Update app.py

app.py

@@ -1,8 +1,7 @@
 import streamlit as st
-from phi.agent import Agent
-from phi.model.groq import Groq
-from phi.tools.duckduckgo import DuckDuckGo
-from phi.tools.yfinance import YFinanceTools
+import requests
+import yfinance as yf
+from groq import Groq
 import os
 
 # Streamlit App Configuration
@@ -12,52 +11,89 @@ st.set_page_config(
     layout="wide"
 )
 
-# Web Search Agent
-def create_web_search_agent():
-    return Agent(
-        name="Web Search Agent",
-        role="Search the web for information",
-        model=Groq(id="llama-3.2-3b-preview"),
-        tools=[DuckDuckGo()],
-        instructions=["Always include sources"],
-        show_tools_call=True,
-        markdown=True,
-    )
+# Initialize Groq Client
+def get_groq_client():
+    try:
+        groq_api_key = st.secrets.get("GROQ_API_KEY") or os.getenv("GROQ_API_KEY")
+        if not groq_api_key:
+            st.error("Groq API Key is missing. Please set it in Secrets or .env file.")
+            return None
+        return Groq(api_key=groq_api_key)
+    except Exception as e:
+        st.error(f"Error initializing Groq client: {e}")
+        return None
 
-# Financial Agent
-def create_financial_agent():
-    return Agent(
-        name="Finance AI Agent",
-        role="Analyze financial data and provide insights",
-        model=Groq(id="llama-3.2-3b-preview"),
-        tools=[
-            YFinanceTools(
-                stock_price=True, 
-                analyst_recommendations=True, 
-                stock_fundamentals=True,
-                company_news=True
-            )
-        ],
-        instructions=["Use tables to display the data"],
-        show_tools_call=True,
-        markdown=True,
-    )
+# Fetch Stock Information
+def get_stock_info(symbol):
+    try:
+        stock = yf.Ticker(symbol)
+        
+        # Fetch key information
+        info = stock.info
+        
+        # Fetch analyst recommendations
+        recommendations = stock.recommendations
+        
+        # Fetch recent news
+        news = stock.news[:5]  # Get last 5 news items
+        
+        return {
+            "basic_info": {
+                "Company Name": info.get('longName', 'N/A'),
+                "Sector": info.get('sector', 'N/A'),
+                "Industry": info.get('industry', 'N/A'),
+                "Market Cap": f"${info.get('marketCap', 'N/A'):,}",
+                "Current Price": f"${info.get('currentPrice', 'N/A'):.2f}"
+            },
+            "recommendations": recommendations,
+            "news": news
+        }
+    except Exception as e:
+        st.error(f"Error fetching stock information: {e}")
+        return None
 
-# Create Multi-Agent
-multi_ai_agent = Agent(
-    team=[create_web_search_agent(), create_financial_agent()],
-    instructions=[
-        "Always include sources", 
-        "Use tables to display the data"
-    ],
-    show_tools_call=True,
-    markdown=True,
-)
+# Generate AI Analysis
+def generate_ai_analysis(stock_info, query_type):
+    client = get_groq_client()
+    if not client:
+        return "Unable to generate AI analysis due to client initialization error."
+    
+    try:
+        # Prepare context for AI
+        context = f"""Stock Information:
+Company: {stock_info['basic_info'].get('Company Name', 'N/A')}
+Sector: {stock_info['basic_info'].get('Sector', 'N/A')}
+Market Cap: {stock_info['basic_info'].get('Market Cap', 'N/A')}
+Current Price: {stock_info['basic_info'].get('Current Price', 'N/A')}
+        """
+        
+        # Generate prompt based on query type
+        if query_type == "Analyst Recommendations":
+            prompt = f"{context}\n\nProvide a detailed analysis of the recent analyst recommendations for this stock."
+        elif query_type == "Latest Company News":
+            prompt = f"{context}\n\nSummarize the key points from the latest company news and their potential impact on the stock."
+        elif query_type == "Stock Fundamentals":
+            prompt = f"{context}\n\nProvide an in-depth analysis of the stock's fundamental financial health."
+        else:
+            prompt = f"{context}\n\nGenerate a comprehensive overview of the stock, including its market position, recent performance, and potential outlook."
+        
+        # Generate response using Groq
+        response = client.chat.completions.create(
+            model="llama3-70b-8192",
+            messages=[
+                {"role": "system", "content": "You are a financial analyst providing professional stock insights."},
+                {"role": "user", "content": prompt}
+            ]
+        )
+        
+        return response.choices[0].message.content
+    except Exception as e:
+        return f"Error generating AI analysis: {e}"
 
-# Streamlit App
+# Streamlit App Main Function
 def main():
     st.title("🤖 Financial Analysis AI Agent")
-    st.write("Get comprehensive financial insights using AI-powered web search and analysis!")
+    st.write("Get comprehensive financial insights using AI-powered analysis!")
 
     # Sidebar for configuration
     st.sidebar.header("🔧 Query Configuration")
@@ -73,41 +109,35 @@ def main():
     query_type = st.sidebar.selectbox(
         "Select Analysis Type",
         [
+            "Comprehensive Financial Overview",
             "Analyst Recommendations",
             "Latest Company News",
-            "Stock Fundamentals",
-            "Comprehensive Financial Overview"
+            "Stock Fundamentals"
         ]
     )
 
-    # Generate Query
-    if query_type == "Analyst Recommendations":
-        query = f"Summarize analyst recommendations for {stock_symbol}"
-    elif query_type == "Latest Company News":
-        query = f"Provide the latest news for {stock_symbol}"
-    elif query_type == "Stock Fundamentals":
-        query = f"Analyze stock fundamentals for {stock_symbol}"
-    else:
-        query = f"Provide a comprehensive financial overview for {stock_symbol}"
-
     # Submit Button
     if st.sidebar.button("Generate Analysis"):
         with st.spinner("Analyzing financial data..."):
-            # Capture the response
-            response_container = st.container()
-            with response_container:
-                try:
-                    # Stream the response
-                    full_response = ""
-                    response_placeholder = st.empty()
-                    for chunk in multi_ai_agent.respond(query, stream=True):
-                        full_response += chunk
-                        response_placeholder.markdown(full_response)
-                    
-                    # Final display
-                    st.success("Analysis Complete!")
-                except Exception as e:
-                    st.error(f"An error occurred: {e}")
+            try:
+                # Fetch Stock Information
+                stock_info = get_stock_info(stock_symbol)
+                
+                if stock_info:
+                    # Display Basic Stock Information
+                    st.subheader(f"Basic Information for {stock_symbol}")
+                    info_df = pd.DataFrame.from_dict(stock_info['basic_info'], orient='index', columns=['Value'])
+                    st.table(info_df)
+                
+                # Generate AI Analysis
+                ai_analysis = generate_ai_analysis(stock_info, query_type)
+                
+                # Display AI Analysis
+                st.subheader("AI-Powered Analysis")
+                st.write(ai_analysis)
+                
+            except Exception as e:
+                st.error(f"An error occurred: {e}")
 
     # Footer
     st.sidebar.markdown("---")