app.py

import os
import time
import uuid
import streamlit as st
import nltk

from helpers.entity_extraction_helpers import process_insurance_document
from services.pii_service import PIIService
from services.openai_service import OpenAIService
from services.mongo_service import MongoService
from services.ocr_service import OCRService


def init_session():
    print("------------------ Initializing")
    if 'a' not in st.session_state:
        st.session_state['pii_instance'] = PIIService()
        print("PII service initialized")
        time.sleep(2)
        st.session_state['openai_instance'] = OpenAIService(st.secrets["OPENAI_KEY"], 
                                        st.secrets["OPENAI_AZURE_ENDPOINT"], 
                                        st.secrets["OPENAI_API_VERSION"], 
                                        st.secrets["DEPLOYMENT_NAME"])
        print("OpenAI service initialized")
        time.sleep(2)
        st.session_state['ocr_instance'] = OCRService(st.secrets["OCR_API_KEY"])
        print("OCR service initialized")
        st.session_state.a = 1
        nltk.downloader.download('maxent_ne_chunker')
        nltk.downloader.download('words')
        nltk.downloader.download('treebank')
        nltk.downloader.download('maxent_treebank_pos_tagger')
        nltk.downloader.download('punkt')
        nltk.download('averaged_perceptron_tagger')
        print("-----------------------------")

st.header('', divider='rainbow')
st.title("Data extraction")
st.header('', divider='rainbow')

init_session()

uploaded_doc = st.file_uploader("Upload an insurance document", type=["pdf"])

if uploaded_doc is not None:
    
    with open(uploaded_doc.name,"wb") as f:
        f.write(uploaded_doc.getbuffer())

    document_id = str(uuid.uuid4())
    print(f"File uploaded :: {uploaded_doc.name} :: {document_id}")

    process_out = process_insurance_document(st.session_state['pii_instance'], "", st.session_state['openai_instance'],
                                st.session_state['ocr_instance']    , uploaded_doc.name, document_id)

    st.header('Extracted entities !! ', divider='rainbow')
    st.write(process_out['entities'])
    st.header('', divider='rainbow')
    st.header('Identified personal entities ', divider='rainbow')
    st.write(process_out['masked_entities'])
    st.header('Masked Text ', divider='rainbow')
    st.write(process_out['masked_text'])

### TO RUN :: streamlit run ui_app.py