semantic.py

# Install: !pip install sentence_transformers
from sentence_transformers import SentenceTransformer
model = SentenceTransformer('distilbert-base-nli-mean-tokens')

# sentences = [doc_set[9234], doc_set[9239], doc_set[1131966]]
sentence_embeddings = model.encode(sentences)

# Calculate cosine distance of the embeddings
from scipy.spatial import distance
print(1 - distance.cosine(sentence_embeddings[0], sentence_embeddings[1]))
print(1 - distance.cosine(sentence_embeddings[0], sentence_embeddings[2]))
print(1 - distance.cosine(sentence_embeddings[1], sentence_embeddings[2]))
sentences