search_batched
API Definition
def search_batched(queries: numpy.ndarray, final_num_neighbors: int, pre_reorder_num_neighbors: int, leaves_to_search: int) -> tuple(index, distance)
Function
Batch query search (single-thread behavior consistent with the open source algorithm).
Parameters
Parameter |
Data Type |
Description |
Value Range |
|---|---|---|---|
queries |
numpy.ndarray |
Queries in a batch. |
The value cannot be null. |
final_num_neighbors |
int |
Number of returned results. |
≥ 1 |
pre_reorder_num_neighbors |
int |
Number of results saved before reordering. |
≥ final_num_neighbors, where final_num_neighbors indicates the number of results returned. |
leaves_to_search |
int |
Number of subspaces to be searched. |
[1, num_leaves], where num_leaves indicates the total number of subspaces in the IVF index partition. |
Return Value
Data Type |
Description |
|---|---|
tuple(index, distance) |
index is the numpy.ndarray type data that contains final_num_neighbors base library IDs. distance is the numpy.ndarray type data that contains final_num_neighbors distances. |