Update app.py

app.py

@@ -1,5 +1,6 @@
 import streamlit as st
 from streamlit_chat import message
+# Initialize the CSVLoader to load the uploaded CSV file
 from langchain.document_loaders.csv_loader import CSVLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings import HuggingFaceEmbeddings
@@ -9,18 +10,23 @@ from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
 import sys
 
+# Display the title of the web page
 st.title("Chat with CSV using open source LLM Inference Point 🦙🦜")
+# Display a markdown message with additional information
 st.markdown("<h3 style='text-align: center; color: white;'>Built by <a href='https://github.com/AIAnytime'>AI Anytime with ❤️ </a></h3>", unsafe_allow_html=True)
 
+# Allow users to upload a CSV file
 uploaded_file = st.sidebar.file_uploader("Upload your Data", type="csv")
 
 if uploaded_file :
+# Initialize the CSVLoader to load the uploaded CSV file
    #use tempfile because CSVLoader only accepts a file_path
     with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
         tmp_file.write(uploaded_file.getvalue())
         tmp_file_path = tmp_file.name
 
     db = DB_FAISS_PATH = "vectorstore/db_faiss"
+# Initialize the CSVLoader to load the uploaded CSV file
     loader = CSVLoader(file_path="data/2019.csv", encoding="utf-8", csv_args={'delimiter': ','})
     data = loader.load()
     db.save_local(DB_FAISS_PATH)
@@ -29,17 +35,25 @@ if uploaded_file :
     chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=db.as_retriever())
 
     def conversational_chat(query):
+# Maintain and display the chat history
             result = chain({"question": query, "chat_history": st.session_state['history']})
+# Maintain and display the chat history
             st.session_state['history'].append((query, result["answer"]))
             return result["answer"]
     
+# Maintain and display the chat history
     if 'history' not in st.session_state:
+# Maintain and display the chat history
         st.session_state['history'] = []
 
+# Maintain and display the chat history
     if 'generated' not in st.session_state:
+# Maintain and display the chat history
         st.session_state['generated'] = ["Hello ! Ask me anything about " + uploaded_file.name + " 🤗"]
 
+# Maintain and display the chat history
     if 'past' not in st.session_state:
+# Maintain and display the chat history
         st.session_state['past'] = ["Hey ! 👋"]
         
     #container for the chat history
@@ -56,13 +70,19 @@ if uploaded_file :
         if submit_button and user_input:
             output = conversational_chat(user_input)
             
+# Maintain and display the chat history
             st.session_state['past'].append(user_input)
+# Maintain and display the chat history
             st.session_state['generated'].append(output)
 
+# Maintain and display the chat history
     if st.session_state['generated']:
         with response_container:
+# Maintain and display the chat history
             for i in range(len(st.session_state['generated'])):
+# Maintain and display the chat history
                 message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="big-smile")
+# Maintain and display the chat history
                 message(st.session_state["generated"][i], key=str(i), avatar_style="thumbs")
             
 # Split the text into Chunks
@@ -95,8 +115,8 @@ qa = ConversationalRetrievalChain.from_llm(llm, retriever=docsearch.as_retriever
 
 # Insert a chat message container.
 with st.chat_message("user"):
-   st.write("Hello 👋")
-   st.line_chart(np.random.randn(30, 3))
+    st.write("Hello 👋")
+    st.line_chart(np.random.randn(30, 3))
 
 # Display a chat input widget.
 st.chat_input("Say something")