Update app.py

app.py

@@ -4,11 +4,13 @@ from dotenv import load_dotenv
 import streamlit as st
 from PyPDF2 import PdfReader
 from langchain.text_splitter import CharacterTextSplitter
+# from langchain.embeddings import HuggingFaceInstructEmbeddings
 from langchain_cohere import CohereEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
-from langchain_groq import ChatGroq  # Ensure this is installed
+# from langchain.llms import Ollama
+from langchain_groq import ChatGroq
 
 # Load environment variables
 load_dotenv()
@@ -19,10 +21,6 @@ logging.basicConfig(
     format='%(asctime)s - %(levelname)s - %(message)s'
 )
 
-# Access API keys
-cohere_api_key = os.getenv("COHERE_API_KEY")
-groq_api_key = os.getenv("GROQ_API_KEY")
-
 # Function to extract text from PDF files
 def get_pdf_text(pdf_docs):
     text = ""
@@ -44,7 +42,13 @@ def get_text_chunks(text):
     return chunks
 
 # Function to create a FAISS vectorstore
+# def get_vectorstore(text_chunks):
+#     embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+#     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+#     return vectorstore
+
 def get_vectorstore(text_chunks):
+    cohere_api_key = os.getenv("COHERE_API_KEY")
     embeddings = CohereEmbeddings(model="embed-english-v3.0", cohere_api_key=cohere_api_key)
     vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
     return vectorstore
@@ -52,17 +56,10 @@ def get_vectorstore(text_chunks):
 # Function to set up the conversational retrieval chain
 def get_conversation_chain(vectorstore):
     try:
-        # Initialize Groq's Chat model
-        llm = ChatGroq(
-            model="llama2-70b-4096",  # You can use other models like "mixtral-8x7b-32768"
-            temperature=0.5,
-            groq_api_key=groq_api_key
-        )
-        
-        # Set up memory for the conversation
+        # llm = Ollama(model="llama3.2:1b")
+        llm = ChatGroq(model="llama-3.3-70b-versatile", temperature=0.5)
         memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
         
-        # Create the conversational retrieval chain
         conversation_chain = ConversationalRetrievalChain.from_llm(
             llm=llm,
             retriever=vectorstore.as_retriever(),
@@ -91,6 +88,7 @@ def handle_userinput(user_question):
 
 # Main function to run the Streamlit app
 def main():
+    load_dotenv()
     st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")
 
     if "conversation" not in st.session_state: