Home
Milvus is an open-source vector database built to power AI applications and vector similarity search. It is available in:
- Milvus standalone
- Milvus cluster
Release date: 2022-01-25
We are excited to announce the general release of Milvus 2.0 and it is now considered as production ready. Without changing the existing functionality released in the PreGA release, we fixed several critical bugs reported by users. We sincerely encourage all users to upgrade your Milvus to 2.0 release for better stability and performance.
| Milvus Version | Python SDK Version | JAVA SDK Version | GO SDK Version | Node SDK |
|---|---|---|---|---|
| 2.0.0 | 2.0.0 | 2.0.2 | 2.0.0 | 2.0.0 |
- Installation: installation guide for Milvus 2.0 (Standalone & Cluster)
- User Guide: introduction & sample use of common operations
- Advanced Deployment: more configurations, deployment with external components, migration from/to Milvus, upgrade using helm chart
-
Bootcamp:
- Benchmark: python scripts for benchmark test on 1 million and 100 million data.
- Solutions: sample codes & quick-deploy guide for use of Milvus in various scenarios, together with related technical articles and live streams.
- Online Demo
Built on top of popular vector search libraries including Faiss, Annoy, HNSW, and more, Milvus was designed for similarity search on dense vector datasets containing millions, billions, or even trillions of vectors. Before proceeding, familiarize yourself with the basic principles of embedding retrieval.
Milvus also supports data sharding, data persistence, streaming data ingestion, hybrid search between vector and scalar data, time travel, and many other advanced functions. The platform offers performance on demand and can be optimized to suit any embedding retrieval scenario. We recommend deploying Milvus using Kubernetes for optimal availability and elasticity.
Milvus adopts a shared-storage architecture featuring storage and computing disaggregation and horizontal scalability for its computing nodes. Following the principle of data plane and control plane disaggregation, Milvus comprises four layers: access layer, coordinator service, worker node, and storage. These layers are mutually independent when it comes to scaling or disaster recovery.
For more details about Milvus' architecture, see Computing/Storage Disaggregation and Main Components.
Milvus is trusted by over 1,000 organizations worldwide and has applications in almost every industry. What follows is a list of Milvus users that have adopted the software in production.