Spaces:
Runtime error
Runtime error
File size: 7,473 Bytes
e4f9cbe |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 |
"""Tests for dataset.compute_signal() when signals are chained."""
import re
from typing import Iterable, List, Optional, cast
import numpy as np
import pytest
from pytest_mock import MockerFixture
from typing_extensions import override
from ..embeddings.vector_store import VectorStore
from ..schema import UUID_COLUMN, Field, Item, RichData, VectorKey, field, schema
from ..signals.signal import (
TextEmbeddingModelSignal,
TextEmbeddingSignal,
TextSignal,
TextSplitterSignal,
clear_signal_registry,
register_signal,
)
from .dataset import DatasetManifest
from .dataset_test_utils import (
TEST_DATASET_NAME,
TEST_NAMESPACE,
TestDataMaker,
enriched_embedding_span,
enriched_embedding_span_field,
enriched_item,
)
from .dataset_utils import lilac_embedding, lilac_span
SIMPLE_ITEMS: list[Item] = [{
UUID_COLUMN: '1',
'str': 'a',
'int': 1,
'bool': False,
'float': 3.0
}, {
UUID_COLUMN: '2',
'str': 'b',
'int': 2,
'bool': True,
'float': 2.0
}, {
UUID_COLUMN: '3',
'str': 'b',
'int': 2,
'bool': True,
'float': 1.0
}]
EMBEDDINGS: list[tuple[str, list[float]]] = [('hello.', [1.0, 0.0, 0.0]),
('hello2.', [1.0, 1.0, 0.0]),
('hello world.', [1.0, 1.0, 1.0]),
('hello world2.', [2.0, 1.0, 1.0])]
STR_EMBEDDINGS: dict[str, list[float]] = {text: embedding for text, embedding in EMBEDDINGS}
class TestSplitter(TextSplitterSignal):
"""Split documents into sentence by splitting on period."""
name = 'test_splitter'
@override
def compute(self, data: Iterable[RichData]) -> Iterable[Item]:
for text in data:
if not isinstance(text, str):
raise ValueError(f'Expected text to be a string, got {type(text)} instead.')
sentences = [f'{sentence.strip()}.' for sentence in text.split('.') if sentence]
yield [
lilac_span(text.index(sentence),
text.index(sentence) + len(sentence)) for sentence in sentences
]
class TestEmbedding(TextEmbeddingSignal):
"""A test embed function."""
name = 'test_embedding'
@override
def compute(self, data: Iterable[RichData]) -> Iterable[Item]:
"""Call the embedding function."""
for example in data:
yield [lilac_embedding(0, len(example), np.array(STR_EMBEDDINGS[cast(str, example)]))]
class TestEmbeddingSumSignal(TextEmbeddingModelSignal):
"""Sums the embeddings to return a single floating point value."""
name = 'test_embedding_sum'
@override
def fields(self) -> Field:
return field('float32')
@override
def vector_compute(self, keys: Iterable[VectorKey], vector_store: VectorStore) -> Iterable[Item]:
# The signal just sums the values of the embedding.
embedding_sums = vector_store.get(keys).sum(axis=1)
for embedding_sum in embedding_sums.tolist():
yield embedding_sum
@pytest.fixture(scope='module', autouse=True)
def setup_teardown() -> Iterable[None]:
# Setup.
register_signal(TestSplitter)
register_signal(TestEmbedding)
register_signal(TestEmbeddingSumSignal)
register_signal(NamedEntity)
# Unit test runs.
yield
# Teardown.
clear_signal_registry()
def test_manual_embedding_signal(make_test_data: TestDataMaker, mocker: MockerFixture) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'hello.',
}, {
UUID_COLUMN: '2',
'text': 'hello2.',
}])
embed_mock = mocker.spy(TestEmbedding, 'compute')
embedding_signal = TestEmbedding()
dataset.compute_signal(embedding_signal, 'text')
embedding_sum_signal = TestEmbeddingSumSignal(embedding=TestEmbedding.name)
dataset.compute_signal(embedding_sum_signal, 'text')
