YoVinchen
75592af33a
Some checks failed
verify / verify (push) Has been cancelled
The API and ingestion tools now use a fixed internal model gateway while governed profiles, embedding cache assignments, traceable citations, and stable API errors establish the boundaries required by later workflows. Constraint: The current Alibaba Cloud workspace rejects all three live model calls with authentication failures Rejected: Give the API or seed tools the Bailian key and direct egress | combines database access, cloud credentials, and public network access Rejected: Mix offline and Bailian vectors in one demo namespace | makes profile activation and retrieval ambiguous Confidence: high Scope-risk: moderate Reversibility: clean Directive: Keep Bailian credentials and egress exclusive to model-gateway and create a new immutable profile hash for any embedding identity change Tested: make verify; 121 backend tests; 14 frontend tests; fresh and populated Alembic upgrade-downgrade-upgrade; two idempotent offline seeds; Docker health and HTTP retrieval; isolated provider smoke Not-tested: Successful live Bailian responses because the supplied workspace credential currently fails authentication
96 lines
3.2 KiB
Python
96 lines
3.2 KiB
Python
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from app.adapters.fake import FakeEmbeddingProvider
|
|
from app.core.config import Settings
|
|
from app.tools.seed_demo import (
|
|
BAILIAN_NAMESPACE,
|
|
OFFLINE_NAMESPACE,
|
|
embed_in_batches,
|
|
embedding_profile_hash,
|
|
load_documents,
|
|
namespace_for_mode,
|
|
prepare_chunks,
|
|
)
|
|
|
|
PROJECT_ROOT = Path(__file__).resolve().parents[3]
|
|
DOCUMENTS_PATH = PROJECT_ROOT / "data" / "samples" / "public" / "demo_documents.jsonl"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_seed_preparation_batches_and_hash_binds_twenty_documents() -> None:
|
|
documents = load_documents(DOCUMENTS_PATH)
|
|
settings = Settings()
|
|
provider = FakeEmbeddingProvider()
|
|
texts = [
|
|
f"标题：{item.title}\n地区：{item.region}\n矿种：{item.mineral}\n正文：{item.content}"
|
|
for item in documents
|
|
]
|
|
|
|
vectors, model = await embed_in_batches(provider, texts)
|
|
chunks = prepare_chunks(
|
|
documents,
|
|
vectors,
|
|
profile_hash=embedding_profile_hash(settings, "fake"),
|
|
embedding_model=model,
|
|
)
|
|
|
|
assert len(chunks) == 20
|
|
assert all(len(item.vector) == 1024 for item in chunks)
|
|
assert all(item.embedding_text == item.embedding_prefix + item.cloud_text for item in chunks)
|
|
assert len({item.chunk_id for item in chunks}) == 20
|
|
assert all(len(item.outbound_manifest_sha256) == 64 for item in chunks)
|
|
assert all(item.embedding_elapsed_ms >= 0 for item in chunks)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_live_and_offline_seed_namespaces_cannot_share_document_identity() -> None:
|
|
documents = load_documents(DOCUMENTS_PATH)
|
|
settings = Settings()
|
|
vectors, model = await embed_in_batches(
|
|
FakeEmbeddingProvider(),
|
|
[f"标题：{item.title}\n正文：{item.content}" for item in documents],
|
|
)
|
|
profile_hash = embedding_profile_hash(settings, "fake")
|
|
|
|
offline = prepare_chunks(
|
|
documents,
|
|
vectors,
|
|
profile_hash=profile_hash,
|
|
embedding_model=model,
|
|
namespace=OFFLINE_NAMESPACE,
|
|
)
|
|
live = prepare_chunks(
|
|
documents,
|
|
vectors,
|
|
profile_hash=profile_hash,
|
|
embedding_model=model,
|
|
namespace=BAILIAN_NAMESPACE,
|
|
)
|
|
|
|
assert OFFLINE_NAMESPACE.knowledge_base_id != BAILIAN_NAMESPACE.knowledge_base_id
|
|
assert OFFLINE_NAMESPACE.access_scope_id != BAILIAN_NAMESPACE.access_scope_id
|
|
assert {item.document_id for item in offline}.isdisjoint({item.document_id for item in live})
|
|
assert namespace_for_mode("fake") is OFFLINE_NAMESPACE
|
|
assert namespace_for_mode("bailian") is BAILIAN_NAMESPACE
|
|
|
|
|
|
def test_seed_rejects_unknown_provider_namespace() -> None:
|
|
with pytest.raises(ValueError, match="invalid_provider_mode"):
|
|
namespace_for_mode("unknown")
|
|
|
|
|
|
def test_seed_rejects_fixture_not_explicitly_marked_synthetic(tmp_path: Path) -> None:
|
|
path = tmp_path / "documents.jsonl"
|
|
path.write_text(
|
|
'{"doc_id":"x","title":"x","content":"x","region":"x",'
|
|
'"mineral":"x","page_no":1,"source_type":"unknown",'
|
|
'"review_state":"LOCAL_PARSED_PENDING_CLOUD_REVIEW",'
|
|
'"cloud_policy_id":"synthetic-demo-v1"}\n',
|
|
encoding="utf-8",
|
|
)
|
|
|
|
with pytest.raises(ValueError, match="non_synthetic_document"):
|
|
load_documents(path)
|