app.py

import os
import logging
from dotenv import load_dotenv
import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain_groq import ChatGroq
from langchain.embeddings import HuggingFaceEmbeddings

# Load environment variables
load_dotenv()
GROQ_API_KEY = os.getenv("GROQ_API_KEY")

# Set up logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# Function to extract text from PDF files
def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        try:
            pdf_reader = PdfReader(pdf)
            for page in pdf_reader.pages:
                extracted_text = page.extract_text()
                if extracted_text:
                    text += extracted_text + "\n"
        except Exception as e:
            logging.error(f"Error reading PDF: {e}")
            st.error("Failed to read one or more PDF files.")
    return text

# Function to split extracted text into chunks
def get_text_chunks(text):
    if not text.strip():
        st.error("No text found in the uploaded PDF.")
        return []
    text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len)
    return text_splitter.split_text(text)

# Function to create a FAISS vectorstore using Hugging Face embeddings
def get_vectorstore(text_chunks):
    if not text_chunks:
        return None
    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
    return FAISS.from_texts(texts=text_chunks, embedding=embeddings)

# Function to set up the conversational retrieval chain
def get_conversation_chain(vectorstore):
    try:
        llm = ChatGroq(model="llama-3.3-70b-versatile", temperature=0.5, api_key=GROQ_API_KEY)
        memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
        
        return ConversationalRetrievalChain.from_llm(
            llm=llm, retriever=vectorstore.as_retriever(), memory=memory
        )
    except Exception as e:
        logging.error(f"Error creating conversation chain: {e}")
        st.error("An error occurred while setting up the conversation chain.")
        return None

# Handle user input
def handle_userinput(user_question):
    if st.session_state.conversation:
        response = st.session_state.conversation({'question': user_question})
        st.session_state.chat_history = response.get('chat_history', [])

        for i, message in enumerate(st.session_state.chat_history):
            if i % 2 == 0:
                st.write(f"**User:** {message.content}")
            else:
                st.write(f"**Bot:** {message.content}")
    else:
        st.warning("Please process the documents first.")

# Main function to run the Streamlit app
def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple PDFs", page_icon="📚")

    if "conversation" not in st.session_state:
        st.session_state.conversation = None
    if "chat_history" not in st.session_state:
        st.session_state.chat_history = None

    st.header("Chat with multiple PDFs 📚")
    user_question = st.text_input("Ask a question about your documents:")
    
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader("Upload your PDFs here and click 'Process'", accept_multiple_files=True)
        
        if st.button("Process"):
            with st.spinner("Processing..."):
                raw_text = get_pdf_text(pdf_docs)
                text_chunks = get_text_chunks(raw_text)

                if text_chunks:
                    vectorstore = get_vectorstore(text_chunks)
                    if vectorstore:
                        st.session_state.conversation = get_conversation_chain(vectorstore)
                        st.success("Processing complete! You can now ask questions.")

if __name__ == '__main__':
    main()