Make the first RAG slice executable without risking production data
Some checks failed
verify / verify (push) Has been cancelled
Some checks failed
verify / verify (push) Has been cancelled
The Stage 1 foundation now proves provider contracts with mocks and validates PostgreSQL/pgvector ingestion, approval binding, retrieval, reranking, and idempotency using only synthetic data. Live Bailian validation remains gated on rotating the exposed key. Constraint: The key shown in chat is compromised and cannot be used or committed Rejected: Mark Stage 1 complete from mock and offline results | real three-model smoke is still required Confidence: high Scope-risk: moderate Reversibility: clean Directive: Do not enable real-data ingestion until Stage 3 cloud approval and outbound manifest controls are enforced end to end Tested: make verify; 41 pytest tests; strict mypy; Ruff; Compose config; pinned image build; empty-volume migration; role denial; two idempotent 20-vector seeds; database restart persistence Not-tested: Live Bailian calls require a newly rotated key; React product UI is not implemented
This commit is contained in:
47
backend/tests/unit/test_fake_models.py
Normal file
47
backend/tests/unit/test_fake_models.py
Normal file
@@ -0,0 +1,47 @@
|
||||
import math
|
||||
|
||||
import pytest
|
||||
|
||||
from app.adapters.fake import FakeEmbeddingProvider, FakeReranker
|
||||
from app.ports.model_providers import ModelProviderError
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_fake_embedding_is_deterministic_normalized_and_1024_dimensional() -> None:
|
||||
provider = FakeEmbeddingProvider()
|
||||
|
||||
first = await provider.embed_documents(["斑岩铜矿 钾化 绢英岩化"])
|
||||
second = await provider.embed_query("斑岩铜矿 钾化 绢英岩化")
|
||||
|
||||
assert first.vectors[0] == second.vectors[0]
|
||||
assert len(first.vectors[0]) == 1024
|
||||
assert math.isclose(sum(value * value for value in first.vectors[0]), 1.0)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_fake_reranker_preserves_original_candidate_index() -> None:
|
||||
reranker = FakeReranker()
|
||||
documents = ["煤层测井对比", "斑岩铜矿钾化带", "铝土矿含矿层"]
|
||||
|
||||
result = await reranker.rerank("斑岩铜矿的钾化带", documents, top_n=2)
|
||||
|
||||
assert result.items[0].index == 1
|
||||
assert result.items[0].document == documents[1]
|
||||
assert result.items[0].relevance_score >= result.items[1].relevance_score
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_fake_providers_reject_inputs_the_live_contract_rejects() -> None:
|
||||
embedder = FakeEmbeddingProvider()
|
||||
reranker = FakeReranker()
|
||||
|
||||
with pytest.raises(ModelProviderError):
|
||||
await embedder.embed_documents([])
|
||||
with pytest.raises(ModelProviderError):
|
||||
await embedder.embed_documents(["x"] * 11)
|
||||
with pytest.raises(ModelProviderError):
|
||||
await reranker.rerank("", ["document"], top_n=1)
|
||||
with pytest.raises(ModelProviderError):
|
||||
await reranker.rerank("query", [], top_n=1)
|
||||
with pytest.raises(ModelProviderError):
|
||||
await reranker.rerank("query", ["document"], top_n=0)
|
||||
Reference in New Issue
Block a user