Blog

Our Journey to 35K+ Stars: The Story of Building Milvus from Scratch

Product

VDBBench 1.0: Open-Source VectorDB Benchmarking with Production Workloads

The High-Performance Vector Database Built for Scale

Milvus is an open-source vector database built for GenAI applications. Install with pip, perform high-speed searches, and scale to tens of billions of vectors with minimal performance loss.

Milvus Quickstart Try Managed Milvus

Start running Milvus in seconds

• Create Collection
• Insert Data
• Search
• Delete Data

from pymilvus import MilvusClient
client = MilvusClient("milvus_demo.db")
client.create_collection(
  collection_name="demo_collection",
  dimension=5
)

Deployment Options to Match Your Unique Journey

• Milvus Lite

Lightweight, easy to start

1. VectorDB-as-a-library runs in notebooks/ laptops with a pip install
2. Best for learning and prototyping

Get Started Learn More

• Milvus Standalone

Robust, single-machine deployment

1. Complete vector database for production or testing
2. Ideal for datasets with up to millions of vectors

Get Started Learn More

• Milvus Distributed

Scalable, enterprise-grade solution

1. Highly reliable and distributed vector database with comprehensive toolkit
2. Scale horizontally to handle billions of vectors

Get Started Learn More

• Zilliz Cloud (fully managed Milvus)

Hassle-free and 10x faster than Milvus

1. Available in both serverless and dedicated cluster
2. SaaS and BYOC options for different security and compliance requirements

Try Free

Learn more about different Milvus deployment models

Plays nicely with all your favorite AI dev tools

• 
• 
• 
• 
• 
• 
• 
• 

Start Building Your GenAI App

Guided with notebooks developed by us and our community

• 

RAG

Try Now

• 

Image Search

Try Now

• 

Multimodal Search

Try Now

• 

Hybrid Search

Try Now

• 

Graph RAG

Try Now

Loved by GenAI developers

• Based on our research, Milvus was selected as the vector database of choice (over Chroma and Pinecone). Milvus is an open-source vector database designed specifically for similarity search on massive datasets of high-dimensional vectors.\
  \
  \
  \
  Nandula Asel\
  \
  Senior Data Scientist\
  \
  

• With its focus on efficient vector similarity search, Milvus empowers you to build robust and scalable image retrieval systems. Whether you’re managing a personal photo library or developing a commercial image search application, Milvus offers a powerful foundation for unlocking the hidden potential within your image collections.\
  \
  \
  \
  Bhargav Mankad\
  \
  Senior Solution Architect\
  \
  

• Milvus is a powerful vector database tailored for processing and searching extensive vector data. It stands out for its high performance and scalability, rendering it perfect for machine learning, deep learning, similarity search tasks, and recommendation systems.\
  \
  \
  \
  Igor Gorbenko\
  \
  Big Data Architect\
  \
  

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• 

• Trusted for production workloads

Trusted for production workloads

Unstructured Data Meetups

Join a Community of Passionate Developers and Engineers Dedicated to Gen AI.

RSVP now

Why Developers Prefer Milvus for Vector Databases

• 

Scale as needed

Scale elastically to support tens of billions of vectors with a fully distributed

• 

Blazing fast

Retrieve data quickly and accurately with Global Index, regardless of scale.

• 

Reusable Code

Write once, and deploy with one line of code into the production environment.

• 

Supportive Community

Fan-favorite vector database with extensive resources and supportive contributors.

• 

Feature-rich

Metadata filtering, hybrid search, multi-vector and more.

Want to learn more about Milvus? View our documentation