GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications
The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
Abstract
Vector databases are widely used as a fundamental tool for addressing the weaknesses of large language model (LLM) applications, specifically hallucinations and the high cost of inference. However, existing vector databases either cater to niche applications with low-latency in-memory search, or offer sophisticated data management capabilities but at the cost of low performance. To address these limitations, we propose GaussDB-Vector, a high-performance, real-time persistent vector database that excels in low-latency scalable search, real-time inserts and deletes, high availability, large-scale distributed search, and hybrid scalar-vector filtered search capabilities. These features are primarily achieved through an innovative storage architecture designed for a graph-based vector index, optimized for I/O operations and adaptable across various dataset sizes and dimensions, complemented by novel buffering strategies to further reduce I/O burdens. GaussDB-Vector supports product quantization, parallel search, and hardware acceleration via SIMD, GPUs, and NPUs in order to further accelerate queries. Experimental results show that GaussDB-Vector outperforms competitive baselines by a factor of 1 to 5 times.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Distinctive Image Features from Scale-Invariant Keypoints
Lowe, D. G. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000029664.99615.94 · Cited by 55,589 · cited 1×
“SIFT contains a collection of image embeddings generated using the SIFT algorithm [27].”
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Oliva, A., & Torralba, A. (2001) · International Journal of Computer Vision · doi:10.1023/a:1011139631724 · Cited by 6,319
Voronoi diagrams—a survey of a fundamental geometric data structure
Aurenhammer, F. (1991) · ACM Computing Surveys · doi:10.1145/116873.116880 · Cited by 4,340
Approximate nearest neighbors: towards removing the curse of dimensionality
Indyk, P., & Motwani, R. (1998) · Proceedings of the thirtieth annual ACM symposium on Theory of computing - STOC '98 · doi:10.1145/276698.276876 · Cited by 4,188
Product Quantization for Nearest Neighbor Search
Jégou, H., Douze, M., & Schmid, C. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.57 · Cited by 2,956 · cited 2×
“GaussDB-Vector adopts PQ-ADC [24] to increase the precision of product quantization, PQ-ADC only quantizes the data in the index, and the query vector remains unchanged.”
Locality-sensitive hashing scheme based on p-stable distributions
Datar, M., Immorlica, N., Indyk, P., & Mirrokni, V. S. (2004) · Proceedings of the twentieth annual symposium on Computational geometry · doi:10.1145/997817.997857 · Cited by 2,936
Malkov, Y. A., & Yashunin, D. A. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2889473 · Cited by 1,904
2014 IEEE Conference on Computer Vision and Pattern Recognition
(2014) · doi:10.1109/cvpr20399.2014 · Cited by 1,774
The log-structured merge-tree (LSM-tree)
O’Neil, P., Cheng, E., Gawlick, D., & O’Neil, E. (1996) · Acta Informatica · doi:10.1007/s002360050048 · Cited by 1,317
Chávez, E., Navarro, G., Baeza-Yates, R., & Marroquín, J. L. (2001) · ACM Computing Surveys · doi:10.1145/502807.502808 · Cited by 1,246
Research works printed but not linked: 10
- A. Andoni, P. Indyk, and I. Razenshteyn. Approximate nearest neighbor search in high dimensions. In ICM, pages 3287–3318, 2018.
- M. Aumüller, E. Bernhardsson, and A. Faithfull. Ann-benchmarks: A benchmarking tool for approximate nearest neighbor algorithms. Inf. Syst., 87(C), Jan. 2020.
- L. Chen, M. Zaharia, and J. Zou. Frugalgpt: How to use large language models while reducing cost and improving performance. arXiv preprint arXiv:2305.05176, 2023. · arXiv
- Q. Chen, B. Zhao, H. Wang, M. Li, C. Liu, Z. Li, M. Yang, J. Wang, M. Yang, and J. Wang. SPANN: Highly-efficient billion-scale approximate nearest neighbor search. In NeurIPS 2021, 2021.
- J. Fan, Z. Pan, L. Wang, and Y. Wang. Codebook-softened product quantization for high accuracy approximate nearest neighbor search. Neurocomput., 507(C):107–116, Oct. 2022.
