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](https://github.com/milvus-io/milvus/blob/master/LICENSE) in October 2019. It is currently a graduate project under [LF AI & Data Foundation](https://lfaidata.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](https://github.com/milvus-io/milvus/tree/1.0).
<summary>Click to take a quick look at our demos!</summary>
<table>
## Make Milvus
You can also build Milvus from source code.
### Prerequisites
Install the following before building Milvus from source code.
-[Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) for version control.
-[Golang](https://golang.org/doc/install) version 1.15 or higher and associated toolkits.
-[CMake](https://cmake.org/install/) version 3.14 or higher for compilation.
-[OpenBLAS](https://github.com/xianyi/OpenBLAS/wiki/Installation-Guide)(Basic Linear Algebra Subprograms) library version 0.3.9 or higher for matrix operations.
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.
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](https://lfaidata.foundation/).
-[Image Search](https://zilliz.com/milvus-demos)
-**Blazing Fast**
Images made searchable. Instantaneously return the most similar images from a massive database.
Average latency measured in milliseconds on ten million vector datasets.
-[Chatbots](https://zilliz.com/milvus-demos)
Supports CPU SIMD, GPU, and FPGA accelerations, fully utilizing available hardware resources to achieve cost efficiency.
Interactive digital customer service that saves users time and businesses money.
Blazing fast similarity search, substructure search, or superstructure search for a specified molecule.
Consistent cross-platform UX from laptop, to local cluster, to cloud.
Embed real-time search and analytics into virtually any application.
## Bootcamps
-**Stable and Resilient**
Milvus [bootcamp](https://github.com/milvus-io/bootcamp/tree/new-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.
Milvus’ built-in replication and failover/failback features ensure data and applications can maintain business continuity in the event of a disruption.
-**High Elasticity**
Component-level scalability makes it possible to only scale where necessary.
-**Community Backed**
With over 1,000 enterprise users, 5,000+ stars on GitHub, and an active open-source community, you’re not alone when you use Milvus.
> **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](https://github.com/milvus-io/milvus/tree/1.0).
## Getting Started
### Demos
-[Image Search](https://zilliz.com/milvus-demos): Images made searchable. Instantaneously return the most similar images from a massive database.
-[Chatbots](https://zilliz.com/milvus-demos): Interactive digital customer service that saves users time and businesses money.
-[Chemical Structure Search](https://zilliz.com/milvus-demos): Blazing fast similarity search, substructure search, or superstructure search for a specified molecule.
## Contributing
...
...
@@ -119,26 +235,25 @@ Contributions to Milvus are welcome from everyone. See [Guidelines for Contribut
## Documentation
### Milvus Docs
For documentation about Milvus, see [Milvus Docs](https://milvus.io/docs/overview.md).
### SDK
The implemented SDK and its API documentatation are listed below:
The implemented SDK and its API documentation are listed below:
-[What is an embedding vector? Why and how does it contribute to the development of Machine Learning?](https://milvus.io/docs/v1.0.0/vector.md)
-[Which vector indexes does Milvus support? Which should I choose?](https://milvus.io/docs/v1.0.0/index.md)
-[How does Milvus compare the distance between vectors?](https://milvus.io/docs/v1.0.0/metric.md)
- You can learn more in [Milvus Server Configurations](https://milvus.io/docs/v1.0.0/milvus_config.md).
## Community
## Contact
Join the Milvus community on [Slack](https://join.slack.com/t/milvusio/shared_invite/zt-e0u4qu3k-bI2GDNys3ZqX1YCJ9OM~GQ) to share your suggestions, advice, and questions with our engineering team.
Join the Milvus community on [Slack Channel](https://join.slack.com/t/milvusio/shared_invite/zt-e0u4qu3k-bI2GDNys3ZqX1YCJ9OM~GQ) to share your suggestions, advice, and questions with our engineering team. You can also submit questions to our [FAQ page](https://milvus.io/docs/v1.0.0/performance_faq.md).
You can also check out our [FAQ page](https://milvus.io/docs/v1.0.0/performance_faq.md) to discover solutions or answers to your issues or questions.
Subscribe to our mailing lists:
...
...
@@ -149,13 +264,11 @@ Subscribe to our mailing lists:
Milvus is licensed under the Apache License, Version 2.0. View a copy of the [License file](https://github.com/milvus-io/milvus/blob/master/LICENSE).
Zilliz, the company behind Milvus, is [actively hiring](https://app.mokahr.com/apply/zilliz/37974#/) full-stack developers and solution engineers to build the next-generation open-source data fabric.