Function: create_search_result

Applicability

Product	Supported (√/x)
Atlas A3 training products / Atlas A3 inference products	x
Atlas A2 training products / Atlas A2 inference products	x
Atlas training products	x
Atlas inference products	√
Atlas 200I/500 A2 inference products	x

Function Usage

Creates data of the aclfvSearchResult type as a search result.

To destroy data of the aclfvSearchResult type, call Function: destroy_search_result.

The Atlas inference accelerator modules in the Atlas inference products does not support this API.

Prototype

C Prototype

        
             aclfvSearchResult *aclfvCreateSearchResult(uint32_t queryCnt, uint32_t *resultNum, uint32_t resultNumDataLen,uint32_t *id0, uint32_t *id1, uint32_t *resultOffset, float *resultDistance, uint32_t dataLen)

Python Function

        
             search_result = acl.fv.create_search_result(query_cnt, result_num, result_num_data_len, id_0, id_1, result_offset, result_distance, data_len)

Parameter Description

Parameter	Description
query_cnt	Int, number of query requests, fixed at 1 in 1:N mode
result_num	Int, number of results of each query request.
result_num_data_len	Int, total memory size of resultNum
id_0	Int, repository 0 ID. The number of elements equals *topK queryCnt**.
id_1	Int, repository 0 ID. The number of elements equals *topK queryCnt**.
result_offset	Int, Denotes the distance between each search result and its corresponding search request.The number of elements equals *topK queryCnt**.
result_distance	Int, distance between each query result and the query request. The number of elements equals *topK queryCnt**.
data_len	Int, requested memory size: topK * queryCnt * 4 bytes

Return Value Description

Return Value	Description
search_result	Int, pointer address. Success: data of the aclfvSearchResult type If 0 is returned, the operation fails.

Return Value

Description

search_result

Int, pointer address.

Success: data of the aclfvSearchResult type
If 0 is returned, the operation fails.

Reference

For details about the API call sequence and sample code, see Feature Vector Search.

Parent topic: Feature Vector Search