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
import whisper

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

model = whisper.load_model("small")
def transcribe(audio):
    # Load audio and pad/trim it to fit 30 seconds
    audio = whisper.load_audio(audio)
    audio = whisper.pad_or_trim(audio)

    # Make log-Mel spectrogram and move to the same device as the model
    mel = whisper.log_mel_spectrogram(audio).to(model.device)

    # Detect the spoken language
    _, probs = model.detect_language(mel)
    detected_language = max(probs, key=probs.get)
    print(f"Detected language: {detected_language}")

    # Decode the audio
    options = whisper.DecodingOptions(fp16=False)
    result = whisper.decode(model, mel, options)

    # Check if the detected language is English; if not, translate the text
    if detected_language != "en":
        # Initialize the translation model; specify source and target languages as needed
        translator = pipeline("translation_xx_to_yy", model="Helsinki-NLP/opus-mt-xx-en")
        translated_text = translator(result.text, max_length=512)[0]['translation_text']
        return translated_text

    return result.text

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 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)
    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 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=0.1)

    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):
    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("QnA with Multiple PDF files💁")

    user_question = st.text_input(result.text)

    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()