Find answers from the community

Updated last year

Is there a way to parse nodes from

Is there a way to parse nodes from documents with gpu? Generating embeddings is lightning fast, but node parsing seems to be the bottleneck for me.

1 comment

LLogan M

nope 🙂 It's not using a gpu or anything, its just a very sequential process

You could multiprocess this in batches of documents though

(tbh adding multiprocessing for this might be a cool PR)

Add a reply