Open namespace-Pt opened 1 week ago
Say there is a long document, then two users ask two different questions based on the document. These two questions are no way similar, targeting on different part of the document. In this case, can snapkv compress the context robustly?
Say there is a long document, then two users ask two different questions based on the document. These two questions are no way similar, targeting on different part of the document. In this case, can snapkv compress the context robustly?