{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:21:22Z","timestamp":1781878882123,"version":"3.54.5"},"reference-count":39,"publisher":"Association for Computing Machinery (ACM)","issue":"12","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:p>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.<\/jats:p>\n          <jats:p>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.<\/jats:p>","DOI":"10.14778\/3750601.3750619","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:38:05Z","timestamp":1758029885000},"page":"4951-4963","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["GaussDB-Vector: A Large-Scale Persistent Real-Time Vector Database for LLM Applications"],"prefix":"10.14778","volume":"18","author":[{"given":"Ji","family":"Sun","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoliang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Pan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqing","family":"Xie","sequence":"additional","affiliation":[{"name":"Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruicheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Nie","sequence":"additional","affiliation":[{"name":"Huawei"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,16]]},"reference":[{"key":"e_1_2_1_1_1","unstructured":"http:\/\/clickhouse.com."},{"key":"e_1_2_1_2_1","unstructured":"http:\/\/elastic.co."},{"key":"e_1_2_1_3_1","unstructured":"http:\/\/faiss.ai."},{"key":"e_1_2_1_4_1","unstructured":"http:\/\/pinecone.io."},{"key":"e_1_2_1_5_1","unstructured":"http:\/\/redis.io."},{"key":"e_1_2_1_6_1","unstructured":"https:\/\/github.com\/pgvector\/pgvector."},{"key":"e_1_2_1_7_1","unstructured":"http:\/\/weaviate.io."},{"key":"e_1_2_1_8_1","first-page":"1233","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems -","volume":"1","author":"Andoni A.","year":"2015","unstructured":"A. Andoni, P. Indyk, T. Laarhoven, I. Razenshteyn, and L. Schmidt. Practical and optimal lsh for angular distance. In Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 1, NIPS'15, page 1225\u20131233, Cambridge, MA, USA, 2015. MIT Press."},{"key":"e_1_2_1_9_1","first-page":"3318","volume-title":"ICM","author":"Andoni A.","year":"2018","unstructured":"A. Andoni, P. Indyk, and I. Razenshteyn. Approximate nearest neighbor search in high dimensions. In ICM, pages 3287\u20133318, 2018."},{"key":"e_1_2_1_10_1","volume-title":"Jan.","author":"Aum\u00fcller M.","year":"2020","unstructured":"M. Aum\u00fcller, E. Bernhardsson, and A. Faithfull. Ann-benchmarks: A benchmarking tool for approximate nearest neighbor algorithms. Inf. Syst., 87(C), Jan. 2020."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/116873.116880"},{"key":"e_1_2_1_12_1","first-page":"218","volume-title":"Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023","author":"Bang F.","year":"2023","unstructured":"F. Bang. GPTCache: An open-source semantic cache for LLM applications enabling faster answers and cost savings. In L. Tan, D. Milajevs, G. Chauhan, J. Gwinnup, and E. Rippeth, editors, Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023), pages 212\u2013218, Singapore, Dec. 2023. Association for Computational Linguistics."},{"key":"e_1_2_1_13_1","first-page":"10","volume-title":"2007 IEEE International Parallel and Distributed Processing Symposium","author":"Beaumont O.","year":"2007","unstructured":"O. Beaumont, A.-M. Kermarrec, L. Marchal, and E. Riviere. Voronet: A scalable object network based on voronoi tessellations. In 2007 IEEE International Parallel and Distributed Processing Symposium, pages 1\u201310, 2007."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/502807.502808"},{"issue":"12","key":"e_1_2_1_15_1","doi-asserted-by":"crossref","first-page":"3772","DOI":"10.14778\/3685800.3685805","article-title":"SingleStore-V: An integrated vector database system","volume":"17","author":"Chen C.","year":"2024","unstructured":"C. Chen, C. Jin, Y. Zhang, S. Podolsky, C. Wu, S.-P. Wang, E. Hanson, Z. Sun, R. Walzer, and J. Wang. SingleStore-V: An integrated vector database system in SingleStore. Proc. VLDB Endow., 17(12):3772\u20133785, 2024.","journal-title":"SingleStore. Proc. VLDB Endow."},{"key":"e_1_2_1_16_1","volume-title":"Frugalgpt: How to use large language models while reducing cost and improving performance. arXiv preprint arXiv:2305.05176","author":"Chen L.","year":"2023","unstructured":"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."},{"key":"e_1_2_1_17_1","volume-title":"NeurIPS 2021","author":"Chen Q.","year":"2021","unstructured":"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."},{"key":"e_1_2_1_18_1","first-page":"262","volume-title":"Proceedings of the Twentieth Annual Symposium on Computational Geometry, SCG '04","author":"Datar M.","year":"2004","unstructured":"M. Datar, N. Immorlica, P. Indyk, and V. S. Mirrokni. Locality-sensitive hashing scheme based on p-stable distributions. In Proceedings of the Twentieth Annual Symposium on Computational Geometry, SCG '04, page 253\u2013262, New York, NY, USA, 2004. Association for Computing Machinery."},{"key":"e_1_2_1_19_1","volume-title":"The faiss library","author":"Douze M.","year":"2024","unstructured":"M. Douze, A. Guzhva, C. Deng, J. Johnson, G. Szilvasy, P.