app.py

import os
from dotenv import load_dotenv
import streamlit as st
from langchain_groq import ChatGroq
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import RetrievalQA

# Load environment variables from .env file
load_dotenv()

def main():
    # Retrieve API key from environment variables
    groq_api_key = os.getenv("GROQ_API_KEY")
    
    # Verify API key is loaded
    if not groq_api_key:
        st.error("GROQ API Key not found. Please check your .env file.")
        return

    st.title("PDF Chat with Groq LLM")
    
    # File uploader
    uploaded_file = st.file_uploader("Upload a PDF", type="pdf")
    
    if uploaded_file is not None:
        # Save the uploaded PDF temporarily
        with open("temp.pdf", "wb") as f:
            f.write(uploaded_file.getbuffer())
        
        # Load the PDF
        loader = PyPDFLoader("temp.pdf")
        pages = loader.load()
        
        # Split the text
        text_splitter = RecursiveCharacterTextSplitter(
            chunk_size=1000, 
            chunk_overlap=200
        )
        texts = text_splitter.split_documents(pages)
        
        # Create embeddings
        embeddings = HuggingFaceEmbeddings(
            model_name="sentence-transformers/all-MiniLM-L6-v2"
        )
        
        # Create vector store
        vectorstore = FAISS.from_documents(texts, embeddings)
        
        # Initialize Groq LLM with API key
        llm = ChatGroq(
            temperature=0.7, 
            model_name='llama3-70b-8192',
            api_key=groq_api_key
        )
        
        # Create QA chain
        qa_chain = RetrievalQA.from_chain_type(
            llm=llm, 
            chain_type="stuff", 
            retriever=vectorstore.as_retriever(search_kwargs={"k": 3})
        )
        
        # Chat input
        query = st.text_input("Ask a question about the PDF:")
        
        if query:
            # Get response
            response = qa_chain.invoke(query)
            st.write("Response:", response['result'])

if __name__ == "__main__":
    main()