Sun, Ji and Li, Guoliang and Pan, James and Wang, Jiang and Xie, Yongqing and Liu, Ruicheng and Nie, Wen},
journal = {PVLDB},
series = {{VLDB} '25},
volume = {18},
number = {12},
pages = {4951--4963},
doi = {10.14778/3750601.3750619},
url = {https://doi.org/10.14778/3750601.3750619},
year = {2025}
}Incoming Citations (Sorted by Pagerank)
Showing 7 of 7 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,419 | Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects | 2027 | VLDB | 4.9605343e-05 |
| 10,500 | Bridging the Gap: Cardinality Estimation for Semantic Queries on Unstructured Data | 2026 | SIGMOD | 4.9605343e-05 |
| 10,593 | VecBench: A Controllable Benchmark for Filtered Vector Search: [Experiments & Analysis] | 2026 | SIGMOD | 4.9605343e-05 |
| 10,980 | TEngineDB-V: An OLAP-Native Vector Search System for Large-k Workloads at Tencent | 2026 | VLDB | 4.9605343e-05 |
| 11,010 | Bridging NL2SQL for CAN Signal Analytics at NIO: From Externalized Schemas to CTE Pipelines | 2026 | VLDB | 4.9605343e-05 |
| 11,018 | Nova: A Multi-Purpose Vector Engine for Low-Latency, Multi-Tenant, and Cross-Table Hybrid Retrieval | 2026 | VLDB | 4.9605343e-05 |
| 13,655 | TrustBCI: A Trustworthy Platform for Collaborative Brain-Computer Interface Data Exchange | 2026 | VLDB | - |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 6 of 6 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 75 | Fast Approximate Nearest Neighbor Search With The Navigating Spreading-out Graph | 2019 | VLDB | 0.00037163157 |
| 181 | Milvus: A Purpose-Built Vector Data Management System | 2021 | SIGMOD | 0.00026425782 |
| 335 | A Comprehensive Survey and Experimental Comparison of Graph-Based Approximate Nearest Neighbor Search | 2021 | VLDB | 0.0002067515 |
| 901 | PASE: PostgreSQL Ultra-High-Dimensional Approximate Nearest Neighbor Search Extension | 2020 | SIGMOD | 0.00013149954 |
| 1,797 | SingleStore-V: An Integrated Vector Database System in SingleStore | 2024 | VLDB | 9.6056634e-05 |
| 4,703 | Learned Cardinality Estimation for Similarity Queries | 2021 | SIGMOD | 6.4458272e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 10,402 | Metric Algebra: Embedding-Independence in Vector Databases | 2027 | SIGMOD |
| 2 | 9,191 | Database Perspective on LLM Inference Systems | 2025 | VLDB |
| 3 | 6,612 | GaussDB: A Cloud-Native Multi-Primary Database with Compute-Memory-Storage Disaggregation | 2024 | VLDB |
| 4 | 9,060 | Cost-Effective, Low Latency Vector Search with Azure Cosmos DB | 2025 | VLDB |
| 5 | 7,974 | Fast Vector Search in PostgreSQL: A Decoupled Approach | 2026 | CIDR |
| 6 | 10,593 | VecBench: A Controllable Benchmark for Filtered Vector Search: [Experiments & Analysis] | 2026 | SIGMOD |
| 7 | 8,673 | Turbocharging Vector Databases using Modern SSDs | 2025 | VLDB |
| 8 | 3,717 | Logical and Physical Optimizations for SQL Query Execution over Large Language Models | 2025 | SIGMOD |
| 9 | 1,797 | SingleStore-V: An Integrated Vector Database System in SingleStore | 2024 | VLDB |
| 10 | 6,455 | AlayaDB: The Data Foundation for Efficient and Effective Long-context LLM Inference | 2025 | SIGMOD |