-E. Mazar\u00e9, M. Lomeli, L. Hosseini, and H. J\u00e9gou. The faiss library. 2024."},{"key":"e_1_2_1_20_1","volume-title":"Oct.","author":"Fan J.","year":"2022","unstructured":"J. Fan, Z. Pan, L. Wang, and Y. Wang. Codebook-softened product quantization for high accuracy approximate nearest neighbor search. Neurocomput., 507(C):107\u2013116, Oct. 2022."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.14778\/3303753.3303754"},{"key":"e_1_2_1_22_1","first-page":"3416","volume-title":"Proceedings of the ACM Web Conference 2023, WWW '23","author":"Gollapudi S.","year":"2023","unstructured":"S. Gollapudi, N. Karia, V. Sivashankar, R. Krishnaswamy, N. Begwani, S. Raz, Y. Lin, Y. Zhang, N. Mahapatro, P. Srinivasan, A. Singh, and H. V. Simhadri. Filtered-diskann: Graph algorithms for approximate nearest neighbor search with filters. In Proceedings of the ACM Web Conference 2023, WWW '23, page 3406\u20133416, New York, NY, USA, 2023. Association for Computing Machinery."},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"e_1_2_1_25_1","first-page":"2336","volume-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition","author":"Kalantidis Y.","year":"2014","unstructured":"Y. Kalantidis and Y. Avrithis. Locally optimized product quantization for approximate nearest neighbor search. In 2014 IEEE Conference on Computer Vision and Pattern Recognition, pages 2329\u20132336, 2014."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3496517"},{"key":"e_1_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889473"},{"issue":"3","key":"e_1_2_1_29_1","doi-asserted-by":"crossref","DOI":"10.1023\/A:1011139631724","article-title":"Modeling the shape of the scene: A holistic representation of the spatial envelope","volume":"42","author":"Oliva A.","year":"2001","unstructured":"A. Oliva and A. Torralba. Modeling the shape of the scene: A holistic representation of the spatial envelope. International Journal of Computer Vision, 42(3), 2001.","journal-title":"International Journal of Computer Vision"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s002360050048"},{"key":"e_1_2_1_31_1","volume-title":"VLDB Journal","author":"Pan J. J.","year":"2024","unstructured":"J. J. Pan, J. Wang, and G. Li. Survey of vector database management systems. VLDB Journal, 2024."},{"key":"e_1_2_1_32_1","volume-title":"NeurIPS 2019","author":"Subramanya S. J.","year":"2019","unstructured":"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."},{"key":"e_1_2_1_33_1","first-page":"1757","volume-title":"Proceedings of the 2021 International Conference on Management of Data, SIGMOD '21","author":"Sun J.","year":"2021","unstructured":"J. Sun, G. Li, and N. Tang. Learned cardinality estimation for similarity queries. In Proceedings of the 2021 International Conference on Management of Data, SIGMOD '21, page 1745\u20131757, New York, NY, USA, 2021. Association for Computing Machinery."},{"key":"e_1_2_1_34_1","first-page":"348","volume-title":"Boosting Accuracy and Efficiency for Vector Retrieval with Local Scaling Graph. In 2025 IEEE 41st International Conference on Data Engineering (ICDE)","author":"Wang H.","year":"2025","unstructured":"H. Wang, W. Wu, C. Luo, A. Bian, C. Meng, Y. Wu, and J. Sun. Boosting Accuracy and Efficiency for Vector Retrieval with Local Scaling Graph. In 2025 IEEE 41st International Conference on Data Engineering (ICDE), pages 336\u2013348, Los Alamitos, CA, USA, May 2025. IEEE Computer Society."},{"key":"e_1_2_1_35_1","first-page":"2627","volume-title":"SIGMOD","author":"Wang J.","year":"2021","unstructured":"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\u20132627, 2021."},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476249.3476255"},{"key":"e_1_2_1_37_1","first-page":"2253","volume-title":"Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, SIGMOD '20","author":"Yang W.","year":"2020","unstructured":"W. Yang, T. Li, G. Fang, and H. Wei. PASE: PostgreSQL ultra-high-dimensional approximate nearest neighbor search extension. In Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, SIGMOD '20, page 2241\u20132253, New York, NY, USA, 2020. Association for Computing Machinery."},{"key":"e_1_2_1_38_1","first-page":"395","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Zhang Q.","year":"2023","unstructured":"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\u2013395, Boston, MA, July 2023. USENIX Association."},{"key":"e_1_2_1_39_1","volume-title":"ICDE","author":"Zhang Y.","year":"2024","unstructured":"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."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3750601.3750619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T13:41:19Z","timestamp":1758030079000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3750601.3750619"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":39,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["10.14778\/3750601.3750619"],"URL":"https:\/\/doi.org\/10.14778\/3750601.3750619","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2025,8]]},"assertion":[{"value":"2025-09-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}