search

Function

Retrieves documents in a database that are similar to the passed document.

Prototype

def search(embeddings, k, filter_dict)

Parameters

Parameter

Data Type

Required/Optional

Description

embeddings

List[List[float]]

Required

Vector embeddings. The number of vectors falls within the range of [1, 1024 × 1024).

k

Integer

Optional

Number of returned similar vectors. The value is greater than 0. The default value is 3. The value range is (0, 10000].

filter_dict

Dict

Optional

Reserved. MindFAISS does not support filtered retrieval.

Return Value

Data Type

Description

Tuple[List[List[float]], List[List[int]]]

Two pieces of data are returned. The first piece of data indicates the score list of the similar vectors, and the second one indicates the ID list of the similar vectors.