News for hackers. Stuff that matters.
Re:New and Improved Embedding Model for OpenAI by gk1 on Thursday December 15, 2022 @07:23PM (#34007788)
I meant OpenAI + Vector Database as more common than OpenAI Search API. And then Pinecone as an example of a vector database.
Re:New and Improved Embedding Model for OpenAI by lmeyerov on Thursday December 15, 2022 @09:58PM (#34009255)
Ah yes, thanks!

Yeah we saw faiss + es leaders for serving embeddings / vector search, and pinecone / weaviate / I think milvus as next tier, so was curious if we could improve the analysis :)

Re:New and Improved Embedding Model for OpenAI by gk1 on Thursday December 15, 2022 @10:07PM (#34009374)
Is the analysis public? I'm curious how you determined the popularity of a product like Pinecone, since we don't have a public metric like GitHub stars.
Re:New and Improved Embedding Model for OpenAI by lmeyerov on Friday December 16, 2022 @11:30AM (#34016511)
Loosely measure search, CVs, and job ads: https://gradientflow.com/the-vector-database-index/

This kind of analysis is rarely precise, but is useful for rougher tasks like tiering

My personal question is if vector indexes are/will be a good-enough general DB feature / compute lib for most users & use cases. A lucrative niche market can still happen as VC dollars disappear, similar to graph DBs, so not a knock, just important for folks deciding how to build things.

Re:New and Improved Embedding Model for OpenAI by andre-z on Friday December 16, 2022 @12:57AM (#34010990)
FAISS is depreciating since it is just a library that does not scale and lacks a lot of vector db functionalities like filtering. ES is often used just by default because Devs have experience with but the performance is very low compared to dedicated solutions. The Github trending for Vector Databases https://github.com/topics/vector-database