Method●Since v0.1

similarity_search_with_score

Return the top-k documents most similar to a text query, with scores.

similarity_search_with_score(
  self,
  query: str,
  k: int = 4,
  filter: dict[str, Any] | None = None,
  **kwargs: Any = {}
) -> list[tuple[Document, float]]

Parameters

Name	Type	Description
`query`*	`str`	Natural-language query to embed and search with
`k`	`int`	Default:`4` Number of results to return
`filter`	`dict[str, Any] \| None`	Default:`None` Filter by metadata
`kwargs`	`Any`	Default:`{}` Additional keyword args

View source on GitHub

similarity_search_with_score

Parameters

LangChain Assistant

Menu

similarity_search_with_score

Parameters