1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
|
import hnswlib
import numpy as np
import pickle
"""
Example of search
"""
dim = 128
num_elements = 10000
# Generating sample data
data = np.float32(np.random.random((num_elements, dim)))
ids = np.arange(num_elements)
# Declaring index
p = hnswlib.Index(space='l2', dim=dim) # possible options are l2, cosine or ip
# Initializing index - the maximum number of elements should be known beforehand
p.init_index(max_elements=num_elements, ef_construction=200, M=16)
# Element insertion (can be called several times):
p.add_items(data, ids)
# Controlling the recall by setting ef:
p.set_ef(50) # ef should always be > k
# Query dataset, k - number of the closest elements (returns 2 numpy arrays)
labels, distances = p.knn_query(data, k=1)
# Index objects support pickling
# WARNING: serialization via pickle.dumps(p) or p.__getstate__() is NOT thread-safe with p.add_items method!
# Note: ef parameter is included in serialization; random number generator is initialized with random_seed on Index load
p_copy = pickle.loads(pickle.dumps(p)) # creates a copy of index p using pickle round-trip
### Index parameters are exposed as class properties:
print(f"Parameters passed to constructor: space={p_copy.space}, dim={p_copy.dim}")
print(f"Index construction: M={p_copy.M}, ef_construction={p_copy.ef_construction}")
print(f"Index size is {p_copy.element_count} and index capacity is {p_copy.max_elements}")
print(f"Search speed/quality trade-off parameter: ef={p_copy.ef}")
|
