Draft:Milvus (vector database)
Submission declined on 24 September 2024 by AlphaBetaGamma (talk).
Where to get help
How to improve a draft
You can also browse Wikipedia:Featured articles and Wikipedia:Good articles to find examples of Wikipedia's best writing on topics similar to your proposed article. Improving your odds of a speedy review To improve your odds of a faster review, tag your draft with relevant WikiProject tags using the button below. This will let reviewers know a new draft has been submitted in their area of interest. For instance, if you wrote about a female astronomer, you would want to add the Biography, Astronomy, and Women scientists tags. Editor resources
|
Developer(s) | Zilliz |
---|---|
Initial release | October 19, 2019 |
Stable release | v2.4.11
/ September 11, 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 an open-source distributed vector database developed by Zilliz. It is licensed under the Apache License 2.0.
History
[edit]Milvus has been developed by Zilliz since 2017. Milvus has joined Linux foundation as an incubation project in January 2020 [2], and became a graduate in June 2021 [2].
Milestones
[edit]- Version 1.0.0 was released on 9 March 2021[3]. The details about its architecture and possible applications were presented on ACM SIGMOD Conference in 2021[4].
- Version 2.0.0 (January 2022)[5] was a major redesign of the whole product, including a new architecture [6][7], storage data format. It also added support for scalar data and integration with Prometheus and Grafana for monitoring and alerts.
- Version 2.1.0 (July 2022) added[8] support for Varchar data type, integration with Apache Kafka and RESTful API.
- Version 2.2.0 (November 2022) added[9] support for bulk data insertion, role-based access control and disk-based indices.
- Version 2.3.0 (August 2023) added[10] support for GPU acceleration, AArch64 platform, range-based similarity search, cosine distance and memory-mapped files.
- Version 2.4.0 (April 2024) added[11] support for sparse vectors, multi-vector and hybrid search [12], FP16 and BF16 data types, grouping search[13] and an advanced GPU-based indexing algorithm Nvidia CAGRA[14].
Features
[edit]Major similarity search related features that are available in the active 2.4.x Milvus branch[15]:
- 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,
- Support of HNSW index, Inverted-lists bases indices and a Brute-force search.
- Re-ranking.
Milvus relies on heavily-modified forks of third-party open-source similarity search libraries, such as Faiss[16][17], DiskANN[18][19] and hnswlib[20].
Deployment options
[edit]Milvus supports working in the following modes[21]:
- embedded, which is achieved via a Python-based wrapper pymilvus[22]
- standalone, which is designed for operating on a single machine. Docker-based images are preferred.
- distributed, which can be deployed on a Kubernetes cluster.
GPU support
[edit]Milvus provides GPU accelerated index building and search using Nvidia CUDA technology via Nvidia Raft library[23].
Integration
[edit]Milvus provides clients for Java[24], NodeJS[25], Python[22], Go[26].
Milvus provides connectors for OpenAI models[27][28], HayStack[29], LangChain[30]
See also
[edit]References
[edit]- ^ "Release notes for Milvus v2.4.11".
- ^ a b "LF AI & Data Foundation Announces Graduation of Milvus Project". June 23, 2021.
- ^ "Version 1.0.0 release". Retrieved September 23, 2024.
- ^ "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.
- ^ "Version 2.0.0 release". Retrieved September 23, 2024.
- ^ "Version 2.0.x new features". Retrieved September 23, 2024.
- ^ "Version 2.x architecture overview". Retrieved September 23, 2024.
- ^ "Release notes for Milvus v2.1.0".
- ^ "Release notes for Milvus v2.2.0".
- ^ "Release notes for Milvus v2.3.0".
- ^ "Release notes for Milvus v2.4.0-rc.1".
- ^ "Hybrid Search". Retrieved September 23, 2024.
- ^ "Grouping search". Retrieved September 23, 2024.
- ^ "CAGRA: Highly Parallel Graph Construction and Approximate Nearest Neighbor Search for GPUs". August 2023. Retrieved September 23, 2024.
- ^ "Milvus overview". Retrieved September 23, 2024.
- ^ "Faiss". Retrieved September 23, 2024.
- ^ "The Faiss library". Retrieved September 23, 2024.
- ^ "DiskANN library". Retrieved September 23, 2024.
- ^ "DiskANN: Fast Accurate Billion-point Nearest Neighbor Search on a Single Node" (PDF). Retrieved September 23, 2024.
- ^ "Hnswlib - fast approximate nearest neighbor search". Retrieved September 23, 2024.
- ^ "Deployment options".
- ^ a b "Python SDK for Milvus".
- ^ "NVIDIA RAFT library".
- ^ "Java SDK for Milvus".
- ^ "NodeJS SDK for Milvus".
- ^ "Go SDK for Milvus".
- ^ "Getting started with Milvus and OpenAI". Mar 28, 2023. Retrieved September 23, 2024.
- ^ "OpenAI and Milvus simple app". Retrieved September 23, 2024.
- ^ "Integration HayStack + Milvus". Retrieved September 23, 2024.
- ^ "Milvus connector for LangChain". Retrieved September 23, 2024.
- in-depth (not just passing mentions about the subject)
- reliable
- secondary
- independent of the subject
Make sure you add references that meet these criteria before resubmitting. Learn about mistakes to avoid when addressing this issue. If no additional references exist, the subject is not suitable for Wikipedia.