I have a pandas dataframe and one of the series is a selection of paragraphs that I wish to compare for similarity. The mean wordcount is 62, so quite short.
typically to get embeddings I would use this syntax; (with sentences being a list of sentences)
sentence_embeddings = model.encode(sentences)
as I am reading from the dataframe with multiple paragraphs it needs to be in a for loop?
for sentence in series:
sentence_embeddings[sentence]=model.encode(sentence)
however this syntax is incorrect if anyone can suggest how I can make this work.