# Make sure the embedding signal is not called twice.
assert embed_mock.call_count == 1
assert dataset.manifest() == DatasetManifest(
namespace=TEST_NAMESPACE,
dataset_name=TEST_DATASET_NAME,
data_schema=schema({
UUID_COLUMN: 'string',
'text': field(
'string',
fields={
'test_embedding': field(
signal=embedding_signal.dict(),
fields=[
enriched_embedding_span_field(
{'test_embedding_sum': field('float32', embedding_sum_signal.dict())})
])
}),
}),
num_items=2)
result = dataset.select_rows()
expected_result = [{
UUID_COLUMN: '1',
'text': enriched_item(
'hello.', {'test_embedding': [enriched_embedding_span(0, 6, {'test_embedding_sum': 1.0})]})
}, {
UUID_COLUMN: '2',
'text': enriched_item(
'hello2.', {'test_embedding': [enriched_embedding_span(0, 7, {'test_embedding_sum': 2.0})]})
}]
assert list(result) == expected_result
def test_auto_embedding_signal(make_test_data: TestDataMaker, mocker: MockerFixture) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'hello.',
}, {
UUID_COLUMN: '2',
'text': 'hello2.',
}])
embed_mock = mocker.spy(TestEmbedding, 'compute')
# The embedding is automatically computed from the TestEmbeddingSumSignal.
embedding_sum_signal = TestEmbeddingSumSignal(embedding=TestEmbedding.name)
dataset.compute_signal(embedding_sum_signal, 'text')
# Make sure the embedding signal is not called twice.
assert embed_mock.call_count == 1
assert dataset.manifest() == DatasetManifest(
namespace=TEST_NAMESPACE,
dataset_name=TEST_DATASET_NAME,
data_schema=schema({
UUID_COLUMN: 'string',
'text': field(
'string',
fields={
'test_embedding': field(
signal=embedding_sum_signal._embedding_signal.dict(),
fields=[
enriched_embedding_span_field(
{'test_embedding_sum': field('float32', embedding_sum_signal.dict())})
])
}),
}),
num_items=2)
result = dataset.select_rows()
expected_result = [{
UUID_COLUMN: '1',
'text': enriched_item(
'hello.', {'test_embedding': [enriched_embedding_span(0, 6, {'test_embedding_sum': 1.0})]})
}, {
UUID_COLUMN: '2',
'text': enriched_item(
'hello2.', {'test_embedding': [enriched_embedding_span(0, 7, {'test_embedding_sum': 2.0})]})
}]
assert list(result) == expected_result
ENTITY_REGEX = r'[A-Za-z]+@[A-Za-z]+'
class NamedEntity(TextSignal):
"""Find special entities."""
name = 'entity'
@override
def fields(self) -> Field:
return field(fields=['string_span'])
@override
def compute(self, data: Iterable[RichData]) -> Iterable[Optional[List[Item]]]:
for text in data:
if not isinstance(text, str):
yield None
continue
yield [lilac_span(m.start(0), m.end(0)) for m in re.finditer(ENTITY_REGEX, text)]
def test_entity_on_split_signal(make_test_data: TestDataMaker) -> None:
text = 'Hello nik@test. Here are some other entities like pii@gmail and all@lilac.'
dataset = make_test_data([{UUID_COLUMN: '1', 'text': text}])
entity = NamedEntity()
dataset.compute_signal(TestSplitter(), 'text')
dataset.compute_signal(entity, ('text', 'test_splitter', '*'))
result = dataset.select_rows(['text'])
assert list(result) == [{
UUID_COLUMN: '1',
'text': enriched_item(
text, {
'test_splitter': [
lilac_span(0, 15, {'entity': [lilac_span(6, 14)]}),
lilac_span(16, 74, {'entity': [
lilac_span(50, 59),
lilac_span(64, 73),
]}),
]
})
}]
|