app.py

import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
import os
from dotenv import load_dotenv
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import ChatPromptTemplate
from dotenv import load_dotenv

from langchain_huggingface import HuggingFaceEndpoint
from langchain_huggingface import HuggingFaceEmbeddings
from langchain.prompts import PromptTemplate



load_dotenv()
hugging_face_api = os.getenv("HUGGINGFACEHUB_API_TOKEN")
os.environ["HUGGINGFACEHUB_API_TOKEN"]=hugging_face_api





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):
    model_name = "sentence-transformers/all-MiniLM-L12-v2"
    model_kwargs = {'device': 'cpu'}
    encode_kwargs = {'normalize_embeddings': False}
    embeddings = HuggingFaceEmbeddings(model_name=model_name,model_kwargs=model_kwargs,encode_kwargs=encode_kwargs)
    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:
    """

    repo_id="mistralai/Mistral-7B-Instruct-v0.3"
    model = HuggingFaceEndpoint(repo_id=repo_id,max_length=128, token=hugging_face_api)

    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):
    model_name = "sentence-transformers/all-MiniLM-L12-v2"
    model_kwargs = {'device': 'cpu'}
    encode_kwargs = {'normalize_embeddings': False}
    embeddings = HuggingFaceEmbeddings(model_name=model_name,model_kwargs=model_kwargs,encode_kwargs=encode_kwargs)

    
    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")
    with st.sidebar:
        st.title('Chat PDF 📚')
        st.markdown('''
    ## About
    This is a simple Streamlit app that allows you to chat with your PDF files.
    ## How to use
        
''')
        st.write('Here you can upload your PDF files and ask questions from the PDF files.We will provide you the most relevant answer from the PDF files. You can also upload multiple files at once.')
    st.header("Chat with your PDF 💁")
    pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button. you can also upload multiple files also", 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")

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

    if user_question:
        user_input(user_question)

    
        



if __name__ == '__main__':
    main()