Function cuvsRefine 

pub unsafe extern "C" fn cuvsRefine(
    res: cuvsResources_t,
    dataset: *mut DLManagedTensor,
    queries: *mut DLManagedTensor,
    candidates: *mut DLManagedTensor,
    metric: cuvsDistanceType,
    indices: *mut DLManagedTensor,
    distances: *mut DLManagedTensor,
) -> cuvsError_t

@defgroup ann_refine_c Approximate Nearest Neighbors Refinement C-API @{ / /** @brief Refine nearest neighbor search.

Refinement is an operation that follows an approximate NN search. The approximate search has already selected n_candidates neighbor candidates for each query. We narrow it down to k neighbors. For each query, we calculate the exact distance between the query and its n_candidates neighbor candidate, and select the k nearest ones.

@param[in] res cuvsResources_t opaque C handle @param[in] dataset device matrix that stores the dataset [n_rows, dims] @param[in] queries device matrix of the queries [n_queris, dims] @param[in] candidates indices of candidate vectors [n_queries, n_candidates], where n_candidates >= k @param[in] metric distance metric to use. Euclidean (L2) is used by default @param[out] indices device matrix that stores the refined indices [n_queries, k] @param[out] distances device matrix that stores the refined distances [n_queries, k]