.
#pip install -U sentence-transformers
#https://github.com/UKPLab/sentence-transformers
from sentence_transformers import SentenceTransformer, LoggingHandler
# Load Sentence model (based on BERT) from URL
model = SentenceTransformer('bert-base-nli-mean-tokens')
# Embed a list of sentences
sentences = ['This framework generates embeddings for each input sentence',
'Sentences are passed as a list of string.',
'The quick brown fox jumps over the lazy dog.']
sentence_embeddings = model.encode(sentences)
# The result is a list of sentence embeddings as numpy arrays
for sentence, embedding in zip(sentences, sentence_embeddings):
print("Sentence:", sentence)
print("Embedding:", embedding.shape, type(embedding))
print("")
result is like this:
Sentence: This framework generates embeddings for each input sentence
Embedding: (768,) <class 'numpy.ndarray'>
Sentence: Sentences are passed as a list of string.
Embedding: (768,) <class 'numpy.ndarray'>
Sentence: The quick brown fox jumps over the lazy dog.
Embedding: (768,) <class 'numpy.ndarray'>
