# Milvus — Cloud-Native Vector Database at Scale

> Milvus is a high-performance cloud-native vector database for scalable AI search. 43.5K+ GitHub stars. Hybrid search (dense + sparse + full-text), GPU-accelerated indexing, multi-tenancy, distributed 

## Install

Save in your project root:

## Quick Use

```bash
# Install Python client
pip install "pymilvus[milvus-lite]"

# Quick start with Milvus Lite (embedded, no server needed)
python -c "
from pymilvus import MilvusClient
client = MilvusClient('milvus_demo.db')
client.create_collection('demo', dimension=128)
import random
data = [{'id': i, 'vector': [random.random() for _ in range(128)], 'text': f'doc {i}'} for i in range(10)]
client.insert('demo', data)
results = client.search('demo', data=[[random.random() for _ in range(128)]], limit=3)
print(results)
"
```

For production: Docker, Kubernetes, or Zilliz Cloud (managed).

---

## Intro

Milvus is a high-performance, cloud-native vector database built for scalable vector search in AI applications. With 43,500+ GitHub stars and Apache 2.0 license under the LF AI & Data Foundation, Milvus supports hybrid search combining dense vectors, sparse vectors, and full-text search. It features GPU-accelerated indexing (HNSW, IVF, DiskANN), multi-tenancy at database/collection/partition levels, hot/cold storage optimization, RBAC, and TLS encryption. Scales from embedded (Milvus Lite) to distributed Kubernetes clusters.

**Best for**: Teams building production vector search, RAG, recommendation systems, or image similarity at scale
**Works with**: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf
**Integrations**: LangChain, LlamaIndex, Haystack, Towhee

---

## Key Features

- **Hybrid search**: Dense vectors + sparse vectors + full-text in one query
- **GPU-accelerated indexing**: HNSW, IVF, FLAT, SCANN, DiskANN with NVIDIA GPU support
- **Distributed architecture**: Kubernetes-native horizontal scaling
- **Multi-tenancy**: Database, collection, and partition-level isolation
- **Milvus Lite**: Embedded mode for local development, no server needed
- **Hot/cold storage**: Cost optimization for large datasets
- **Enterprise security**: RBAC, TLS encryption, audit logging

---

### FAQ

**Q: What is Milvus?**
A: Milvus is a cloud-native vector database with 43.5K+ stars for scalable AI search. It supports hybrid search, GPU-accelerated indexing, and scales from embedded to distributed clusters. Apache 2.0, LF AI & Data Foundation.

**Q: How do I install Milvus?**
A: For development: `pip install "pymilvus[milvus-lite]"`. For production: use Docker, Kubernetes, or Zilliz Cloud (managed service).

---

## Source & Thanks

> Created by [Zilliz](https://github.com/milvus-io) under LF AI & Data Foundation. Apache 2.0.
> [milvus-io/milvus](https://github.com/milvus-io/milvus) — 43,500+ GitHub stars

---
Source: https://tokrepo.com/en/workflows/35f9fae3-15e7-492c-a4ae-04f6d850bef8
Author: AI Open Source