In his excellent write up on state of the art embedding models, Aapo Tanskanen compares the retrieval score for when the source documents are split into chunks and when they’re not: Transformer-based single embedding models have traditionally had 512 token context windows because of the usage of the original BERT encoder. Newer models, like the BGE-M3, have expanded the token window to much larger scales. It could be tempting to forget chunking and just embed long texts as they are. However...
