Getting the best match from a set of embeddings including the query itself

get_best_match.py

import numpy as np
from sklearn.preprocessing import normalize

# Use the first question as the query
QUERY_ID = 0

# Noralize the data
norm_data = normalize(sentence_embeddings, norm='l2')

# Calculate scores as dot product between all embedding & query
scores = np.dot(norm_data, norm_data[QUERY_ID].T)

# The best match is the entry with the second highest score (the highest is the query itself)
MATCH_ID = np.argsort(scores)[-2]