MiniLM-L6-v2 maps paragraphs to 384 dimension vector for clustering or search

Re:MiniLM-L6-v2 maps paragraphs to 384 dimension vector for ... by sharemywin on Tuesday March 21, 2023 @03:00PM (#35250871)

anybody have thoughts on this:

https://engineering.fb.com/2017/03/29/data-infrastructure/fa...

for doing the similarity search?

I've also be thinking about looking into this:

https://milvus.io/

[ Parent | on HN ]

Re:MiniLM-L6-v2 maps paragraphs to 384 dimension vector for ... by PaulHoule on Tuesday March 21, 2023 @03:03PM (#35250906)

Faiss is great.

[ Parent | on HN ]

Re:MiniLM-L6-v2 maps paragraphs to 384 dimension vector for ... by monatis on Wednesday March 22, 2023 @01:06AM (#35257055)

Similarity search becomes a part of many technical stacks. Qdrant can be deployed as a service for fast, lightweight and filterable vector search. It's opensource, and you can also get up and running instantly and for free wit the cloud offering. You can try here https://qdrant.tech

[ Parent | on HN ]