import streamlit as st from transformers import pipeline from transformers import AutoModelForQuestionAnswering, AutoTokenizer from transformers import DebertaV2Tokenizer st.set_page_config(page_title="Automated Question Answering System") st.title("Automated Question Answering System") st.subheader("Try") @st.cache_resource(show_spinner=True) def question_model(): model_name = "kxx-kkk/FYP_deberta-v3-base-squad2_mrqa" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForQuestionAnswering.from_pretrained(model_name) question_answerer = pipeline("question-answering", model=model, tokenizer=tokenizer) return question_answerer st.markdown("

Question Answering on Academic Essays

", unsafe_allow_html=True) st.markdown("

What is extractive question answering about?

", unsafe_allow_html=True) st.write("Extractive question answering is a Natural Language Processing task where text is provided for a model so that the model can refer to it and make predictions about where the answer to a question is.") # st.markdown('___') tab1, tab2 = st.tabs(["Input text", "Upload File"]) with tab1: sample_question = "What is NLP?" with open("sample.txt", "r") as text_file: sample_text = text_file.read() context = st.text_area("Use the example below / input your essay in English (10,000 characters max)", value=sample_text, max_chars=10000, height=330) question = st.text_input(label="Use the example question below / enter your own question", value=sample_question) button = st.button("Get answer") if button: with st.spinner(text="Loading question model..."): question_answerer = question_model() with st.spinner(text="Getting answer..."): answer = question_answerer(context=context, question=question) answer = answer["answer"] container = st.container(border=True) container.write("
Answer:
" + answer, unsafe_allow_html=True) with tab2: uploaded_file = st.file_uploader("Choose a .txt file to upload", type=["txt"]) if uploaded_file is not None: raw_text = str(uploaded_file.read(),"utf-8") context = st.text_area("", value=raw_text, height=330) question = st.text_input(label="Enter your question", value=sample_question) button = st.button("Get answer") if button: with st.spinner(text="Loading question model..."): question_answerer = question_model() with st.spinner(text="Getting answer..."): answer = question_answerer(context=context, question=question) answer = answer["answer"] st.success(answer)