app.py

import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
import os
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 environment variables
load_dotenv()
api_key = os.getenv("GOOGLE_API_KEY")
genai.configure(api_key=api_key)

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

def get_text_chunks(text):
    """Split text into manageable chunks for processing."""
    text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
    chunks = text_splitter.split_text(text)
    return chunks

def get_vector_store(text_chunks):
    """Create a FAISS vector store from text chunks."""
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
    vector_store.save_local("faiss_index")

def get_conversational_chain():
    """Create a conversational chain with a custom prompt template."""
    prompt_template = """
    Answer the question as detailed as possible from the provided context. If the answer is not in the provided context, say "answer is not available in the context". Do not provide incorrect answers.

    Context:
    {context}

    Question:
    {question}

    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 user_input(user_question):
    """Process user input, search FAISS index, and generate a response."""
    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")

    # Load FAISS index with deserialization flag
    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)

    # Perform similarity search
    docs = new_db.similarity_search(user_question)

    # Generate response using the conversational chain
    chain = get_conversational_chain()
    response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)

    # Display the response
    st.write("Reply:", response["output_text"])

def main():
    """Main function to run the Streamlit app."""
    st.set_page_config("Chat With Multiple PDF")
    st.header("Chat with Multiple PDF using Gemini💁")

    # User input for questions
    user_question = st.text_input("Ask a Question from the PDF Files")

    if user_question:
        user_input(user_question)

    # Sidebar for uploading and processing PDFs
    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()