Gets the most relevant documents to a query along with their similarity score. The returned documents are ordered by similarity (most similar at the first index)
similaritySearchVectorWithScore(
query: number[],
k: number,
filter: string
): Promise<[Document<Record<string, any>>, number][]>| Name | Type | Description |
|---|---|---|
query* | number[] | The embedded query to search the store by |
k* | number | The number of documents to retreive |
filter | string | The SQL |