Milvus (vector database)
 | A major contributor to this article appears to have a close connection with its subject. (November 2024) |
| Milvus | |
|---|---|
 | |
| Developer | Zilliz |
| Release | October 19, 2019 |
| Stable release | v2.6.16
/ May 13, 2026.:[1] |
| Preview release | v3.0.0-beta
/ May 9, 2026.:[2] |
| Written in | Go, C++ |
| Operating system | Linux, macOS |
| Platform | x86, ARM |
| Type | Vector database |
| License | Apache License 2.0 |
| Website | milvus |
| Repository | github |
Milvus is a distributed vector database developed by Zilliz. It is available as both open-source software and a cloud service called Zilliz Cloud.
Milvus is an open-source project under the LF AI & Data Foundation[3] and is distributed under the Apache License 2.0.
History
[edit]Milvus has been developed by Zilliz since 2017.[4]
Milvus joined Linux Foundation as an incubation project in January 2020 and became a graduate in June 2021.[3] The details about its architecture and possible applications were presented at ACM SIGMOD Conference in 2021.[5]
Milvus 2.0, a major redesign of the whole product with a new architecture,[6] was released in January 2022.
Milvus 3.0 release candidate, which introduces elements of data lake / data warehouse based data processing, was published in May 2026. [2]
Features
[edit]Similarity search
[edit]Various similarity search-related features are available in Milvus:[7]
- In-memory, on-disk and GPU indices,
- Single query, batch query and range query search,
- Support of sparse vectors, binary vectors, JSON and arrays,
- FP32, FP16 and BF16 data types,
- Euclidean distance, inner product distance and cosine distance support for floating-point data,
- Hamming distance and jaccard distance for binary data,
- Support of graph indices (including HNSW), Inverted-lists based indices and a brute-force search.
- Support of vector quantization for lossy input data compression, including product quantization (PQ) and scalar quantization (SQ), that trades stored data size for accuracy,
- Re-ranking.
Milvus' similarity search engine relies on modified forks of third-party open-source similarity search libraries, such as Faiss,[8][9] DiskANN[10][11] (including the AiSAQ [12] technology from KIOXIA) and hnswlib.[13]
Milvus includes optimizations for I/O data layout, specific to graph search indices.[14]
Database
[edit]As a database, Milvus provides the following features:[7]
- Support for column-oriented databases
- Four supported data consistency levels, including strong consistency and eventual consistency[15]
- Data sharding
- Streaming data ingestion, which allows processing and ingestion of data in real-time as it arrives
- A dynamic schema, which allows insertion of data without a predefined schema
- Independent storage and compute layers
- Support for multi-tenancy scenarios (database-oriented, collection-oriented, partition-oriented)[16]
- Memory-mapped data storage
- Role-based access control
- Multi-vector and hybrid search[17]
Milvus 3.0 introduces the following features:
- Snapshots
- Nullable vector fields
- Evaluation rollbacks
Data lake
[edit]Milvus 3.0 introduces the following[18] large scale operations, applicable for vectors:
Deployment options
[edit]Milvus can be deployed as an embedded database, standalone server, or distributed cluster. Zilliz Cloud offers a fully managed version.[19]
GPU support
[edit]Milvus provides GPU accelerated index building and search using Nvidia CUDA technology[20][21] via the Nvidia cuVS library,[22] including the GPU-based graph indexing algorithm CAGRA.[23]
Integration
[edit]Milvus provides official SDK clients for Java, NodeJS, Python and Go.[24] An additional C# SDK client was contributed by Microsoft.[7][25] The database can integrate with DataDog,[26] Prometheus and Grafana for monitoring and alerts, as well as generative AI frameworks Haystack,[27] LangChain,[28] IBM Watsonx,[29] and those provided by OpenAI.[30][31]
Several storage providers have built integrations with Milvus to support AI workloads and large-scale vector search. These integrations aim to optimize performance, simplify inferencing workflows, and enhance data management capabilities:
Milvus is included in the SUSE AI platform product.[40] [41] Red Hat OpenShift AI self-managed product supports deploying Milvus.[42]
See also
[edit]
References
[edit]- ↑ "Release notes for Milvus v2.6.16". GitHub.
- 1 2 "Release notes for Milvus v3.0.0-beta". GitHub.
- 1 2 "LF AI & Data Foundation Announces Graduation of Milvus Project". June 23, 2021.
- ↑ Liao, Ingrid Lunden and Rita (2022-08-24). "Zilliz raises $60M, relocates to SF". TechCrunch. Retrieved 2024-10-21.
- ↑ "Milvus: A Purpose-Built Vector Data Management System". SIGMOD '21: Proceedings of the 2021 International Conference on Management of Data. June 18, 2021. pp. 2614–2627. doi:10.1145/3448016.3457550. ISBN 978-1-4503-8343-1.
- ↑ Guo, Rentong; Luan, Xiaofan; Xiang, Long; Yan, Xiao; Yi, Xiaomeng; Luo, Jigao; Cheng, Qianya; Xu, Weizhi; Luo, Jiarui; Liu, Frank; Cao, Zhenshan; Qiao, Yanliang; Wang, Ting; Tang, Bo; Xie, Charles (2022). "Manu: A Cloud Native Vector Database Management System". arXiv:2206.13843 [cs.DB].
