I am a bit curious, I watched an implementation of small to big retrieval and noticed that they include the same information over various chunk sizes. During retrieval wouldn’t we be getting the same information over various chunks sizes?
Right, but wouldn't you limit the "different" chunks you are getting, essentially limiting the context? Cause you might end up retrieving kinda the same info (same parent) that is present on both the 256,512 and 1024 chunk.
Interesting so although we might be creating chunks of smaller sizes eg 128,256,512 (given a parent of 1024), for the retrieval only the smallest ones will be used for our case the 128. I suppose the intermediate ones are used for the merging process you mentioned? Really appreciate the insights you provided
Thank you. I do have a followup question thought it is more of an opinion. Would you pair this retrieval approach with a reranker? If yes, I suppose you would do it after the chunks were merged