Update app.py

app.py

@@ -3,187 +3,165 @@ import yfinance as yf
 import pandas as pd
 from groq import Groq
 import os
-import requests
 from duckduckgo_search import DDGS
+import json
 
-# Streamlit App Configuration
-st.set_page_config(
-    page_title="Financial Analysis AI Agent",
-    page_icon="💹",
-    layout="wide"
-)
-
-# Initialize Groq Client
-def get_groq_client():
-    try:
-        # Try to get API key from Hugging Face secrets first
-        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
-
-# Fetch Stock Information
-def get_stock_info(symbol):
-    try:
-        stock = yf.Ticker(symbol)
-        
-        # Fetch key information
-        info = stock.info
-        
-        # Create a structured dictionary of key financial metrics
-        stock_data = {
-            "Company Name": info.get('longName', 'N/A'),
-            "Current Price": f"${info.get('currentPrice', 'N/A'):.2f}",
-            "Market Cap": f"${info.get('marketCap', 'N/A'):,}",
-            "PE Ratio": info.get('trailingPE', 'N/A'),
-            "Dividend Yield": f"{info.get('dividendYield', 'N/A'):.2%}",
-            "52 Week High": f"${info.get('fiftyTwoWeekHigh', 'N/A'):.2f}",
-            "52 Week Low": f"${info.get('fiftyTwoWeekLow', 'N/A'):.2f}",
-            "Sector": info.get('sector', 'N/A'),
-            "Industry": info.get('industry', 'N/A')
+class FinancialIntelligentAgent:
+    def __init__(self, api_key):
+        self.groq_client = Groq(api_key=api_key)
+        self.tools = {
+            "stock_info": self.get_stock_info,
+            "news_search": self.get_duckduckgo_news,
+            "market_sentiment": self.analyze_market_sentiment,
+            "risk_assessment": self.assess_investment_risk
         }
+
+    def get_stock_info(self, symbol):
+        """Retrieve comprehensive stock information"""
+        try:
+            stock = yf.Ticker(symbol)
+            info = stock.info
+            return {
+                "basic_info": {
+                    "Company Name": info.get('longName', 'N/A'),
+                    "Current Price": f"${info.get('currentPrice', 'N/A'):.2f}",
+                    "Market Cap": f"${info.get('marketCap', 'N/A'):,}",
+                    "Sector": info.get('sector', 'N/A'),
+                    "Industry": info.get('industry', 'N/A')
+                },
+                "financial_metrics": {
+                    "PE Ratio": info.get('trailingPE', 'N/A'),
+                    "Dividend Yield": f"{info.get('dividendYield', 'N/A'):.2%}",
+                    "52 Week Range": f"${info.get('fiftyTwoWeekLow', 'N/A')} - ${info.get('fiftyTwoWeekHigh', 'N/A')}"
+                }
+            }
+        except Exception as e:
+            return {"error": str(e)}
+
+    def get_duckduckgo_news(self, symbol, limit=5):
+        """Search and retrieve news about the stock"""
+        try:
+            with DDGS() as ddgs:
+                news_results = list(ddgs.news(f"{symbol} stock recent news", max_results=limit))
+                return [
+                    {
+                        "title": result.get('title', 'N/A'),
+                        "link": result.get('url', ''),
+                        "source": result.get('source', 'N/A')
+                    } for result in news_results
+                ]
+        except Exception as e:
+            return [{"error": str(e)}]
+
+    def analyze_market_sentiment(self, symbol, news):
+        """Analyze market sentiment based on news"""
+        try:
+            news_context = "\n".join([news['title'] for news in news])
+            response = self.groq_client.chat.completions.create(
+                model="llama3-70b-8192",
+                messages=[
+                    {"role": "system", "content": "You are a market sentiment analyst."},
+                    {"role": "user", "content": f"Analyze the market sentiment for {symbol} based on these news headlines:\n{news_context}"}
+                ]
+            )
+            return response.choices[0].message.content
+        except Exception as e:
+            return f"Sentiment analysis error: {e}"
+
+    def assess_investment_risk(self, stock_info):
+        """Perform comprehensive risk assessment"""
+        try:
+            stock_context = json.dumps(stock_info, indent=2)
+            response = self.groq_client.chat.completions.create(
+                model="llama3-70b-8192",
+                messages=[
+                    {"role": "system", "content": "You are a risk assessment expert in financial investments."},
+                    {"role": "user", "content": f"Conduct a detailed investment risk assessment based on these stock details:\n{stock_context}"}
+                ]
+            )
+            return response.choices[0].message.content
+        except Exception as e:
+            return f"Risk assessment error: {e}"
+
+    def generate_comprehensive_analysis(self, symbol):
+        """Generate a comprehensive financial analysis using multiple tools"""
+        # Autonomous tool selection and execution
+        analysis_results = {}
         
