changed imports

app.py

@@ -1,20 +1,22 @@
-import streamlit as st
-import os
-from langchain_groq import ChatGroq
+# Langchain imports
+from langchain_community.vectorstores.faiss import FAISS
 from langchain_community.document_loaders import WebBaseLoader
-# from langchain_community.embeddings import OllamaEmbeddings
-from langchain_google_genai import GoogleGenerativeAIEmbeddings
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.chains.combine_documents import create_stuff_documents_chain
 from langchain_core.prompts import ChatPromptTemplate
 from langchain.chains import create_retrieval_chain
-from langchain_community.vectorstores.faiss import FAISS
 
+# Embedding and model imports
+from langchain_google_genai import GoogleGenerativeAIEmbeddings
+from langchain_groq import ChatGroq
+
+# Other
+import streamlit as st
+import os
 import time
 from PyPDF2 import PdfReader
 import tempfile
 
-
 st.title("Ask your questions from pdf(s) or website")
 option = None
 
@@ -55,6 +57,11 @@ def llm_model():
         print("Response time :", time.process_time()-start)
         st.write(response['answer'])
 
+        with st.expander("Did not like the response? Check out more here"):
+            for i, doc in enumerate(response['context']):
+                st.write(doc.page_content)
+                st.write("-----------------------------")
+
 st.session_state.embeddings = GoogleGenerativeAIEmbeddings(model = 'models/embedding-001')
 st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size =1000, chunk_overlap= 200)
 
@@ -76,10 +83,4 @@ if option:
             st.session_state.vector = FAISS.from_texts(st.session_state.final_documents,st.session_state.embeddings)
             llm_model()
 
-        # with st.expander("Document Similarity Search"):
-        #     for i, doc in enumerate(response['context']):
-        #         st.write(doc.page_content)
-        #         st.write("-----------------------------")
-
-