Update app.py

app.py

@@ -1,34 +1,23 @@
 import streamlit as st
 import PyPDF2
-import os
-import faiss
-import numpy as np
-from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.vectorstores import FAISS
-from langchain.llms import OpenAI
+from langchain.embeddings import GroqEmbeddings
+from langchain_groq import ChatGroq
 from langchain.chains import RetrievalQA
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from dotenv import load_dotenv
-
-# Load environment variables
-load_dotenv()
-
-# Streamlit UI
-st.title("PDF Q&A Assistant")
-st.write("Upload a PDF and ask questions about its content.")
 
-# Input Groq API Key
-groq_api_key = st.secrets["GROQ_API_KEY"]
+# Set up Groq API key
+groq_api_key = "your_groq_api_key"
 
-# Initialize Groq Model
-llm = OpenAI(api_key=groq_api_key, base_url="https://api.groq.com")
-embeddings = OpenAIEmbeddings(api_key=groq_api_key, base_url="https://api.groq.com")
+# Initialize LLM and Embeddings using Groq
+llm = ChatGroq(model_name="llama3-70b", api_key=groq_api_key)
+embeddings = GroqEmbeddings(api_key=groq_api_key)
 
 uploaded_file = st.file_uploader("Upload your PDF", type=["pdf"])
 
 if uploaded_file:
     with st.spinner("Processing PDF..."):
-        pdf_reader = PyPDF2.PdfReader(uploaded_file)
+        pdf_reader = PyPDF2.PdfReader(uploaded_file)  
         text = "".join([page.extract_text() for page in pdf_reader.pages if page.extract_text()])
 
         # Split text into smaller chunks for better retrieval