Tiered Index

1
cdef class Index

1
def trained(self)

1
cdef class IndexParams

1
def __init__(self, *, metric="sqeuclidean", algo="cagra", upstream_params=None, min_ann_rows=None, create_ann_index_on_extend=None,)

1
def metric(self)

1
def algo(self)

1
def min_ann_rows(self)

1
def create_ann_index_on_extend(self)

1
def upstream_params(self)

1
def build(IndexParams index_params, dataset, resources=None)

1
>>> import cupy as cp
2
>>> from cuvs.neighbors import cagra, tiered_index
3
>>> n_samples = 50000
4
>>> n_features = 50
5
>>> n_queries = 1000
6
>>> k = 10
7
>>> dataset = cp.random.random_sample((n_samples, n_features),
8
...                                   dtype=cp.float32)
9
>>> build_params = tiered_index.IndexParams(metric="sqeuclidean",
10
...                                         algo="cagra")
11
>>> index = tiered_index.build(build_params, dataset)
12
>>> distances, neighbors = tiered_index.search(cagra.SearchParams(),
13
...                                            index, dataset, k)
14
>>> distances = cp.asarray(distances)
15
>>> neighbors = cp.asarray(neighbors)

1
def extend(Index index, new_vectors, resources=None)

1
>>> import cupy as cp
2
>>> from cuvs.neighbors import tiered_index
3
>>> n_samples = 50000
4
>>> n_features = 50
5
>>> n_queries = 1000
6
>>> dataset = cp.random.random_sample((n_samples, n_features),
7
...                                   dtype=cp.float32)
8
>>> index = tiered_index.build(tiered_index.IndexParams(), dataset)
9
>>> n_rows = 100
10
>>> more_data = cp.random.random_sample((n_rows, n_features),
11
...                                     dtype=cp.float32)
12
>>> index = tiered_index.extend(index, more_data)

1
def search(search_params, Index index, queries, k, neighbors=None, distances=None, resources=None, filter=None)

1
>>> import cupy as cp
2
>>> from cuvs.neighbors import cagra, tiered_index
3
>>> n_samples = 50000
4
>>> n_features = 50
5
>>> n_queries = 1000
6
>>> dataset = cp.random.random_sample((n_samples, n_features),
7
...                                   dtype=cp.float32)
8
>>> # Build the index
9
>>> index = tiered_index.build(tiered_index.IndexParams(algo="cagra"),
10
...                            dataset)
11
>>>
12
>>> # Search using the built index
13
>>> queries = cp.random.random_sample((n_queries, n_features),
14
...                                   dtype=cp.float32)
15
>>> k = 10
16
>>> search_params = cagra.SearchParams()
17
>>>
18
>>> distances, neighbors = tiered_index.search(search_params, index,
19
...                                            queries, k)