Method●Since v1.0

asRetriever

Creates a VectorStoreRetriever instance with flexible configuration options.

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

Parameters

Name	Type	Description
`kOrFields`	`number \| Partial<VectorStoreRetrieverInput<FakeVectorStore>>`	If a number is provided, it sets the `k` parameter (number of items to retrieve). If an object is provided, it should contain various configuration options.
`filter`	`(doc: Document) => boolean`	Optional filter criteria to limit the items retrieved based on the specified filter type.
`callbacks`	`Callbacks`	Optional callbacks that may be triggered at specific stages of the retrieval process.
`tags`	`string[]`	Tags to categorize or label the `VectorStoreRetriever`. Defaults to an empty array if not provided.
`metadata`	`Record<string, unknown>`	Additional metadata as key-value pairs to add contextual information for the retrieval process.
`verbose`	`boolean`	If `true`, enables detailed logging for the retrieval process. Defaults to `false`.

Example

Basic usage with a `k` value:

const retriever = myVectorStore.asRetriever(5);

View source on GitHub

asRetriever

Parameters

Example

LangChain Assistant

Menu

asRetriever

Parameters

Example