Milvus
The open-source vector database built for scalable similarity search.
GitHub Stars
26k+
Contributors
400+
Enterprise Users
1000+
About Milvus
Milvus is a cloud-native vector database designed to store, index, and manage massive embedding vectors generated by deep neural networks and other machine learning models. Its architecture separates compute from storage, allowing for high scalability and resilience. Milvus supports various data types, advanced indexing algorithms for high-speed retrieval, and attribute filtering for more precise searches. It offers simple SDKs for various languages, configurable consistency levels, and features like time travel for data versioning. Milvus can be self-hosted as an open-source project or used as a fully managed service through Zilliz Cloud, its creator.
Core Features
Performance
Blazing-fast vector similarity search with support for advanced indexing algorithms like HNSW, IVF, and more.
Scalability
Cloud-native architecture that separates compute and storage, enabling high scalability for large datasets.
Rich Features
Supports attribute filtering, configurable consistency levels, time travel, and various data types.
Ease Of Use
Provides simple and intuitive SDKs for Python, Go, Java, and Node.js.
Deployment Options
Open Source
Self-host and manage Milvus for free. Ideal for customization and control.
Zilliz Cloud
A fully managed Milvus service, providing a hassle-free, enterprise-ready solution with a free tier.