from gensim.models import Word2Vec

# Small demo corpus
sentences = [
    ["the", "quick", "brown", "fox", "jumps"],
    ["the", "lazy", "dog", "sleeps"],
    ["the", "fox", "outsmarts", "the", "dog"],
]

# Train a skip-gram Word2Vec model
model = Word2Vec(
    sentences,       # list of tokenized sentences
    vector_size=50,  # embedding dimensions
    window=2,        # context window size
    min_count=1,     # include all words
    sg=1,            # 1 for skip-gram; 0 for CBOW
)

# Find most similar words to “fox”
similar_words = model.wv.most_similar("fox", topn=3)
for word, score in similar_words:
    print(word, score)