110 lines
3.4 KiB
Python
110 lines
3.4 KiB
Python
"""Unit tests for query embedding and provider-neutral Dense Top-N retrieval."""
|
|
|
|
from math import nan
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
|
|
from ekp_core.dense_retrieval import (
|
|
DenseRetrievalContractError,
|
|
DenseRetrievalService,
|
|
InvalidRetrievalQueryError,
|
|
)
|
|
from ekp_domain import IndexProfile
|
|
from ekp_embedding import FakeEmbeddingProvider
|
|
from ekp_vector_store import DenseSearchRequest, FakeVectorStore, VectorRecord
|
|
|
|
|
|
def _record(
|
|
*,
|
|
vector: tuple[float, ...],
|
|
profile_id: str = "profile-v1",
|
|
filename: str = "policy.md",
|
|
) -> VectorRecord:
|
|
"""Build a minimal traceable vector row for exact-search assertions."""
|
|
return VectorRecord(
|
|
index_record_id=uuid4(),
|
|
chunk_id=uuid4(),
|
|
document_id=uuid4(),
|
|
filename=filename,
|
|
page=1,
|
|
page_end=1,
|
|
section="制度",
|
|
chunk_index=0,
|
|
content="测试内容",
|
|
embedding=vector,
|
|
embedding_model="fake",
|
|
index_profile_id=profile_id,
|
|
)
|
|
|
|
|
|
def test_fake_vector_store_filters_profile_before_cosine_top_n() -> None:
|
|
store = FakeVectorStore()
|
|
closest = _record(vector=(1.0, 0.0), filename="closest.md")
|
|
farther = _record(vector=(0.5, 0.5), filename="farther.md")
|
|
shadow = _record(vector=(1.0, 0.0), profile_id="shadow-v2", filename="shadow.md")
|
|
store.upsert((farther, shadow, closest))
|
|
|
|
candidates = store.dense_search(DenseSearchRequest((1.0, 0.0), "profile-v1", 2))
|
|
|
|
assert [candidate.filename for candidate in candidates] == ["closest.md", "farther.md"]
|
|
assert all(candidate.index_profile_id == "profile-v1" for candidate in candidates)
|
|
assert candidates[0].score == pytest.approx(1.0)
|
|
|
|
|
|
def test_dense_service_uses_default_top_twenty_and_trims_query() -> None:
|
|
embedding = FakeEmbeddingProvider(model_name="fake", dimensions=8)
|
|
store = FakeVectorStore()
|
|
service = DenseRetrievalService(
|
|
embedding,
|
|
store,
|
|
IndexProfile("profile-v1", "structure_v1", "fake", 8),
|
|
)
|
|
|
|
result = service.search(" 住宿标准 ")
|
|
|
|
assert result.query == "住宿标准"
|
|
assert result.index_profile_id == "profile-v1"
|
|
assert result.candidates == ()
|
|
assert store.dense_search_calls == 1
|
|
assert store.search_requests[0].top_n == 20
|
|
assert store.search_requests[0].index_profile_id == "profile-v1"
|
|
|
|
|
|
def test_dense_service_rejects_empty_query() -> None:
|
|
service = DenseRetrievalService(
|
|
FakeEmbeddingProvider(model_name="fake", dimensions=8),
|
|
FakeVectorStore(),
|
|
IndexProfile("profile-v1", "structure_v1", "fake", 8),
|
|
)
|
|
|
|
with pytest.raises(InvalidRetrievalQueryError):
|
|
service.search(" ")
|
|
|
|
|
|
class InvalidEmbeddingProvider:
|
|
"""Protocol-compatible provider returning a deliberately invalid vector."""
|
|
|
|
model_name = "fake"
|
|
dimensions = 2
|
|
max_batch_size = 1
|
|
|
|
def embed(self, texts: object) -> tuple[tuple[float, ...], ...]:
|
|
return ((nan, 0.0),)
|
|
|
|
|
|
def test_dense_service_rejects_non_finite_query_embedding() -> None:
|
|
service = DenseRetrievalService(
|
|
InvalidEmbeddingProvider(),
|
|
FakeVectorStore(),
|
|
IndexProfile("profile-v1", "structure_v1", "fake", 2),
|
|
)
|
|
|
|
with pytest.raises(DenseRetrievalContractError, match="non-finite"):
|
|
service.search("退款")
|
|
|
|
|
|
def test_dense_search_request_rejects_invalid_top_n() -> None:
|
|
with pytest.raises(ValueError, match="top_n"):
|
|
DenseSearchRequest((1.0, 0.0), "profile-v1", 0)
|