Update app.py

app.py

@@ -61,9 +61,6 @@ for ticker, data in all_data.items():
         series_list.append(s)
 adj_close_data = pd.concat(series_list, axis=1) if series_list else pd.DataFrame()
 
-# Display the first few rows to verify (for debugging; remove in production)
-print(adj_close_data.head())
-
 # Update available symbols to include new tickers
 available_symbols = ['TSLA', 'MSFT', 'NVDA', 'GOOG', 'AMZN', 'SPY', 'AAPL', 'META', 'NFLX', 'INTC', 'AMD', 'IBM', 'ORCL', 'CSCO', 'JPM', 'BAC', 'WFC', 'V', 'MA', 'XOM', 'CVX', 'PFE', 'JNJ', 'MRK', 'PLTR', 'SOUN']
 
@@ -182,41 +179,59 @@ def generate_response(user_query, enable_thinking=False):
             start_date, end_date = parse_dates(user_query)
             print(f"Parsed dates: {start_date} to {end_date}")  # Debugging
             if start_date is None or end_date is None:
-                return "Invalid date range provided. Please specify a valid range, e.g., 'between 2010 and 2020'."
-            hist = fetch_stock_data(symbol, start_date.strftime('%Y-%m-%d'), end_date.strftime('%Y-%m-%d'))
-            print(f"Data fetched for {symbol}: {'Valid' if hist is not None and not hist.empty else 'Empty/None'}")  # Debugging
-            if "average price" in user_query.lower():
-                if hist is not None and not hist.empty and 'Close' in hist.columns:
-                    avg_price = hist['Close'].mean()
-                    summary = f"The average adjusted closing price for {symbol} from {start_date.strftime('%Y-%m-%d')} to {end_date.strftime('%Y-%m-%d')} is ${avg_price:.2f}."
-                else:
-                    summary = f"No data available for {symbol} in the specified period."
-            elif "cagr" in user_query.lower() or "return" in user_query.lower():
-                growth_rate = calculate_growth_rate(start_date, end_date, symbol)
-                if growth_rate is not None:
-                    summary = f"The CAGR for {symbol} over the period from {start_date.strftime('%Y-%m-%d')} to {end_date.strftime('%Y-%m-%d')} is {growth_rate:.2f}%."
-                else:
-                    summary = f"No data available for {symbol} in the specified period."
-            investment_match = re.search(r'\$(\d+)', user_query)
-            if investment_match:
-                principal = float(investment_match.group(1))
-                years = (end_date - start_date).days / 365.25
-                projected = calculate_investment(principal, years)
-                summary += f" Projecting ${principal} at 7% return over {years:.1f} years: ${projected:.2f}."
+                summary = "Invalid date range provided. Please specify a valid range, e.g., 'between 2010 and 2020'."
+            else:
+                hist = fetch_stock_data(symbol, start_date.strftime('%Y-%m-%d'), end_date.strftime('%Y-%m-%d'))
+                print(f"Data fetched for {symbol}: { 'Valid' if hist is not None and not hist.empty else 'Empty/None'}")  # Debugging
+                if "average price" in user_query.lower():
+                    if hist is not None and not hist.empty and 'Close' in hist.columns:
+                        avg_price = hist['Close'].mean()
+                        summary = f"The average adjusted closing price for {symbol} from {start_date.strftime('%Y-%m-%d')} to {end_date.strftime('%Y-%m-%d')} is ${avg_price:.2f}."
+                    else:
+                        summary = f"No data available for {symbol} in the specified period."
+                elif "cagr" in user_query.lower() or "return" in user_query.lower():
+                    growth_rate = calculate_growth_rate(start_date, end_date, symbol)
+                    if growth_rate is not None:
+                        summary = f"The CAGR (geometric average annual return) for {symbol} over the period from {start_date.strftime('%Y-%m-%d')} to {end_date.strftime('%Y-%m-%d')} is {growth_rate:.2f}%."
+                    else:
+                        summary = f"No data available for {symbol} in the specified period."
+                investment_match = re.search(r'\$(\d+)', user_query)
+                if investment_match:
+                    principal = float(investment_match.group(1))
+                    years = (end_date - start_date).days / 365.25
+                    projected = calculate_investment(principal, years)
+                    summary += f" Projecting ${principal} at 7% return over {years:.1f} years: ${projected:.2f}."
         else:
             summary = "Could not identify a valid stock symbol in the query. Please specify a company or ticker (e.g., 'Tesla' or 'TSLA')."
+    
+    # Enhanced system prompt for better guidance
     system_prompt = (
         "You are FinChat, a knowledgeable financial advisor. Always respond in a friendly, professional manner. "
         "For greetings like 'Hi' or 'Hello', reply warmly, e.g., 'Hi! I'm FinChat, your financial advisor. What can I help you with today regarding stocks, investments, or advice?' "
-        "Provide accurate, concise advice based on data."
+        "Provide accurate, concise advice based on the provided data summary. If no data is available, suggest alternatives politely. "
+        "Use the data summary to inform your response where relevant."
     )
-    # Placeholder for generation logic (tokenize, generate, decode)
-    return summary or "Please provide a specific stock or investment query."
+    
+    # Integrate thinking if enabled (simple chain-of-thought prompt)
+    thinking_prompt = "Think step by step before responding. " if enable_thinking else ""
+    
+    # Prepare messages for the model
+    messages = [
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": f"{thinking_prompt}Query: {user_query}\nData summary: {summary if summary else 'No specific data computed; respond generally based on knowledge.'}"}
+    ]
+    
+    # Generate response using the model
+    input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
+    outputs = model.generate(input_ids, max_new_tokens=200, do_sample=True, temperature=0.7)
+    response = tokenizer.decode(outputs[0][input_ids.shape[1]:], skip_special_tokens=True)
+    
+    return response
 
 # Gradio interface setup
 demo = gr.Interface(
     fn=generate_response,
-    inputs=[gr.Textbox(lines=2, placeholder="Enter your query (e.g., 'Tesla average price between 2010 and 2020')"), gr.Checkbox(label="Enable Thinking")],
+    inputs=[gr.Textbox(lines=2, placeholder="Enter your query (e.g., 'average return for TSLA stock between 2010 and 2020')"), gr.Checkbox(label="Enable Thinking")],
     outputs="text",
     title="FinChat",
     description="Ask about stock performance, CAGR, or investments."