Spaces:
Runtime error
Runtime error
File size: 11,771 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 |
"""Tests for dataset.select_rows(udf_col)."""
from typing import Iterable, Optional, cast
import numpy as np
import pytest
from typing_extensions import override
from ..embeddings.vector_store import VectorStore
from ..schema import UUID_COLUMN, VALUE_KEY, Field, Item, RichData, VectorKey, field
from ..signals.signal import (
TextEmbeddingModelSignal,
TextEmbeddingSignal,
TextSignal,
TextSplitterSignal,
clear_signal_registry,
register_signal,
)
from .dataset import BinaryFilterTuple, BinaryOp, Column, val
from .dataset_test_utils import TestDataMaker, enriched_item
from .dataset_utils import lilac_embedding, lilac_span
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 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 LengthSignal(TextSignal):
name = 'length_signal'
_call_count: int = 0
def fields(self) -> Field:
return field('int32')
def compute(self, data: Iterable[RichData]) -> Iterable[Optional[Item]]:
for text_content in data:
self._call_count += 1
yield len(text_content)
class TestSignal(TextSignal):
name = 'test_signal'
@override
def fields(self) -> Field:
return field(fields={'len': 'int32', 'flen': 'float32'})
@override
def compute(self, data: Iterable[RichData]) -> Iterable[Optional[Item]]:
return [{'len': len(text_content), 'flen': float(len(text_content))} for text_content in data]
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
class ComputedKeySignal(TextSignal):
name = 'computed_key'
@override
def fields(self) -> Field:
return field('int64')
@override
def compute(self, data: Iterable[RichData]) -> Iterable[Optional[Item]]:
for text in data:
yield 1
def key(self, is_computed_signal: Optional[bool] = False) -> str:
return f'key_{is_computed_signal}'
@pytest.fixture(scope='module', autouse=True)
def setup_teardown() -> Iterable[None]:
# Setup.
register_signal(LengthSignal)
register_signal(TestSplitter)
register_signal(TestEmbedding)
register_signal(TestSignal)
register_signal(TestEmbeddingSumSignal)
register_signal(ComputedKeySignal)
# Unit test runs.
yield
# Teardown.
clear_signal_registry()
def test_udf(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'hello'
}, {
UUID_COLUMN: '2',
'text': 'everybody'
}])
signal_col = Column('text', signal_udf=TestSignal())
result = dataset.select_rows(['text', signal_col])
assert list(result) == [{
UUID_COLUMN: '1',
'text': 'hello',
'test_signal(text)': {
'len': 5,
'flen': 5.0
}
}, {
UUID_COLUMN: '2',
'text': 'everybody',
'test_signal(text)': {
'len': 9,
'flen': 9.0
}
}]
def test_udf_with_filters(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'hello'
}, {
UUID_COLUMN: '2',
'text': 'everybody'
}])
signal_col = Column('text', signal_udf=TestSignal())
# Filter by source feature.
filters: list[BinaryFilterTuple] = [('text', BinaryOp.EQUALS, 'everybody')]
result = dataset.select_rows(['text', signal_col], filters=filters)
assert list(result) == [{
UUID_COLUMN: '2',
'text': 'everybody',
'test_signal(text)': {
'len': 9,
'flen': 9.0
}
}]
def test_udf_with_uuid_filter(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'hello'
}, {
UUID_COLUMN: '2',
'text': 'everybody'
}])
# Filter by a specific UUID.
filters: list[BinaryFilterTuple] = [(UUID_COLUMN, BinaryOp.EQUALS, '1')]
udf_col = Column('text', signal_udf=LengthSignal())
result = dataset.select_rows(['text', udf_col], filters=filters)
assert list(result) == [{UUID_COLUMN: '1', 'text': 'hello', 'length_signal(text)': 5}]
assert cast(LengthSignal, udf_col.signal_udf)._call_count == 1
filters = [(UUID_COLUMN, BinaryOp.EQUALS, '2')]
result = dataset.select_rows(['text', udf_col], filters=filters)
assert list(result) == [{UUID_COLUMN: '2', 'text': 'everybody', 'length_signal(text)': 9}]
assert cast(LengthSignal, udf_col.signal_udf)._call_count == 1 + 1
# No filters.
result = dataset.select_rows(['text', udf_col])
assert list(result) == [{
UUID_COLUMN: '1',
'text': 'hello',
'length_signal(text)': 5
}, {
UUID_COLUMN: '2',
'text': 'everybody',
'length_signal(text)': 9
}]
assert cast(LengthSignal, udf_col.signal_udf)._call_count == 2 + 2
def test_udf_with_uuid_filter_repeated(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': ['hello', 'hi']
}, {
UUID_COLUMN: '2',
'text': ['everybody', 'bye', 'test']
}])
# Filter by a specific UUID.
filters: list[BinaryFilterTuple] = [(UUID_COLUMN, BinaryOp.EQUALS, '1')]
udf_col = Column(('text', '*'), signal_udf=LengthSignal())
result = dataset.select_rows(['text', udf_col], filters=filters)
assert list(result) == [{
UUID_COLUMN: '1',
'text': ['hello', 'hi'],
'length_signal(text)': [5, 2]
}]
