Interesting idea! What are you suggesting to do with relevance? I feel like one MEANS request returns just one best matching result while a user may want to have more. We decided to express it in SQL logic like what you see below but I'm really curious how the MEANS operator could be applied.
-----
SELECT id
FROM index_name
ORDER BY emb <-> $query_vector
LIMIT k;
-----
$query_vector may come from anywhere including being transformed on the fly from 'some text'.
Are you doing this to unlock natural human-to-model conversations? I was speaking to an AI-demo-assistant yesterday and I think I get whay you are talking about when you say the delay has to be really small.
It is an interesting idea. What troubles me is the read/write rate in a real production environment. If it is bound by S3, a buffer will eventually be needed and then it all become very complicated. At least it is how it looks on the surface
Very interesting project! I guess it could be even better if you didn't have to ingest the session data into a database but just build an index on top. I have an idea how to do it
Thanks a lot for your comment! We agree that a dataset as small as 5 GB may sound strange but it was a conscious decision. Check out our blog post to read more about the methodology of this benchmark itself.
Thanks a lot for the analytics! I am wondering how this new trend will re-shape the open-source community. I hear that some projects are denying contributions to save time going through a lot of generated code while on the other hand a lot of new projects pop up (even tough not many stay active).
Hey, great project! You mention that you didn't want to use a vector database in this project. Any particular reason for this? Have you also thought about using a search engine like Elastic or OpenSearch?