milvus-io/milvus
A high-performance, cloud-native vector database designed for scalable Approximate Nearest Neighbor (ANN) search on massive unstructured data.
Core Features
Quick Start
pip install -U pymilvusDetailed Introduction
Milvus is an open-source, high-performance vector database built to power AI applications by efficiently organizing and searching vast amounts of unstructured data like text and images. Written in Go and C++, it leverages hardware acceleration for superior vector search performance. Its fully-distributed, Kubernetes-native architecture ensures horizontal scalability, enabling it to manage billions of vectors and process tens of thousands of queries per second with real-time updates. Milvus also provides a lightweight version, Milvus Lite, for easy Python integration, and is available as a fully managed service on Zilliz Cloud.