app.py

import faiss
import numpy as np

# Load FAISS index
FAISS_PATH = "asa_faiss.index"
index = faiss.read_index(FAISS_PATH)

# Example query vector (random, replace with actual embedding from your model)
query_vector = np.random.rand(1, index.d).astype('float32')

# Search FAISS index
D, I = index.search(query_vector, k=1)  # k=1 means get 1 nearest neighbor

print(f"Closest match index: {I[0][0]}, Distance: {D[0][0]}")