-        return stock_data
-    except Exception as e:
-        st.error(f"Error fetching stock information: {e}")
-        return None
-
-# Fetch News Using DuckDuckGo
-def get_duckduckgo_news(symbol, limit=5):
-    try:
-        with DDGS() as ddgs:
-            # Search for recent news about the stock
-            news_results = list(ddgs.news(f"{symbol} stock recent news", max_results=limit))
-            
-            # Transform results to a consistent format
-            formatted_news = [
-                {
-                    "title": result.get('title', 'N/A'),
-                    "link": result.get('url', ''),
-                    "publisher": result.get('source', 'N/A'),
-                    "source": "DuckDuckGo"
-                } for result in news_results
-            ]
-            
-            return formatted_news
-    except Exception as e:
-        st.warning(f"DuckDuckGo news search error: {e}")
-        return []
-
-# Generate AI Analysis
-def generate_ai_analysis(stock_info, news, 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
-        stock_context = "\n".join([f"{k}: {v}" for k, v in stock_info.items()])
-        
-        # Prepare news context
-        news_context = "Recent News:\n" + "\n".join([
-            f"- {news['title']} (Source: {news['publisher']})"
-            for news in news
-        ])
+        # Step 1: Gather Stock Information
+        analysis_results['stock_info'] = self.tools['stock_info'](symbol)
         
-        # Full context
-        full_context = f"{stock_context}\n\n{news_context}"
+        # Step 2: Retrieve News
+        analysis_results['news'] = self.tools['news_search'](symbol)
         
-        # Generate prompt based on query type
-        if query_type == "Analyst Recommendations":
-            prompt = f"Provide a comprehensive analysis of analyst recommendations for this stock. Consider the following details:\n{full_context}\n\nFocus on: current analyst ratings, price targets, and recent sentiment changes."
-        elif query_type == "Latest News Analysis":
-            prompt = f"Analyze the latest news and its potential impact on the stock. Consider these details:\n{full_context}\n\nProvide insights on how recent news might affect the stock's performance."
-        elif query_type == "Comprehensive Analysis":
-            prompt = f"Provide a holistic analysis of the stock, integrating financial metrics and recent news:\n{full_context}\n\nOffer a balanced perspective on investment potential."
-        else:
-            prompt = f"Generate a detailed financial and news-based analysis:\n{full_context}"
+        # Step 3: Analyze Market Sentiment
+        analysis_results['market_sentiment'] = self.tools['market_sentiment'](
+            symbol, 
+            analysis_results['news']
+        )
         
-        # Generate response using Groq
-        response = client.chat.completions.create(
-            model="llama3-70b-8192",
-            messages=[
-                {"role": "system", "content": "You are a professional financial analyst providing nuanced stock insights."},
-                {"role": "user", "content": prompt}
-            ]
+        # Step 4: Assess Investment Risk
+        analysis_results['risk_assessment'] = self.tools['risk_assessment'](
+            analysis_results['stock_info']
         )
         
-        return response.choices[0].message.content
-    except Exception as e:
-        return f"Error generating AI analysis: {e}"
+        return analysis_results
 