- 1 2 3 "Milvus overview". Retrieved September 23, 2024.
- ↑ "Faiss". GitHub. Retrieved September 23, 2024.
- ↑ Douze, Matthijs; Guzhva, Alexandr; Deng, Chengqi; Johnson, Jeff; Szilvasy, Gergely; Mazaré, Pierre-Emmanuel; Lomeli, Maria; Hosseini, Lucas; Jégou, Hervé (2024). "The Faiss library". arXiv:2401.08281 [cs.LG].
- ↑ "DiskANN library". GitHub. Retrieved September 23, 2024.
- ↑ Subramanya, Suhas Jayaram; Kadekodi, Rohan; Krishaswamy, Ravishankar; Simhadri, Harsha Vardhan (8 December 2019). "DiskANN: fast accurate billion-point nearest neighbor search on a single node". Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc.: 13766–13776.
- ↑ "KIOXIA AiSAQ Technology Integrated into Milvus Vector Database". Retrieved May 14, 2026.
- ↑ "Hnswlib - fast approximate nearest neighbor search". GitHub. Retrieved September 23, 2024.
- ↑ Wang, Mengzhao; Xu, Weizhi; Yi, Xiaomeng; Wu, Songlin; Peng, Zhangyang; Ke, Xiangyu; Gao, Yunjun; Xu, Xiaoliang; Guo, Rentong; Xie, Charles (2024). "Starling: An I/O-Efficient Disk-Resident Graph Index Framework for High-Dimensional Vector Similarity Search on Data Segment". Proceedings of the ACM on Management of Data. 2: 1–27. arXiv:2401.02116. doi:10.1145/3639269.
- ↑ "Consistency levels in Milvus". Retrieved September 29, 2024.
- ↑ "Multi-tenancy strategies". Retrieved September 29, 2024.
- ↑ "Hybrid Search". Retrieved September 23, 2024.
- ↑ "Vector Lakebase: End the AI Data Silo". 2026-05-14. Retrieved 2026-05-14.
- ↑ "Zilliz cloud". Retrieved October 10, 2024.
- ↑ "What's New In Milvus 2.3 Beta - 10X faster with GPUs". Retrieved September 29, 2024.
- ↑ "Milvus 2.3 Launches with Support for Nvidia GPUs". 23 March 2023. Retrieved September 29, 2024.
- ↑ "NVIDIA cuVS library". GitHub.
- ↑ Ootomo, Hiroyuki; Naruse, Akira; Nolet, Corey; Wang, Ray; Feher, Tamas; Wang, Yong (August 2023). "CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs". arXiv:2308.15136 [cs.DS].
- ↑ "Install Milvus Go SDK". Retrieved September 29, 2024.
- ↑ "Get Started with Milvus Vector DB in .NET". March 6, 2024. Retrieved September 29, 2024.
- ↑ "Integration roundup: Monitoring your modern database platforms". 26 February 2025. Retrieved February 26, 2025.
- ↑ "Integration HayStack + Milvus". Retrieved September 23, 2024.
- ↑ "Milvus connector for LangChain". Retrieved September 23, 2024.
- ↑ "IBM watsonx.data's integrated vector database: unify, prepare, and deliver your data for AI". IBM. April 9, 2024. Retrieved September 29, 2024.
- ↑ "Getting started with Milvus and OpenAI". Mar 28, 2023. Retrieved September 23, 2024.
- ↑ "OpenAI and Milvus simple app". GitHub. Retrieved September 23, 2024.
- ↑ "Pure Storage Introduces New GenAI Infrastructure with NVIDIA and Run:ai". Pure Storage. 2024-06-25.
- ↑ "Cloudian AI Inferencing Platform". Cloudian. 2024-05-07.
- ↑ "Weka Debuts New Solution Blueprint to Simplify AI Inferencing at Scale". Weka. 2024-04-23.
- ↑ "Revolutionizing Biomedical GenAI with Hyperscale RAG: DDN Infinia, Milvus, and the Full PubMed Dataset". DDN. 2024-06-03.
- ↑ "Hitachi Vantara unveils AI agent-building iQ Studio". 2025-11-05. Retrieved 2026-05-14.
- ↑ "Vector Database Solution with NetApp". 2025-09-15. Retrieved 2026-05-14.
- ↑ "Connecting NAI Labs to an External Milvus Vector Database". Retrieved 2026-05-14.
- ↑ "The Data Foundation of the AI Factory: Enabling Agentic AI with Nutanix Unified Storage". 2026-03-16. Retrieved 2026-05-14.
- ↑ "Announcing SUSE AI: An Enterprise ready AI platform". 2024-11-17. Retrieved 2026-05-14.
- ↑ "Accelerating Innovation with HPE and SUSE: Secure, Scalable, and AI-Ready Infrastructure". 2025-08-04. Retrieved 2026-05-14.
- ↑ "Deploying a RAG stack in a data science project". Retrieved 2026-05-14.