Search

APP_ERROR Search(int n, const float16_t *queries, int topk, idx_t *indices, float *distances, unsigned int tableLen = 0, const float *table = nullptr)

Queries the topk base library subscript indexes nearest to the query vector and the corresponding distances. For example, if a valid mapping table (tableLen > 0 and *table is a non-null pointer) is passed, the distance after mapping is output.

int n: number of feature vectors to be queried.

const float16_t *queries: feature vectors to be queried. The length is n x vector dimension dim.

int topk: sorts the distances between the query vector and the base library and returns topk results.

unsigned int tableLen: length of the mapping table. The default value is 0, indicating that no mapping is performed. Currently, the mapping table length can be set to 10000.

const float *table: pointer of the mapping table, pointing to the storage space of valid mapping values with the tableLen length. Currently, the supported redundancy length is 48, that is, the length of the space to which *table points is 10048 x sizeof(float) bytes.

float *distances: external memory, indicating the cosine distance corresponding to topk x n base library feature vectors with the highest query similarity. The length is n x topk.

idx_t *indices: external memory, indicating the subscript index corresponding to the topk base library vectors with the highest query similarity. The length is n x topk.

APP_ERROR: return status. For details, see Return Code Reference.

• n: The value range is [0, capacity].
• topk: The value range of k is [0, 1024].
• If both TableLen and *table meet the requirements during the parameter pass, the API maps the calculated distance.

  First, the distance value is normalized to a floating point number f1 in the range of [0, 1], and then f1 is multiplied by tableLen and rounded up to obtain an integer index between [0, tableLen]. Then, the integer index is used as an offset to obtain the corresponding score from the memory space pointed to by *table. The mapping is completed, and score is saved to *distance .

  The index mapping formula is as follows: ((CosDistance + 1)/2) x tableLen