7.0 KiB
Take a quick look at our demos!
|
|
|
| Image search | Chatbots | Chemical structure search |
|---|
Milvus is an AI-infused database geared towards (embedding) vector similarity search. Milvus is dedicated to lowering the bar for unstructured data search and providing a consistent user experience regardless of users' deployment environment.
Milvus was released under the open-source Apache License 2.0 in October 2019. It is currently an incubation-stage project under LF AI & Data Foundation.
- Functionality-level Autoscaling
With the main functionalities implemented equivalent among nodes, Milvus is able to autoscale at the functionality level, providing the foundation for a more efficient resource scheduling.
- Hybrid Search
In addition to vectors, basic numeric types, such as boolean, integer, floating-point number, etc, are introduced in Milvus. Search for data from hybrid fields are now supported in the Milvus collection.
- Combined Data Storage
Milvus has reinforced its support for both streaming and batch data persistence and for the adaptation of alternative message/storage engines, in response to users' increasing demand for high database throughput.
- Multiple Indexes in a Single Field
Milvus now supports multiple indexes in a single vector filed, and it decouples indexing from querying. Users are allowed to maintain multiple indexes simultaneously and switch flexibly among them according to their needs.
IMPORTANT The master branch is for the development of Milvus v2.0. On March 9th, 2021, we released Milvus v1.0 which is our first stable version of Milvus with long-term support. To try out Milvus v1.0, switch to branch 1.0.
Getting Started
To install a Milvus stand-alone
See Install Milvus Standalone.
To install a Milvus cluster
See Install Milvus Cluster.
Demos
- 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.
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
Milvus Docs
For documentation about Milvus, see Milvus Docs.
SDK
The implemented SDK and its API document are listed below:
Recommended Articles
- What is an embedding vector? Why and how does it contribute to the development of Machine Learning?
- What types of vector index does Milvus support? Which should I choose?
- How does Milvus compare the distance between vectors?
- You can learn more in Milvus Server Configurations.
Contact
Join the Milvus community on Slack Channel to share your suggestions, advice, and questions with our engineer team. You can also ask for help at our FAQ page.
You can subscribe to our mailing lists at:
and follow us on social media:
License
Milvus is licensed under the Apache License, Version 2.0. View a copy of the License file.
Acknowledgments
Milvus adopts dependencies from the following: