import numpy as np

def most_similar(query_word, vocab, embeddings, top_n=3):
    # Get vector for the query word
    if query_word not in vocab:
        raise ValueError('Query word not in vocabulary!')
    query_vec = embeddings[vocab.index(query_word)]
    # Normalize query vector
    query_vec = query_vec / np.linalg.norm(query_vec)
    similarities = []
    for word, vec in zip(vocab, embeddings):
        # Normalize each embedding
        vec_norm = vec / np.linalg.norm(vec)
        # Cosine similarity (since normalized)
        sim = np.dot(query_vec, vec_norm)
        similarities.append((word, sim))
    # Sort by similarity, descending, skip the query word itself
    similarities = sorted(similarities, key=lambda x: x[1], reverse=True)
    return [w for w, s in similarities if w != query_word][:top_n]

# Example usage:
vocab = ['cat', 'dog', 'car', 'apple']
embeddings = np.array([
    [1, 2],      # cat
    [0.9, 2.1],  # dog
    [-2, 0.5],   # car
    [0.2, -1],   # apple
])

print(most_similar('cat', vocab, embeddings, top_n=2))
# Output: ['dog', 'car']