assert cast(LengthSignal, udf_col.signal_udf)._call_count == 2
# Filter by a specific UUID.
filters = [(UUID_COLUMN, BinaryOp.EQUALS, '2')]
result = dataset.select_rows(['text', udf_col], filters=filters)
assert list(result) == [{
UUID_COLUMN: '2',
'text': ['everybody', 'bye', 'test'],
'length_signal(text)': [9, 3, 4]
}]
assert cast(LengthSignal, udf_col.signal_udf)._call_count == 2 + 3
def test_udf_deeply_nested(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': [['hello'], ['hi', 'bye']]
}, {
UUID_COLUMN: '2',
'text': [['everybody', 'bye'], ['test']]
}])
udf_col = Column(('text', '*', '*'), signal_udf=LengthSignal())
result = dataset.select_rows([udf_col])
assert list(result) == [{
UUID_COLUMN: '1',
'length_signal(text.*)': [[5], [2, 3]]
}, {
UUID_COLUMN: '2',
'length_signal(text.*)': [[9, 3], [4]]
}]
assert cast(LengthSignal, udf_col.signal_udf)._call_count == 6
def test_udf_with_embedding(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'hello.',
}, {
UUID_COLUMN: '2',
'text': 'hello2.',
}])
dataset.compute_signal(TestEmbedding(), 'text')
signal_col = Column('text', signal_udf=TestEmbeddingSumSignal(embedding='test_embedding'))
result = dataset.select_rows([val('text'), signal_col])
expected_result: list[Item] = [{
UUID_COLUMN: '1',
f'text.{VALUE_KEY}': 'hello.',
'test_embedding_sum(text.test_embedding.*.embedding)': [1.0]
}, {
UUID_COLUMN: '2',
f'text.{VALUE_KEY}': 'hello2.',
'test_embedding_sum(text.test_embedding.*.embedding)': [2.0]
}]
assert list(result) == expected_result
# Select rows with alias.
signal_col = Column(
'text', signal_udf=TestEmbeddingSumSignal(embedding='test_embedding'), alias='emb_sum')
result = dataset.select_rows([val('text'), signal_col])
expected_result = [{
UUID_COLUMN: '1',
f'text.{VALUE_KEY}': 'hello.',
'emb_sum': [1.0]
}, {
UUID_COLUMN: '2',
f'text.{VALUE_KEY}': 'hello2.',
'emb_sum': [2.0]
}]
assert list(result) == expected_result
def test_udf_with_nested_embedding(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': ['hello.', 'hello world.'],
}, {
UUID_COLUMN: '2',
'text': ['hello world2.', 'hello2.'],
}])
dataset.compute_signal(TestEmbedding(), ('text', '*'))
signal_col = Column(('text', '*'), signal_udf=TestEmbeddingSumSignal(embedding='test_embedding'))
result = dataset.select_rows([val(('text', '*')), signal_col])
expected_result = [{
UUID_COLUMN: '1',
f'text.*.{VALUE_KEY}': ['hello.', 'hello world.'],
'test_embedding_sum(text.*.test_embedding.*.embedding)': [[1.0], [3.0]]
}, {
UUID_COLUMN: '2',
f'text.*.{VALUE_KEY}': ['hello world2.', 'hello2.'],
'test_embedding_sum(text.*.test_embedding.*.embedding)': [[4.0], [2.0]]
}]
assert list(result) == expected_result
def test_udf_throws_without_precomputing(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'hello.',
}, {
UUID_COLUMN: '2',
'text': 'hello2.',
}])
# Embedding is not precomputed, yet we ask for the embedding.
signal_col = Column('text', signal_udf=TestEmbeddingSumSignal(embedding='test_embedding'))
with pytest.raises(ValueError, match='Embedding signal "test_embedding" is not computed'):
dataset.select_rows([val('text'), signal_col])
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.')
result: list[Item] = []
for sentence in text.split('.'):
start = text.index(sentence)
end = start + len(sentence)
result.append(lilac_span(start, end))
yield result
def test_udf_after_precomputed_split(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'sentence 1. sentence 2 is longer',
}, {
UUID_COLUMN: '2',
'text': 'sentence 1 is longer. sent2 is short',
}])
dataset.compute_signal(TestSplitter(), 'text')
udf = Column('text', signal_udf=LengthSignal())
result = dataset.select_rows(['*', udf], combine_columns=True)
assert list(result) == [{
UUID_COLUMN: '1',
'text': enriched_item('sentence 1. sentence 2 is longer', {
'length_signal': 32,
'test_splitter': [lilac_span(0, 10), lilac_span(11, 32)]
})
}, {
UUID_COLUMN: '2',
'text': enriched_item('sentence 1 is longer. sent2 is short', {
'length_signal': 36,
'test_splitter': [lilac_span(0, 20), lilac_span(21, 36)]
})
}]
def test_is_computed_signal_key(make_test_data: TestDataMaker) -> None:
dataset = make_test_data([{
UUID_COLUMN: '1',
'text': 'hello.',
}, {
UUID_COLUMN: '2',
'text': 'hello2.',
}])
signal_col = Column('text', signal_udf=ComputedKeySignal())
# Filter by source feature.
filters: list[BinaryFilterTuple] = [('text', BinaryOp.EQUALS, 'everybody')]
result = dataset.select_rows(['text', signal_col])
assert list(result) == [{
UUID_COLUMN: '1',
'text': 'hello.',
'key_False(text)': 1
}, {
UUID_COLUMN: '2',
'text': 'hello2.',
'key_False(text)': 1
}]
|