Update app.py

app.py

@@ -3,7 +3,7 @@ from langchain_groq import ChatGroq
 import yfinance as yf
 
 # Initialize the ChatGroq model
-llm = ChatGroq(model_name="Llama3-8b-8192", api_key="groq_api_key")
+llm = ChatGroq(model_name="Llama3-8b-8192", api_key="groq_api_key")  # Ensure this key is set in your Hugging Face secrets
 
 # Custom CSS for dark blue theme
 st.markdown(
@@ -47,18 +47,28 @@ if prompt := st.chat_input("Ask me about stocks..."):
     # Fetch stock data or generate response based on user input
     if "invest" in prompt.lower() or "should I invest" in prompt.lower():
         company_name = prompt.split()[-1]  # Assuming the last word is the ticker symbol or company name
-        stock_data = yf.Ticker(company_name).info
         
-        response = f"Here is the data for {company_name}:\n"
-        response += f"Current Price: {stock_data.get('currentPrice', 'N/A')}\n"
-        response += f"Market Cap: {stock_data.get('marketCap', 'N/A')}\n"
-        response += f"PE Ratio: {stock_data.get('trailingPE', 'N/A')}\n"
-        response += f"Dividend Yield: {stock_data.get('dividendYield', 'N/A')}\n"
+        try:
+            stock_data = yf.Ticker(company_name).info
+            
+            # Check if stock_data contains valid information
+            if 'currentPrice' in stock_data:
+                response = f"Here is the data for {company_name}:\n"
+                response += f"Current Price: {stock_data.get('currentPrice', 'N/A')}\n"
+                response += f"Market Cap: {stock_data.get('marketCap', 'N/A')}\n"
+                response += f"PE Ratio: {stock_data.get('trailingPE', 'N/A')}\n"
+                response += f"Dividend Yield: {stock_data.get('dividendYield', 'N/A')}\n"
+            else:
+                response = f"Sorry, I couldn't find data for {company_name}. Please check the ticker symbol."
         
-        # Add more insights or advice logic here if needed
+        except Exception as e:
+            response = f"An error occurred while fetching data: {str(e)}"
 
     else:
-        response = llm.invoke(prompt)  # Use the LLM for general questions
+        try:
+            response = llm.invoke(prompt)  # Use the LLM for general questions
+        except Exception as e:
+            response = f"An error occurred while processing your request: {str(e)}"
 
     # Display assistant response in chat message container
     with st.chat_message("assistant"):