-# Main Streamlit App
+# Streamlit Application
 def main():
-    st.title("🚀 Advanced Financial Insight AI")
-    st.markdown("Comprehensive stock analysis with DuckDuckGo news search")
+    st.title("🤖 Agentic AI Financial Analyst")
+    st.markdown("Advanced autonomous financial intelligence platform")
 
-    # Sidebar Configuration
-    st.sidebar.header("🔍 Stock Analysis")
+    # API Key Management
+    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 required!")
+        return
+
+    # Initialize Intelligent Agent
+    agent = FinancialIntelligentAgent(groq_api_key)
+
     # Stock Symbol Input
-    stock_symbol = st.sidebar.text_input(
+    stock_symbol = st.text_input(
         "Enter Stock Symbol", 
         value="NVDA", 
-        help="Enter a valid stock ticker (e.g., AAPL, GOOGL)"
-    )
-
-    # Analysis Type Selection
-    query_type = st.sidebar.selectbox(
-        "Select Analysis Type",
-        [
-            "Comprehensive Analysis",
-            "Analyst Recommendations",
-            "Latest News Analysis"
-        ]
+        help="Enter a valid stock ticker"
     )
 
-    # Generate Analysis Button
-    if st.sidebar.button("Generate Analysis"):
-        with st.spinner("Fetching and analyzing stock data..."):
+    # Analysis Button
+    if st.button("Generate Comprehensive Analysis"):
+        with st.spinner("Autonomous analysis in progress..."):
             try:
-                # Fetch Stock Information
-                stock_info = get_stock_info(stock_symbol)
-                
-                if stock_info:
-                    # Display Stock Information
-                    st.subheader(f"Financial Snapshot: {stock_symbol}")
-                    info_df = pd.DataFrame.from_dict(stock_info, orient='index', columns=['Value'])
-                    st.table(info_df)
-                
-                # Fetch News via DuckDuckGo
-                real_time_news = get_duckduckgo_news(stock_symbol)
-                
+                # Execute Agentic Analysis
+                analysis_results = agent.generate_comprehensive_analysis(stock_symbol)
+
+                # Display Stock Information
+                st.subheader(f"📊 Stock Overview: {stock_symbol}")
+                st.json(analysis_results['stock_info'])
+
                 # Display News
-                st.subheader("📰 Latest News")
-                for news in real_time_news:
-                    st.markdown(f"**{news['title']}**")
-                    st.markdown(f"*Source: {news['publisher']}*")
-                    st.markdown(f"[Read more]({news['link']})")
+                st.subheader("📰 Recent News")
+                for news in analysis_results['news']:
+                    st.markdown(f"**{news.get('title', 'N/A')}**")
+                    st.markdown(f"[Read more]({news.get('link', '#')})")
                     st.markdown("---")
-                
-                # Generate AI Analysis
-                ai_analysis = generate_ai_analysis(stock_info, real_time_news, query_type)
-                
-                # Display AI Analysis
-                st.subheader("🤖 AI-Powered Insights")
-                st.write(ai_analysis)
-                
+
+                # Display Market Sentiment
+                st.subheader("📈 Market Sentiment Analysis")
+                st.write(analysis_results['market_sentiment'])
+
+                # Display Risk Assessment
+                st.subheader("⚖️ Investment Risk Assessment")
+                st.write(analysis_results['risk_assessment'])
+
             except Exception as e:
-                st.error(f"An error occurred: {e}")
+                st.error(f"Analysis failed: {e}")
 
-    # Disclaimer
-    st.sidebar.markdown("---")
     st.sidebar.warning(
-        "🚨 Disclaimer: This is an AI-generated analysis. "
-        "Always consult with a financial advisor before making investment decisions."
+        "🚨 Disclaimer: AI-generated insights. "
+        "Consult financial professionals for decisions."
     )
 
-# Run the Streamlit app
 if __name__ == "__main__":
     main()