Apply multiple rows of pandas dataframe to text2text-generation pipeline

🤗Transformers
1

Hi,

I am trying to apply the text of all the rows of a pandas dataframe on a text2text-generation pipeline.

However, everytime that I apply a list of multiple strings, only the first item of the list is being processed.

Is there any method to apply multiple strings into the pipeline in once in order to get these triples in 1 output format?

Please see below for the code

Thanks in advance.

from transformers import pipeline

triplet_extractor = pipeline('text2text-generation', model='Babelscape/rebel-large', tokenizer='Babelscape/rebel-large')

# We need to use the tokenizer manually since we need special tokens.
extracted_text = triplet_extractor.tokenizer.batch_decode([triplet_extractor('text', return_tensors=True, return_text=False)[0]["generated_token_ids"]])

print(extracted_text)

{‘Decent Little Reader, Poor Tablet’,
‘Ok For What It Is’,
‘Too Heavy and Poor weld quality,’,
‘difficult mount’,
‘just got it installed’}