The community member is asking whether the semantic splitter is better than the paragraph splitter for chunking techniques, and whether there is any improved relevancy in the retrieved nodes. The comments suggest that it likely depends on the specific use case, and the community members agree that testing both approaches may be necessary to determine the best approach.
Hey does anyone know if sematic splitter is better than using paragraph splitter for chunking technique? Like is there any improved relevancy in the retrieved nodes? Does it just depend and you need to simply test both?
