Neural Search for medium sized corpora

Thank you for these great resources.

“Vector search” is more commonly used, so you might’ve heard it called that. In case not: https://www.pinecone.io/learn/what-is-similarity-search/

That article is very basic and fluffy, but the more technical article that it is based on and links to is excellent, so thanks for (indirectly) pointing to it:

https://hanxiao.io/2018/01/10/Build-Cross-Lingual-End-to-End...

The other stuff on that guy's (Han Xiao's) blog also looks interesting. I think this neural search stuff explains why we're all getting such low-precision results on Google/DDG by the standards we were used to. But, the claimed advantages are impressive. This is a big change in how search engines work, and I was unfamiliar with it before.

I still have reservations about where enough training data is supposed to come from, without already having a big system and user base. But, maybe some more info about that is out there. So this is another thing to look into. Wow.

I think 10 million documents is a large corpus. A retriever like Sklearn TfIdf will have a hard time handling it in a reasonable time. The main goal of Cherche is to prototype a neural search engine quickly and with a large choice of retrievers and rankers for corpus sizes < 1 million documents which is a common use case in the industry.

Search implements a wrapper of the Python ElasticSearch client that is scalable and dedicated to corpora composed of tens of millions of documents.