new_app

import os
import argparse
from dotenv import load_dotenv

from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_google_genai import (
    GoogleGenerativeAIEmbeddings,
    ChatGoogleGenerativeAI
)
from langchain.vectorstores import FAISS
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
import google.generativeai as genai

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


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


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


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


def get_conversational_chain():
    """Create a conversational chain for question answering."""
    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 available in the context, just say, "answer is not available in the context", don't provide the wrong answer.

Context:
{context}

Question:
{question}

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


def process_user_input(user_question, vector_store):
    """Process user input and generate a response."""
    docs = vector_store.similarity_search(user_question)
    chain = get_conversational_chain()
    response = chain(
        {"input_documents": docs, "question": user_question}, return_only_outputs=True
    )
    return response["output_text"]


def main():
    """Main function for the CLI program."""
    parser = argparse.ArgumentParser(
        description="Chat with PDF files using Gemini AI"
    )
    parser.add_argument(
        "pdf_files", nargs="+", help="Paths to the PDF files to be processed"
    )
    args = parser.parse_args()

    print("Processing PDF files...")
    processed_pdf_text = get_pdf_text(args.pdf_files)
    text_chunks = get_text_chunks(processed_pdf_text)
    vector_store = get_vector_store(text_chunks)
    print("PDFs processed successfully!")

    while True:
        user_question = input("\nAsk a question (or type 'exit' to quit): ")
        if user_question.strip().lower() == "exit":
            print("Goodbye!")
            break
        response = process_user_input(user_question, vector_store)
        print("\nReply:", response)


if __name__ == "__main__":
    main()