langchain.retrievers.multi_vector.SearchType

class langchain.retrievers.multi_vector.SearchType(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)

要执行的搜索类型的枚举器。

similarity = 'similarity'

相似性搜索。

mmr = 'mmr'

相似性搜索的最大边际相关性重新排序。

Examples using SearchType

• Set this to your Zep server URL

• The vectorstore to use to index the child chunks

• You need the dgml-utils package to use the DocugamiLoader (run pip install directly without “poetry run” if you are not using poetry)