app.py

import streamlit as st

st.markdown("""### TL;DR: give me the keywords!
Here you can get the keywords and topic of the article based on it's title or abstract.

The only supported language is English.""")

st.markdown("<p style=\"text-align:center\"><img width=700px src='https://c.tenor.com/IKt-6tAk9CUAAAAd/thats-a-lot-of-words-lots-of-words.gif'></p>", unsafe_allow_html=True)

#from transformers import pipeline

#pipe = pipeline("ner", "Davlan/distilbert-base-multilingual-cased-ner-hrl")

#st.markdown("#### Title:")
title = st.text_area("Title:")
abstract = st.text_area("abstract:")

from transformers import AutoModel, AutoTokenizer
#from tqdm import tqdm as tqdm

import transformers
transformers.utils.logging.disable_progress_bar()

model_name = "distilroberta-base"
main_model = AutoModel.from_pretrained(model_name)
main_tokenizer = AutoTokenizer.from_pretrained(model_name)


from utils.utils import *
import spacy
#import en_core_web_sm

import os
os.system("python3 -m spacy download en")

# Вообще, стоит найти pipeline, заточенный под научный текст.
# Но этим займёмся потом, если будет время.
main_nlp = spacy.load('en_core_web_sm')

text = title + abstract

if not text is None and len(text) > 0:
    #keywords = get_candidates(text, main_nlp)
    keywords = get_keywords(summaries[0], main_nlp, main_model, main_tokenizer)
    st.markdown(f"{keywords}")
else:
    st.markdown("Please, try to enter something.")