Can someone point me to the code where it combines a question with previous context into a single coherent question? I saw this in a demo/tutorial at some point

This community is probably the experts on this, what methods are there to do information retrieval on highly noisy sources like chat channels (Slack, Discord, etc)? Due to the small amount of text, lack of context, and noise - embedding models don't seem to do well at all with these sources.

I'm trying to use the SentenceSplitter but it's removing all the spaces, newlines etc between sentences. Is there some way to keep the text in the input format? Even within the same node, all of the whitespaces between sentences are gone.