An Open Source Vector Similarity Search Engine
Milvus is easy-to-use, highly reliable, scalable, robust, and blazing fast.
Milvus is an LF AI Foundation incubation project.
Comprehensive Similarity Metrics
Milvus offers frequently used similarity metrics, including Euclidean distance, inner product, Hamming distance, Jaccard distance, etc., allowing you to explore vector similarity in the most effective and efficient way possible.
Leading-Edge Performance
Milvus is built on top of multiple optimized Approximate Nearest Neighbor Search (ANNS) indexing libraries, including faiss, annoy, hnswlib, etc., thus ensuring that you always get the best performance across various scenarios.
Dynamic Data Management
No longer troubled by static data, you can operate data with insertion, deletion, search and update whenever needed.
Near Real Time Search
Data is available for search almost immediately after being inserted and updated. Milvus does the heavy lifting in your best interests in terms of both result accuracy and data consistency.
Cost Efficient
Milvus harnesses the parallelism of modern processors and enables billion-scale similarity searches in milliseconds on a single off-the-shelf server.
Rich Data Type and Advanced Search
Milvus supports various data types for fields in a record. You can also use advanced search methods, such as filtering, sorting and aggregation for one or multiple fields.
Highly Scalable and Robust
You can deploy Milvus in a distributed environment. To increase the capacity and reliability of a Milvus cluster, you can simply add more nodes.
Cloud Native
We make it easy for you to run Milvus on public cloud, private cloud, or somewhere in between.
Ease of Use
Milvus provides easy-to-use SDKs in Python, Java, Go and C++, as well as a RESTful API.
Open Source
Milvus is open-sourced on GitHub.
Contributions and feedback are welcome!
Tools & SDK
Milvus User Community
Get Involved
Contribute
Milvus is a community project. We encourage you to join the effort and contribute feedback, ideas and code.
Join Us on Github >