The distance between feature vectors (word vectors, topic vectors, document context vectors, etc.) drives the performance of the NLP pipeline or any machine learning pipeline.
Pairwise distances available in sklearn:
'cityblock', 'cosine', 'euclidean', 'l1', 'l2', 'manhattan', 'braycurtis',
'canberra', 'chebyshev', 'correlation', 'dice', 'hamming', 'jaccard',
'kulsinski', 'mahalanobis', 'matching', 'minkowski', 'rogerstanimoto',
'russellrao', 'seuclidean', 'sokalmichener', 'sokalsneath', 'sqeuclidean',
'yule'