Milvus (vector database)
 | This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these messages)
|
 | |
| Developer(s) | Zilliz |
|---|---|
| Initial release | October 19, 2019 |
| Stable release | v2.4.15
/ November 5, 2024.:[1] |
| Repository | github |
| Written in | C++, Go |
| Operating system | Linux, macOS |
| Platform | x86, ARM |
| Type | Vector database |
| License | Apache License 2.0 |
| Website | milvus |
Milvus is a distributed vector database developed by Zilliz. It is available as both open-source software and a cloud service.
Milvus is an open-source project under LF AI & Data Foundation[2] distributed under the Apache License 2.0.
History
[edit]Milvus has been developed by Zilliz since 2017.[3]
Milvus joined Linux foundation as an incubation project in January 2020 and became a graduate in June 2021.[2] The details about its architecture and possible applications were presented on ACM SIGMOD Conference in 2021[4]
Milvus 2.0, a major redesign of the whole product with a new architecture,[5] was released in January 2022.
Features
[edit]Similarity search
[edit]Major similarity search related features that are available in the active 2.4.x Milvus branch[6]:
- 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 heavily-modified forks of third-party open-source similarity search libraries, such as Faiss,[7][8] DiskANN[9][10] and hnswlib.[11]
Milvus includes optimizations for I/O data layout, specific to graph search indices.[12]
Database
[edit]As a database, Milvus provides the following features:[6]:
- Column-oriented database
- Supported data consistency levels[13]:
- Strong consistency ensures that users can read the latest version of data,
- Bounded staleness allows data inconsistency during a certain period of time,
- Session ensures that all data writes can be immediately perceived in reads during the same session,
- Eventual consistency ensures that replicas eventually converge to the same state given that no further write operations are done.
- Data sharding
- Streaming data ingestion, which allows to process and ingest data in real-time as it arrives,
- Dynamic schema, which allows inserting the data without a predefined schema,
- Storage/computing disaggregation, which splits the database system into several mutually independent layers,
- Multi-tenancy scenarios (database-oriented, collection-oriented, partition-oriented)[14]
- Memory-mapped data storage,
- Role-based access control,
- Multi-vector and hybrid search[15]
Deployment options
[edit]Milvus supports working in the following modes[16]
- Embedded, which is achieved via a Python-based wrapper pymilvus[17]
- Standalone, which is designed for operating on a single machine. Docker-based images are preferred.
- Distributed, which can be deployed on a Kubernetes cluster.
A fully managed SaaS version called Zilliz Cloud[18] is available.
GPU support
[edit]Milvus provides GPU accelerated index building and search using Nvidia CUDA technology[19][20] via Nvidia RAFT library,[21] including a recent GPU-based graph indexing algorithm Nvidia CAGRA[22]
Integration
[edit]Milvus provides official SDK clients for Java, NodeJS, Python and Go.[23] An additional C# SDK client was contributed by Microsoft.[6][24]
Milvus support integration with Prometheus and Grafana for monitoring and alerts.
Milvus provides connectors[6] for OpenAI models,[25][26] HayStack,[27] LangChain[28]
Milvus supports integration with IBM Watsonx.[29]
See also
[edit]
References
[edit]- ^ "Release notes for Milvus v2.4.15". GitHub.
- ^ a b "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].
- ^ a b c d "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.
- ^ "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.
- ^ "Deployment options".
- ^ "Python SDK for Milvus". GitHub.
- ^ "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 RAFT 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.
- ^ "Getting started with Milvus and OpenAI". Mar 28, 2023. Retrieved September 23, 2024.
- ^ "OpenAI and Milvus simple app". GitHub. Retrieved September 23, 2024.
- ^ "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.
 | This article has not been added to any content categories. Please help out by adding categories to it so that it can be listed with similar articles. (November 2024) |