ConfigsMar 31, 2026·2 min read

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

TO
TokRepo精选 · Community
Quick Use

Use it first, then decide how deep to go

This block should tell both the user and the agent what to copy, install, and apply first.

# 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 under LF AI & Data Foundation. Apache 2.0. milvus-io/milvus — 43,500+ GitHub stars

Related Assets

Kokoro — Lightweight 82M TTS in 9 Languages

Kokoro is an 82M parameter text-to-speech model delivering quality comparable to larger models. 6.2K+ GitHub stars. Supports English, Spanish, French, Japanese, Chinese, and more. Apache 2.0.

TokRepo精选

GPT4All — Run LLMs Privately on Your Desktop

GPT4All runs large language models privately on everyday desktops and laptops without GPUs or API calls. 77.2K+ GitHub stars. Desktop app + Python SDK, LocalDocs for private data. MIT licensed.

TokRepo精选

vLLM — High-Throughput LLM Serving Engine

vLLM is a high-throughput and memory-efficient LLM inference engine. 74.8K+ GitHub stars. PagedAttention, continuous batching, OpenAI-compatible API, multi-GPU serving. Apache 2.0.

TokRepo精选
◈Home🏆Trending👤Me