from sentence_transformers import SentenceTransformer, util


sentences = [
    "Reset a customer password from the account portal.",
    "Reset a user password in the account portal.",
    "Deploy the billing service to production.",
    "Release the billing service to production.",
    "Archive the weekly database backup.",
    "Bake sourdough bread after the dough rises.",
]

model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2", device="cpu")
pairs = util.paraphrase_mining(
    model,
    sentences,
    show_progress_bar=False,
    batch_size=16,
    top_k=3,
    max_pairs=8,
)

print("Top paraphrase pairs:")
for rank, (score, first_id, second_id) in enumerate(pairs[:5], start=1):
    print(f"{rank}. score={score:.4f}")
    print(f"   {first_id}: {sentences[first_id]}")
    print(f"   {second_id}: {sentences[second_id]}")

expected_pair = frozenset({0, 1})
top_pairs = {frozenset({first_id, second_id}) for _, first_id, second_id in pairs[:3]}

if expected_pair not in top_pairs:
    raise SystemExit("password reset pair missing from the top paraphrase results")

print("verification: PASS password reset duplicate pair found")