forked from lancedb/lancedb
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_index.py
More file actions
194 lines (161 loc) · 6.51 KB
/
test_index.py
File metadata and controls
194 lines (161 loc) · 6.51 KB
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
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright The LanceDB Authors
from datetime import timedelta
import random
import pyarrow as pa
import pytest
import pytest_asyncio
from lancedb import AsyncConnection, AsyncTable, connect_async
from lancedb.index import BTree, IvfFlat, IvfPq, Bitmap, LabelList, HnswPq, HnswSq
@pytest_asyncio.fixture
async def db_async(tmp_path) -> AsyncConnection:
return await connect_async(tmp_path, read_consistency_interval=timedelta(seconds=0))
def sample_fixed_size_list_array(nrows, dim):
vector_data = pa.array([float(i) for i in range(dim * nrows)], pa.float32())
return pa.FixedSizeListArray.from_arrays(vector_data, dim)
DIM = 8
NROWS = 256
@pytest_asyncio.fixture
async def some_table(db_async):
data = pa.Table.from_pydict(
{
"id": list(range(NROWS)),
"vector": sample_fixed_size_list_array(NROWS, DIM),
"tags": [
[f"tag{random.randint(0, 8)}" for _ in range(2)] for _ in range(NROWS)
],
}
)
return await db_async.create_table(
"some_table",
data,
)
@pytest_asyncio.fixture
async def binary_table(db_async):
data = [
{
"id": i,
"vector": [i] * 128,
}
for i in range(NROWS)
]
return await db_async.create_table(
"binary_table",
data,
schema=pa.schema(
[
pa.field("id", pa.int64()),
pa.field("vector", pa.list_(pa.uint8(), 128)),
]
),
)
@pytest.mark.asyncio
async def test_create_scalar_index(some_table: AsyncTable):
# Can create
await some_table.create_index("id")
# Can recreate if replace=True
await some_table.create_index("id", replace=True)
indices = await some_table.list_indices()
assert str(indices) == '[Index(BTree, columns=["id"], name="id_idx")]'
assert len(indices) == 1
assert indices[0].index_type == "BTree"
assert indices[0].columns == ["id"]
# Can't recreate if replace=False
with pytest.raises(RuntimeError, match="already exists"):
await some_table.create_index("id", replace=False)
# can also specify index type
await some_table.create_index("id", config=BTree())
await some_table.drop_index("id_idx")
indices = await some_table.list_indices()
assert len(indices) == 0
@pytest.mark.asyncio
async def test_create_bitmap_index(some_table: AsyncTable):
await some_table.create_index("id", config=Bitmap())
indices = await some_table.list_indices()
assert str(indices) == '[Index(Bitmap, columns=["id"], name="id_idx")]'
indices = await some_table.list_indices()
assert len(indices) == 1
index_name = indices[0].name
stats = await some_table.index_stats(index_name)
assert stats.index_type == "BITMAP"
assert stats.distance_type is None
assert stats.num_indexed_rows == await some_table.count_rows()
assert stats.num_unindexed_rows == 0
assert stats.num_indices == 1
@pytest.mark.asyncio
async def test_create_label_list_index(some_table: AsyncTable):
await some_table.create_index("tags", config=LabelList())
indices = await some_table.list_indices()
assert str(indices) == '[Index(LabelList, columns=["tags"], name="tags_idx")]'
@pytest.mark.asyncio
async def test_create_vector_index(some_table: AsyncTable):
# Can create
await some_table.create_index("vector")
# Can recreate if replace=True
await some_table.create_index("vector", replace=True)
# Can't recreate if replace=False
with pytest.raises(RuntimeError, match="already exists"):
await some_table.create_index("vector", replace=False)
# Can also specify index type
await some_table.create_index("vector", config=IvfPq(num_partitions=100))
indices = await some_table.list_indices()
assert len(indices) == 1
assert indices[0].index_type == "IvfPq"
assert indices[0].columns == ["vector"]
assert indices[0].name == "vector_idx"
stats = await some_table.index_stats("vector_idx")
assert stats.index_type == "IVF_PQ"
assert stats.distance_type == "l2"
assert stats.num_indexed_rows == await some_table.count_rows()
assert stats.num_unindexed_rows == 0
assert stats.num_indices == 1
@pytest.mark.asyncio
async def test_create_4bit_ivfpq_index(some_table: AsyncTable):
# Can create
await some_table.create_index("vector", config=IvfPq(num_bits=4))
# Can recreate if replace=True
await some_table.create_index("vector", config=IvfPq(num_bits=4), replace=True)
# Can't recreate if replace=False
with pytest.raises(RuntimeError, match="already exists"):
await some_table.create_index("vector", replace=False)
indices = await some_table.list_indices()
assert len(indices) == 1
assert indices[0].index_type == "IvfPq"
assert indices[0].columns == ["vector"]
assert indices[0].name == "vector_idx"
stats = await some_table.index_stats("vector_idx")
assert stats.index_type == "IVF_PQ"
assert stats.distance_type == "l2"
assert stats.num_indexed_rows == await some_table.count_rows()
assert stats.num_unindexed_rows == 0
assert stats.num_indices == 1
@pytest.mark.asyncio
async def test_create_hnswpq_index(some_table: AsyncTable):
await some_table.create_index("vector", config=HnswPq(num_partitions=10))
indices = await some_table.list_indices()
assert len(indices) == 1
@pytest.mark.asyncio
async def test_create_hnswsq_index(some_table: AsyncTable):
await some_table.create_index("vector", config=HnswSq(num_partitions=10))
indices = await some_table.list_indices()
assert len(indices) == 1
@pytest.mark.asyncio
async def test_create_index_with_binary_vectors(binary_table: AsyncTable):
await binary_table.create_index(
"vector", config=IvfFlat(distance_type="hamming", num_partitions=10)
)
indices = await binary_table.list_indices()
assert len(indices) == 1
assert indices[0].index_type == "IvfFlat"
assert indices[0].columns == ["vector"]
assert indices[0].name == "vector_idx"
stats = await binary_table.index_stats("vector_idx")
assert stats.index_type == "IVF_FLAT"
assert stats.distance_type == "hamming"
assert stats.num_indexed_rows == await binary_table.count_rows()
assert stats.num_unindexed_rows == 0
assert stats.num_indices == 1
# the dataset contains vectors with all values from 0 to 255
for v in range(256):
res = await binary_table.query().nearest_to([v] * 128).to_arrow()
assert res["id"][0].as_py() == v