appStore/multiapp.py

"""Frameworks for running multiple Streamlit applications as a single app.
"""
import streamlit as st
from PIL import Image
import tempfile
import logging
from sklearn.feature_extraction import _stop_words
from haystack.document_stores import InMemoryDocumentStore
from haystack.pipelines import ExtractiveQAPipeline
from haystack.nodes import FARMReader, TfidfRetriever
import scripts.process as pre
import scripts.clean as clean
logger = logging.getLogger(__name__)

# Initialization
if 'file' not in st.session_state:
    st.session_state['pipeline'] = None
    
class MultiApp:
    """
    Framework for combining multiple streamlit applications.
    """
    def __init__(self):
        self.apps = []

    def add_app(self, title, func):
        """Adds a new application.
        Parameters
        ----------
        func:
            the python function to render this app.
        title:
            title of the app. Appears in the dropdown in the sidebar.
        """
        self.apps.append({
            "title": title,
           # "icon": icon,
            "function": func
        })

    def run(self):
        if 'file' not in st.session_state:
            st.session_state['pipeline'] = None
    
        st.sidebar.write(format_func=lambda app: app['title'])
        image = Image.open('appStore/img/sdsn.png')
        st.sidebar.image(image)
        app = st.sidebar.radio(
            'Pages',
            self.apps,
            format_func=lambda app: app['title'])    
        app['function']()
        st.sidebar.markdown('')
        st.sidebar.markdown("##  📌 Upload document ")
        file = st.sidebar.file_uploader('', type=['pdf', 'docx', 'txt']) #Upload PDF File
        
        if file is not None:
            with tempfile.NamedTemporaryFile(mode="wb") as temp:
                bytes_data = file.getvalue()
                temp.write(bytes_data)
                file_name = file.name
                file_path = temp.name
                
                st.write("Filename: ", file.name)
                
                # load document
                documents = pre.load_document(temp.name,file_name)
                documents_processed = pre.preprocessing(documents)
                pipeline = start_haystack(documents_processed)
                st.session_state['pipeline'] = pipeline