Well, I suppose its website have answered the similar question. From my point of view, FAISS and ANNOY are algorithm libraries which can be integrated into any application, but can't be used directly. Meanwhile, Milvus is a server can provide ANNS services independently, which already integrated many ANNS libraryies like FAISS and ANNOY. On the other hand, neighter FAISS nor ANNOY can solve all scenarios which have different vectors data size and distribution. As a server, Milvus can choose right algorithm to solve the problem.

disclosure: I am with the Milvus team.

Milvus positions itself as an open source vector similarity search engine built on top of various ANNS algorithms,including Faiss, Annoy, HNSW, etc.

As a vector similarity search engine server, Milvus is designed for easy to use, high reliability, easy to scale, and high performance. Milvus supports near real-time search, CRUD, WAL, data consistency, distributed deployment, high availability, and more.

Hope this answers your question.

It sounds like a database for AI. Is there any performance report I could read?

good to use, could have a try