import streamlit as st
#from transformers import pipeline

#pipe = pipeline('sentiment-analysis')
#text = st.text_area('enter some text!')

#if text: 
 # out = pipe(text)
  #st.json(out)
  
from transformers import pipeline

model_name = "deepset/xlm-roberta-large-squad2"

qa_pl = pipeline('question-answering', model=model_name, tokenizer=model_name, device=0)

#predictions = []

# batches might be faster 
ctx  = st.text_area('Gib context')
q = st.text_area('Gib question')

if context: 
  result = qa_pl(context=ctx, question=q)
  st.json(result["answer"])

#for ctx, q in test_df[["context", "question"]].to_numpy():

#    result = qa_pl(context=ctx, question=q)
    
#    predictions.append(result["answer"])

#model = AutoModelForQuestionAnswering.from_pretrained(model_name)
#tokenizer = AutoTokenizer.from_pretrained(model_name)