from sentence_transformers import CrossEncoder

pairs = [
    (
        "How do I reset a user password?",
        "Use the account settings page to send a password reset link.",
    ),
    (
        "How do I reset a user password?",
        "Rotate the signing key before deploying a new release.",
    ),
    (
        "Which document explains database backups?",
        "Create a snapshot, copy it to archive storage, and record the restore point.",
    ),
]

model = CrossEncoder("cross-encoder/ms-marco-MiniLM-L6-v2", device="cpu")
scores = model.predict(pairs, show_progress_bar=False)

ranked_pairs = sorted(
    zip(scores, pairs),
    key=lambda item: float(item[0]),
    reverse=True,
)

for rank, (score, (query, passage)) in enumerate(ranked_pairs, start=1):
    print(f"{rank}. score={float(score):.2f}")
    print(f"   query: {query}")
    print(f"   passage: {passage}")

if float(scores[0]) <= float(scores[1]):
    raise SystemExit("password reset pair did not score above unrelated release text")

if float(scores[2]) <= float(scores[1]):
    raise SystemExit("backup pair did not score above unrelated release text")

print("check: relevant pairs scored above the unrelated pair")