What’s Milvus, the golang open-source vector database?
Milvus is an open-source vector database constructed to energy embedding similarity search and AI purposes. Milvus makes unstructured information search extra accessible and offers a constant person expertise whatever the deployment surroundings.
Milvus 2.0 is a cloud-native vector database with storage and computation separated by design. All parts on this refactored model of Milvus are stateless to reinforce elasticity and adaptability. For extra structure particulars, see Milvus Structure Overview.
Milvus was launched underneath the open-source Apache License 2.0 in October 2019. It’s presently a graduate challenge underneath LF AI & Knowledge Basis.
Golang Mission Key options
Millisecond search on trillion vector datasetsSimplified unstructured information administrationDependable, at all times on vector databaseExtremely scalable and elasticHybrid searchUnified Lambda constructionGroup supported, trade acknowledged
Fast begin
Set up Milvus
Construct Milvus from supply code
Examine the necessities first.
Linux techniques (Ubuntu 18.04 or later beneficial):
go: >= 1.18 cmake: >= 3.18 gcc: 7.5
MacOS techniques with x86_64 (Huge Sur 11.5 or later beneficial):
go: >= 1.18 cmake: >= 3.18 llvm: >= 12
MacOS techniques with Apple Silicon (Monterey 12.0.1 or later beneficial):
go: >= 1.18 (Arch=ARM64) cmake: >= 3.18 llvm: >= 13
Clone Milvus repo and construct.
# Clone github repository. $ git clone https://github.com/milvus-io/milvus.git # Set up third-party dependencies. $ cd milvus/ $ ./scripts/install_deps.sh # Compile Milvus. $ make
For the total story, see developer’s documentation.
IMPORTANT The grasp department is for the event of Milvus v2.0. On March ninth, 2021, we launched Milvus v1.0, the primary steady model of Milvus with long-term assist. To make use of Milvus v1.0, swap to department 1.0.
Milvus 2.0 vs. 1.x: Cloud-native, distributed structure, extremely scalable, and extra
See Milvus 2.0 vs. 1.x for extra data.
