Welcome to Milvus

What is Milvus

Milvus is an open source similarity search engine for massive feature vectors. Designed with heterogeneous computing architecture for the best cost efficiency. Searches over billion-scale vectors take only milliseconds with minimum computing resources.

Milvus provides stable Python, Java and C++ APIs.

Keep up-to-date with newest releases and latest updates by reading Milvus release notes.

Heterogeneous computing

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

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

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

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

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

Milvus is compatible with almost all deep learning models and major programming languages such as Python, Java and C++, etc.
Ease of use

Milvus can be easily installed in a few steps and enables you to exclusively focus on feature vectors.
Visualized monitor

You can track system performance on Prometheus-based GUI monitor dashboards.

Architecture

Get started

Hardware Requirements

Component	Recommended configuration
CPU	Intel CPU Haswell or higher
GPU	NVIDIA Pascal series or higher
Memory	8 GB or more (depends on data size)
Storage	SATA 3.0 SSD or higher

Install using docker

Use Docker to install Milvus is a breeze. See the Milvus install guide for details.

Build from source

Software requirements

Ubuntu 18.04 or higher
CMake 3.14 or higher
CUDA 10.0 or higher
NVIDIA driver 418 or higher

Compilation

Step 1 Install dependencies

$ cd [Milvus sourcecode path]/core
./ubuntu_build_deps.sh

Step 2 Build

$ cd [Milvus sourcecode path]/core
$ ./build.sh -t Debug
or 
$ ./build.sh -t Release

When the build is completed, all the stuff that you need in order to run Milvus will be installed under [Milvus root path]/core/milvus.

Launch Milvus server

$ cd [Milvus root path]/core/milvus

Add lib/ directory to LD_LIBRARY_PATH

$ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/path/to/milvus/lib

Then start Milvus server:

$ cd scripts
$ ./start_server.sh

To stop Milvus server, run:

$ ./stop_server.sh

To edit Milvus settings in conf/server_config.yaml and conf/log_config.conf, please read Milvus Configuration.

Try your first Milvus program

Run Python example code

Make sure Python 3.5 or higher is already installed and in use.

Install Milvus Python SDK.

# Install Milvus Python SDK
$ pip install pymilvus==0.2.3

Create a new file example.py, and add Python example code to it.

Run the example code.

# Run Milvus Python example
$ python3 example.py

Run C++ example code

 # Run Milvus C++ example
 $ cd [Milvus root path]/core/milvus/bin
 $ ./sdk_simple

Run Java example code

Make sure Java 8 or higher is already installed.

Refer to this link for the example code.

Contribution guidelines

Contributions are welcomed and greatly appreciated. If you want to contribute to Milvus, please read our contribution guidelines. This project adheres to the code of conduct of Milvus. By participating, you are expected to uphold this code.

We use GitHub issues to track issues and bugs. For general questions and public discussions, please join our community.