6.3 KiB
Welcome to Milvus
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 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 built 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 |
| RAM | 8 GB or more (depends on data size) |
| Hard drive | 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.
Milvus roadmap
Please read our roadmap to learn about upcoming features.
Contribution guidelines
Contributions are welcomed and greatly appreciated. Please read our contribution guidelines for detailed contribution workflow. 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.
Join the Milvus community
To connect with other users and contributors, welcome to join our slack channel.
Thanks
We greatly appreciate the help of the following people.
- akihoni found a broken link and a small typo in the README file.