app.py

import streamlit as st
import os
from haystack.utils import fetch_archive_from_http, clean_wiki_text, convert_files_to_docs
from haystack.schema import Answer
from haystack.document_stores import InMemoryDocumentStore
from haystack.pipelines import ExtractiveQAPipeline
from haystack.nodes import FARMReader, TfidfRetriever
import logging
from markdown import markdown
from annotated_text import annotation
from PIL import Image

os.environ['TOKENIZERS_PARALLELISM'] ="false"

#Haystack Components
@st.cache(hash_funcs={"builtins.SwigPyObject": lambda _: None},allow_output_mutation=True)
def start_haystack():
    document_store = InMemoryDocumentStore()
    load_and_write_data(document_store)
    retriever = TfidfRetriever(document_store=document_store)
    reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2-distilled", use_gpu=True)
    pipeline = ExtractiveQAPipeline(reader, retriever)
    return pipeline

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

    document_store.write_documents(docs)

pipeline = start_haystack()

def set_state_if_absent(key, value):
    if key not in st.session_state:
        st.session_state[key] = value

set_state_if_absent("question", "Who is Arya's father?")
set_state_if_absent("results", None)


def reset_results(*args):
    st.session_state.results = None

#Streamlit App

image = Image.open('got-haystack.png')
st.image(image)

st.markdown( """
This QA demo uses a [Haystack Extractive QA Pipeline](https://haystack.deepset.ai/components/ready-made-pipelines#extractiveqapipeline) with 
an [InMemoryDocumentStore](https://haystack.deepset.ai/components/document-store) which contains documents about Game of Thrones 👑
Go ahead and ask questions about the marvellous kingdom!
""", unsafe_allow_html=True)

question = st.text_input("", value=st.session_state.question, max_chars=100, on_change=reset_results)

def ask_question(question):
    prediction = pipeline.run(query=question, params={"Retriever": {"top_k": 10}, "Reader": {"top_k": 5}})
    results = []
    for answer in prediction["answers"]:
        answer = answer.to_dict()
        if answer["answer"]:
            results.append(
                {
                    "context": "..." + answer["context"] + "...",
                    "answer": answer["answer"],
                    "relevance": round(answer["score"] * 100, 2),
                    "offset_start_in_doc": answer["offsets_in_document"][0]["start"],
                }
            )
        else:
            results.append(
                {
                    "context": None,
                    "answer": None,
                    "relevance": round(answer["score"] * 100, 2),
                }
            )
    return results

if question:
    with st.spinner("👑    Performing semantic search on royal scripts..."):
        try:
            msg = 'Asked ' + question
            logging.info(msg)
            st.session_state.results = ask_question(question)    
        except Exception as e:
            logging.exception(e)
    


if st.session_state.results:
    st.write('## Top Results')
    for count, result in enumerate(st.session_state.results):
        if result["answer"]:
            answer, context = result["answer"], result["context"]
            start_idx = context.find(answer)
            end_idx = start_idx + len(answer)
            st.write(
                markdown(context[:start_idx] + str(annotation(body=answer, label="ANSWER", background="#964448", color='#ffffff')) + context[end_idx:]),
                unsafe_allow_html=True,
            )
            st.markdown(f"**Relevance:** {result['relevance']}")
        else:
            st.info(
                "🤔    Haystack is unsure whether any of the documents contain an answer to your question. Try to reformulate it!"
            )