Method●Since v0.3

asRetriever

Converts the vector store into a retriever, making it suitable for use in retrieval-based workflows and allowing additional configuration.

asRetriever(
  kOrFields: number | Partial<VectorStoreRetrieverInput<VectorStoreInterface>>,
  filter: string | object,
  callbacks: Callbacks,
  tags: string[],
  metadata: Record<string, unknown>,
  verbose: boolean
): VectorStoreRetriever<VectorStoreInterface>

Parameters

Name	Type	Description
`kOrFields`	`number \| Partial<VectorStoreRetrieverInput<VectorStoreInterface>>`	Optional parameter for specifying either the number of documents to retrieve or partial retriever configurations.
`filter`	`string \| object`	Optional filter based on `FilterType` for retrieval restriction.
`callbacks`	`Callbacks`	Optional callbacks for tracking retrieval events or progress.
`tags`	`string[]`	General-purpose tags to add contextual information to the retriever.
`metadata`	`Record<string, unknown>`	General-purpose metadata providing additional context for retrieval.
`verbose`	`boolean`	If `true`, enables detailed logging during retrieval.

View source on GitHub

asRetriever

Parameters

LangChain Assistant

Menu

asRetriever

Parameters