import streamlit as st
import transformers
from transformers import pipeline
from transformers import AutoTokenizer, AutoModelForMaskedLM
import pandas as pd


tokenizer = AutoTokenizer.from_pretrained("moussaKam/AraBART", padding= True, truncation=True, max_length=128)
model = AutoModelForMaskedLM.from_pretrained("moussaKam/AraBART")


def next_word(text, pipe):
    res_dict= {  
  'Word':[],
  'Score':[],
  }
    res=pipe(text)
    for e in res:
        res_dict['Word'].append(e['token_str'])
        res_dict['Score'].append(e['score'])
    return res_dict

st.title("Predict Next Word")
st.write("Use our model to expand your query based on the DB content")
default_value = "التاريخ هو تحليل و"
# sent is the the variable holding the user's input
sent = st.text_area("Text", default_value, height = 30)
sent += ' <mask>'

pipe = pipeline("fill-mask", tokenizer = tokenizer, model = model)
dict_next_words = next_word(sent, pipe)
df = pd.DataFrame.from_dict(dict_next_words)
df.reset_index(drop=True, inplace=True)
st.table(df)