I am trying to get the bert embeddings for all the values present in dataframe.

My code looks like:

from sentence_transformers import SentenceTransformer, util
model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
import pandas as pd

sentences =[ ["I'm happy", "I'm full of happiness"], ["I am sam", "I am good"]]

df = pd.DataFrame(sentences)

encoded_df = df.applymap(model.encode(convert_to_tensor=True))

Facing the below error:

encode() missing 1 required positional argument: 'sentences'

Is there any method to achieve this?

CodePudding user response：

You can use

encoded_df = df.applymap(lambda x: model.encode(x, convert_to_tensor=True))