README

milvus banner


What is Milvus?

Milvus is an open-source vector database built to power AI applications and embedding similarity search. Milvus makes unstructured data search more accessible, and provides a consistent user experience regardless of the deployment environment.

Both Milvus Standalone and Milvus Cluster are available.

Milvus was released under the open-source Apache License 2.0 in October 2019. It is currently a graduate project under LF AI & Data Foundation.

Key features

Millisecond search on trillion vector datasets Average latency measured in milliseconds on trillion vector datasets.
Simplified unstructured data management
  • Rich APIs designed for data science workflows.
  • Consistent user experience across laptop, local cluster, and cloud.
  • Embed real-time search and analytics into virtually any application.
  • Reliable, always on vector database Milvus’ built-in replication and failover/failback features ensure data and applications can maintain business continuity in the event of a disruption.
    Highly scalable and elastic Component-level scalability makes it possible to scale up and down on demand. Milvus can autoscale at a component level according to the load type, making resource scheduling much more efficient.
    Hybrid search In addition to vectors, Milvus supports data types such as Boolean, integers, floating-point numbers, and more. A collection in Milvus can hold multiple fields for accommodating different data features or properties. By complementing scalar filtering to vector similarity search, Milvus makes modern search much more flexible than ever.
    Unified Lambda structure Milvus combines stream and batch processing for data storage to balance timeliness and efficiency. Its unified interface makes vector similarity search a breeze.
    Community supported, industry recognized With over 1,000 enterprise users, 6,000+ stars on GitHub, and an active open-source community, you’re not alone when you use Milvus. As a graduate project under the LF AI & Data Foundation, Milvus has institutional support.

    IMPORTANT The master branch is for the development of Milvus v2.0. On March 9th, 2021, we released Milvus v1.0, the first stable version of Milvus with long-term support. To use Milvus v1.0, switch to branch 1.0.

    Installation

    Install Milvus Standalone

    Install with Docker-Compose

    $ cd milvus/deployments/docker/standalone
    $ sudo docker-compose up -d
    

    Install with Helm

    $ helm install -n milvus --set image.all.repository=registry.zilliz.com/milvus/milvus --set image.all.tag=master-latest milvus milvus-helm-charts/charts/milvus-ha
    

    Build from source code

    # Clone github repository.
    $ cd /home/$USER/
    $ git clone https://github.com/milvus-io/milvus.git
    
    # Install third-party dependencies.
    $ cd /home/$USER/milvus/
    $ ./scripts/install_deps.sh
    
    # Compile Milvus standalone.
    $ make standalone
    

    Install Milvus Cluster

    Install with Docker-Compose

    $ cd milvus/deployments/docker/distributed
    $ sudo docker-compose up -d
    

    Install with Helm

    $ helm install -n milvus --set image.all.repository=registry.zilliz.com/milvus/milvus --set image.all.tag=master-latest --set standalone.enabled=false milvus milvus-helm-charts/charts/milvus-ha
    

    Build from source code

    # Clone github repository.
    $ cd /home/$USER
    $ git clone https://github.com/milvus-io/milvus.git
    
    # Install third-party dependencies.
    $ cd milvus
    $ ./scripts/install_deps.sh
    
    # Compile Milvus Cluster.
    $ make milvus
    

    Milvus 2.0 is better than Milvus 1.x

      Milvus 1.x Milvus 2.0
    Architecture Shared storage Cloud native
    Scalability 1 to 32 read nodes with only one write node 500+ nodes
    Durability
  • Local disk
  • Network file system (NFS)
  • Object storage service (OSS)
  • Distributed file system (DFS)
  • Availability 99% 99.9%
    Data consistency Eventual consistency Three levels of consistency:
  • Strong
  • Session
  • Consistent prefix
  • Data types supported Vectors
  • Vectors
  • Fixed-length scalars
  • String and text (in planning)
  • Basic operations supported
  • Data insertion
  • Data deletion
  • Approximate nearest neighbor (ANN) Search
  • Data insertion
  • Data deletion (in planning)
  • Data query
  • Approximate nearest neighbor (ANN) Search
  • Recurrent neural network (RNN) search (in planning)
  • Advanced features
  • Mishards
  • Milvus DM
  • Scalar filtering
  • Time Travel
  • Multi-site deployment and multi-cloud integration
  • Data management tools
  • Index types and libraries
  • Faiss
  • Annoy
  • Hnswlib
  • RNSG
  • Faiss
  • Annoy
  • Hnswlib
  • RNSG
  • ScaNN (in planning)
  • On-disk index (in planning)
  • SDKs
  • Python
  • Java
  • Go
  • RESTful
  • C++
  • Python
  • Go (in planning)
  • RESTful (in planning)
  • C++ (in planning)
  • Release status Long-term support (LTS) Release candidate. A stable version will be released in August.

    Getting Started

    Demos

    Image search Chatbots Chemical structure search
    • Image Search

      Images made searchable. Instantaneously return the most similar images from a massive database.

    • Chatbots

      Interactive digital customer service that saves users time and businesses money.

    • Chemical Structure Search

      Blazing fast similarity search, substructure search, or superstructure search for a specified molecule.

    Bootcamps

    Milvus bootcamp are designed to expose users to both the simplicity and depth of the vector database. Discover how to run benchmark tests as well as build similarity search applications spanning chatbots, recommendation systems, reverse image search, molecular search, and much more.

    Contributing

    Contributions to Milvus are welcome from everyone. See Guidelines for Contributing for details on submitting patches and the contribution workflow. See our community repository to learn about our governance and access more community resources.

    Documentation

    SDK

    The implemented SDK and its API documentation are listed below:

    Community

    Join the Milvus community on Slack to share your suggestions, advice, and questions with our engineering team.

    Miluvs Slack Channel

    You can also check out our FAQ page to discover solutions or answers to your issues or questions.

    Subscribe to our mailing lists:

    Follow us on social media:

    Join Us

    Zilliz, the company behind Milvus, is actively hiring full-stack developers and solution engineers to build the next-generation open-source data fabric.

    Acknowledgments

    Milvus adopts dependencies from the following:

    • Thank FAISS for the excellent search library.
    • Thank etcd for providing some great open-source tools.
    • Thank Pulsar for its great distributed information pub/sub platform.
    • Thank RocksDB for the powerful storage engines.