Milvus

An open-source vector database developed by Zilliz for storing and similarity-searching large collections of vector embeddings.

1 articleLast mentioned

Milvus is an open-source vector database for storing vector embeddings and searching them by similarity. It was developed by the startup Zilliz and released in 2019, and was donated to the LF AI & Data Foundation in 2020, where it is maintained as a foundation project. It is designed to handle billions of vectors in a distributed architecture; Zilliz offers a managed cloud service, Zilliz Cloud.

It is widely used in RAG systems as the store that holds document embeddings and retrieves the documents closest to a query, and also in image search and recommendation systems. It is counted among the leading vector databases alongside Pinecone, Weaviate, and Qdrant.

This entry is based on AIPOST articles and widely known facts. If something is wrong, please send us a correction request.

Articles covering this entry

  • NVIDIA Agent Toolkit Bets on Harness Engineering and Knowledge GraphsAI News ·

    The company's NeMo Retriever parse, embed and rerank components feed Milvus vector stores for exactly this purpose.

    Read article

Found a mistake or missing an entry?

Wiki entries are based on AIPOST articles and widely known facts. If an entry is wrong, send us a correction request and we will check and fix it. Names from new articles are added to the wiki after the article is published.