app.py

import streamlit as st
from haystack.utils import fetch_archive_from_http, clean_wiki_text, convert_files_to_docs
from haystack.document_stores import InMemoryDocumentStore
from haystack.pipelines import ExtractiveQAPipeline
from haystack.nodes import FARMReader, TfidfRetriever
import validators
import json

doc_dir = './article_txt_got'
document_store = InMemoryDocumentStore()
docs = convert_files_to_docs(dir_path=doc_dir, clean_func=clean_wiki_text, split_paragraphs=True)

document_store.write_documents(docs)
retriever = TfidfRetriever(document_store=document_store)
reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2", use_gpu=True)

pipeline = ExtractiveQAPipeline(reader, retriever)

def ask_question(question):
    prediction = pipeline.run(query=question, params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 5}})
    st.write(prediction)

question = st.text_input(label="Ask a Question about Game of Thromes", value="Who is Arya's father?")

if question:
    ask_question(question)