Update app.py

app.py

@@ -1,3 +1,4 @@
+# Step 1: Import required modules
 import streamlit as st
 from PyPDF2 import PdfReader
 import docx2txt
@@ -5,20 +6,19 @@ import json
 import pandas as pd
 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
+import whisper
+from groq import GroqAPI
 from dotenv import load_dotenv
 
 # Step 2: Load environment variable
 load_dotenv()
-api_key = os.getenv("GOOGLE_API_KEY")
+groq_api_key = os.getenv("GROQ_API_KEY")
 
-# Step 3: Configure Google_API
-genai.configure(api_key=api_key)
+# Step 3: Initialize Groq API
+groq = GroqAPI(api_key=groq_api_key)
 
 # Step 4: Function to read files and extract text
 def extract_text(file):
@@ -59,7 +59,7 @@ def get_text_chunks(text):
 
 # Step 6: Function for converting chunks into embeddings and saving the FAISS index
 def get_vector_store(text_chunks):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    embeddings = groq.get_embeddings(text_chunks)
     vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
     
     # Ensure the directory exists
@@ -69,7 +69,7 @@ def get_vector_store(text_chunks):
     vector_store.save_local("faiss_index")
     print("FAISS index saved successfully.")
 
-# Step 7: Function to implement Gemini-Pro Model
+# Step 7: Function to implement the Groq Model
 def get_conversational_chain():
     prompt_template = """
     Answer the question as detailed as possible from the provided context. If the answer is not in
@@ -79,14 +79,14 @@ def get_conversational_chain():
 
     Answer:
     """
-    model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
+    model = groq.get_chat_model("llama3-8b-8192")  # Replace with your Groq model ID
     prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
     chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
     return chain
 
 # Step 8: Function to take inputs from user and generate response
 def user_input(user_question):
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    embeddings = groq.get_embeddings([user_question])
     new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
     docs = new_db.similarity_search(user_question)
     chain = get_conversational_chain()
@@ -96,7 +96,7 @@ def user_input(user_question):
 # Step 9: Streamlit App
 def main():
     st.set_page_config(page_title="RAG Chatbot")
-    st.header("Chat with Multiple Files using RAG and Gemini ")
+    st.header("Chat with Multiple Files using RAG and Groq 💁")
 
     user_question = st.text_input("Ask a Question")