icsa

https://github.com/hwchase17/langchain/tree/master/langchain/docstore)/base.py The search method of base.py states: """Search for document. If page exists, return the page summary, and a Document object. If page does not exist, return similar entries. """...

Add C-minHash variant

11

C-minHash (or Circulant minHash) needs only two permutations versus K permutations, in practice. This minHash variant could save significant storage space for large-scale data. source: https://arxiv.org/abs/2109.03337