- 10.5555/3495724.3496517 · doi:10.5555/3495724.3496517
- S. J. Subramanya, Devvrit, R. Kadekodi, R. Krishnaswamy, and H. V. Simhadri. DiskANN: Fast accurate billion-point nearest neighbor search on a single node. In NeurIPS 2019, November 2019.
- J. Wang, X. Yi, R. Guo, H. Jin, P. Xu, S. Li, X. Wang, X. Guo, C. Li, X. Xu, K. Yu, Y. Yuan, Y. Zou, J. Long, Y. Cai, Z. Li, Z. Zhang, Y. Mo, J. Gu, R. Jiang, Y. Wei, and C. Xie. Milvus: A purpose-built vector data management system. In SIGMOD, pages 2614–2627, 2021.
- Q. Zhang, S. Xu, Q. Chen, G. Sui, J. Xie, Z. Cai, Y. Chen, Y. He, Y. Yang, F. Yang, M. Yang, and L. Zhou. VBASE: Unifying online vector similarity search and relational queries via relaxed monotonicity. In 17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23), pages 377–395, Boston, MA, July 2023. USENIX Association.
- Y. Zhang, S. Liu, and J. Wang. Are there fundamental limitations in supporting vector data management in relational databases? A case study of PostgreSQL. In ICDE, 2024.
Cited by
Fu, S., Liu, F., Zhou, J., Cai, J., & Pan, Z. (2026) · Electronics · doi:10.3390/electronics15050943 · Cited by 2
Multimodal LLMs-Assisted Context-Aware Framework for Cyber Forensics
Khanna, D., & Kumar, C. R. S. (2026) · Biennial International Conference on Nascent Technologies in Engineering (ICNTE) · doi:10.1109/icnte66387.2026.11437517
“Scalability can be enhanced through distributed vector databases [27] and load-balanced microservices that can maintain high throughput during large-scale investigations or continuous content monitoring.”
Mohanty, S. S. (2026) · Journal of Artificial Intelligence & Cloud Computing · doi:10.47363/jaicc/2026(5)518
Bibi, S., Akhtar, F., Younis, M., Bibi, S., & Raza, B. (2026) · VFAST Transactions on Software Engineering · doi:10.21015/vtse.v14i1.2353 · Cited by 3
CCD-Level and Load-Aware Thread Orchestration for in-Memory Vector ANNS on Multi-Core CPUs
Huang, Y., Ma, B., Sun, Y., Shi, Y., Chen, X., Zhong, X., Wang, Z., Hu, Y., & Weng, C. (2026) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65706.2026.00281
“After SPANN, DiskANN, and Starling are proposed [47]–[49], [50] pgvector and Cosmos DB show the integration of persistent vector search and relational and NoSQL databases [45].”
Metadata
- Authors
- Sun, J., Li, G., Pan, J., Wang, J., Xie, Y., Liu, R., & Nie, W.
- Affiliations
- Tsinghua University (CN)
- Huawei Technologies (China) (CN)
- Venue
- Proceedings of the VLDB Endowment
- Published
- 2025-08
- Volume
- 18
- Issue
- 12
- Pages
- 4951-4963
- ISSN
- 2150-8097 (ISSN-L)
- OpenAlex
- W4414241804
- Cited by
- 13
- References
- 17
- Citations by year
- 2026: 13
- FWCI
- 5.47
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Proceedings of the VLDB Endowment (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Advanced Database Systems and Queries
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Information Systems › Data Management and Algorithms
- Keywords
- vector databases, large language models, persistent databases, real-time search, distributed search, product quantization, I/O optimization, buffering strategies, SIMD acceleration, GPU acceleration, hallucination mitigation, high availability
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications. https://app.cochat.ai/papers/10.14778/3750601.3750619
- The paper
- Sun, J., Li, G., Pan, J., Wang, J., Xie, Y., Liu, R., & Nie, W. (2025). GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications. Proceedings of the VLDB Endowment. https://doi.org/10.14778/3750601.3750619
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.