textReader.py

import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
import os
import tabula

from langchain_google_genai import GoogleGenerativeAIEmbeddings
import google.generativeai as genai

from langchain.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
from dotenv import load_dotenv

load_dotenv()
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))


def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        for page in pdf_reader.pages:
            text += page.extract_text()
    return text


def extract_tables(pdf_docs):
    tables = []
    for pdf in pdf_docs:
        tables += tabula.read_pdf(pdf, pages='all', multiple_tables=True)
    return tables


def get_text_chunks(text):
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
    chunks = text_splitter.split_text(text)
    return chunks


def get_vector_store(text_chunks):
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    vector_store = FAISS.from_texts(text_chunks, embeddings)
    vector_store.save_local("faiss_index")


def get_conversation_chain():
    prompt_template = """
    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
    Context:\n {context}?\n
    Question: \n{question}\n

    Answer:
    """
    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
    return chain


def answer_question(user_question, pdf_text):
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
    docs = new_db.similarity_search(pdf_text)
    chain = get_conversation_chain()
    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
    return response["output_text"]


def textReader():
    st.header("Chat with TaxCraft")
    st.write("Upload the documents related to tax and get information on tax deduction")

    uploaded_files = st.file_uploader("Upload PDF Files", accept_multiple_files=True)

    user_question = st.text_input("Ask a Question:")

    if uploaded_files and user_question:
        pdf_text = get_pdf_text(uploaded_files)
        if st.button("Submit & Process"):
            with st.spinner("Processing..."):
                raw_text = get_pdf_text(uploaded_files)
                text_chunks = get_text_chunks(raw_text)
                get_vector_store(text_chunks)
                tables = extract_tables(uploaded_files)
                answer = answer_question(user_question, pdf_text)
                st.success("Done")
                st.write("Reply: ", answer)

    with st.sidebar:
        st.title("Menu:")
        st.write("You can ask any question related to tax.")
        st.write("Please upload the PDF files for better results.")