Find answers from the community

Updated 9 months ago

I'm curious that, for

I'm curious that, for RecursiveRetriever or BM25Retriever or other retriever that requires to store the nodes as attribute, are they suitable for use cases where large amount of documents exist? Would that consume too much memory?

2 comments

bbeaverTango

I tested it on a few hundred docs would have to increase the size and check it out. But they seem to work fine until now.

llgfusb

thanks~

Add a reply