search_with_threshold

Function

Retrieves vectors similar to the passed vector in a database and filters them based on the threshold.

Prototype

def search_with_threshold(embeddings, k, threshold, filter_dict)

Parameters

Parameter

Data Type

Required/Optional

Description

embeddings

Union[ndarray, List[Dict[int, float]]]

Required

Dense or sparse vector. For a dense vector, the data type is ndarray; for a sparse vector, the data type is List[Dict[int, float]].

k

Integer

Optional

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

threshold

Float

Optional

Score threshold. The default value is 0.1. The value range is [0.0, 1.0].

filter_dict

Dict

Optional

Dictionary consisting of retrieval criteria. Currently, only document IDs can be filtered. The filtered document IDs are passed in a list. The length of the ID list cannot exceed 1000 × 1000. For example, if you need to filter the documents whose IDs are 1, 2, and 4, the input dictionary is {"document_id": [1, 2, 4]}.

Return Value

Data Type

Description

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

Scores and IDs of the most similar k vectors.