mpdf.py

import streamlit as st
from PyPDF2 import PdfReader
from langchain_text_splitters import RecursiveCharacterTextSplitter
import os

from langchain_google_genai import GoogleGenerativeAIEmbeddings
import google.generativeai as genai
from langchain_community.vectorstores import FAISS
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain.chains.question_answering import load_qa_chain
from langchain_core.prompts import PromptTemplate
from dotenv import load_dotenv

load_dotenv()
genai.configure(api_key=os.environ['GOOGLE_API_KEY'])

## first we will create a function to read all pages from all pdfs and extract the text
def get_pdf_text(pdf_docs):
    text=""
    for pdf in pdf_docs:
        ## first we will read every pdf using pdfreader, also there are many pages in a pdf so this pdf_reader will be in form of a list
        pdf_reader=PdfReader(pdf)
        for page in pdf_reader.pages:
            text+=page.extract_text()
    return text

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,embedding=embeddings)
    ## we will store this vector store locally
    vector_store.save_local("faiss_index")

def get_conversational_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 present in the given context then just say,"answer is not found", don't make up any answers and don't provide any wrong answrers.
    Context:\n {context}?\n
    Question:\n {question}\n

    Answer:
    """
    model=ChatGoogleGenerativeAI(model="gemini-1.5-flash",temperature=0.3)
    prompt=PromptTemplate(template=prompt_template,input_variables=["context","question"])
    ## since we have to do internal text summarization so its better to use stuff chain
    chain = load_qa_chain(model,chain_type="stuff",prompt=prompt)

    return chain

def user_input(user_question):
    embeddings=GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    new_db=FAISS.load_local("faiss_index",embeddings,allow_dangerous_deserialization=True)
    docs=new_db.similarity_search(user_question)

    chain=get_conversational_chain()

    response=chain(
        {"input_documents":docs,"question":user_question}
        , return_only_outputs=True)
    print(response)
    st.write("Reply: ",response["output_text"])

def main():
    st.set_page_config("Chat PDF")
    st.header("Chat with Multiple PDFs using Gemini💁")

    user_question = st.text_input("Ask a Question from the PDF Files")

    if user_question:
        user_input(user_question)

    with st.sidebar:
        st.title("Menu:")
        pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button", accept_multiple_files=True)
        if st.button("Submit & Process"):
            with st.spinner("Processing..."):
                raw_text = get_pdf_text(pdf_docs)
                text_chunks = get_text_chunks(raw_text)
                get_vector_store(text_chunks)
                st.success("Done")



if __name__ == "__main__":
    main()