Milvos Logo
👋Join the Milvus Slack channelhere

An Open Source Vector Similarity

Search Engine

What is Milvus

Milvus is an open source similarity search engine for massive-scale feature vectors. Built with heterogeneous computing architecture for the best cost efficiency. Searches over billion-scale vectors take only milliseconds with minimum computing resources. Milvus can be used in a wide variety of scenarios to boost AI development.

  • icon

    Heterogeneous computing

    Milvus is designed with heterogeneous computing architecture for the best performance and cost efficiency.

  • icon

    Multiple indexes

    Milvus supports a variety of indexing types that employs quantization, tree-based, and graph indexing techniques.

  • icon

    Intelligent resource management

    Milvus automatically adapts search computation and index building processes based on your datasets and available resources.

  • icon

    Horizontal scalability

    Milvus supports online / offline expansion to scale both storage and computation resources with simple commands.

  • icon

    High availability

    Milvus is integrated with Kubernetes framework so that all single point of failures could be avoided.

  • icon

    Ease of use

    Milvus can be easily installed in a few steps and supports Prometheus-based GUI monitor dashboards.

Vector Search Tool Comparison

  • CPU/GPU heterogeneous computing capability
  • Quantization index
  • Hash index
  • Graph index
  • High availability
  • Distributed architecture
  • Easy-to-use user interface
  • GUI monitoring dashboard
  • Simple deployment
  • Python/JAVA/C++ SDK
  • RESTful API
  • Enterprise user support
  • Milvus
  • Faiss
  • Sptag

Scenarios

Personalized Recommender System

High-performance recommender system built with the PaddlePaddle deep learning platform

Chemical Structure Similarity Search

High-performance similarity search of massive-scale chemical structures

Try on Cloud
Boost AI development with MilvusGet started