Update app.py

app.py

@@ -21,9 +21,16 @@ create_spending_chart,
     create_card_performance_chart
 )
 import plotly.graph_objects as go
+import gradio as gr
+from utils.api_client import RewardPilotClient
+from utils.formatters import format_recommendation, format_analytics
+from utils.llm_explainer import get_llm_explainer
+import config
+
+# Initialize clients
+client = RewardPilotClient(config.ORCHESTRATOR_URL)
+llm = get_llm_explainer()
 
-# ===================== Initialize API client =====================
-client = RewardPilotClient()
 
 # ===================== Main Recommendation Function =====================
 def get_recommendation(
@@ -90,6 +97,154 @@ def get_recommendation(
     
     return formatted_text, comparison_table, stats
 
+
+def get_recommendation_with_ai(user_id, merchant, category, amount):
+    """Get card recommendation with LLM-powered explanation"""
+    
+    try:
+        # Get base recommendation from orchestrator
+        result = client.get_recommendation(
+            user_id=user_id,
+            merchant=merchant,
+            category=category,
+            amount=float(amount)
+        )
+        
+        if not result.get('success'):
+            return f"❌ Error: {result.get('error', 'Unknown error')}", None
+        
+        data = result['data']
+        
+        # Generate LLM explanation if enabled
+        ai_explanation = ""
+        if config.LLM_ENABLED:
+            try:
+                ai_explanation = llm.explain_recommendation(
+                    card=data['recommended_card'],
+                    rewards=data['rewards_earned'],
+                    rewards_rate=data['rewards_rate'],
+                    merchant=merchant,
+                    category=category,
+                    amount=float(amount),
+                    warnings=data.get('warnings'),
+                    annual_potential=data.get('annual_potential'),
+                    alternatives=data.get('alternatives', [])
+                )
+            except Exception as e:
+                print(f"LLM explanation failed: {e}")
+                ai_explanation = ""
+        
+        # Format output with AI explanation
+        output = f"""
+## 🎯 Recommendation for ${amount} at {merchant}
+
+### 💳 Best Card: **{data['recommended_card']}**
+
+**Rewards Earned:** ${data['rewards_earned']:.2f} ({data['rewards_rate']})
+
+"""
+        
+        # Add AI explanation if available
+        if ai_explanation:
+            output += f"""
+### 🤖 AI Insight
+
+{ai_explanation}
+
+---
+
+"""
+        
+        # Add detailed breakdown
+        output += f"""
+### 📊 Breakdown
+
+- **Category:** {category}
+- **Annual Potential:** ${data.get('annual_potential', 0):.2f}
+- **Optimization Score:** {data.get('optimization_score', 'N/A')}/100
+"""
+        
+        # Add warnings
+        if data.get('warnings'):
+            output += "\n\n### ⚠️ Warnings\n\n"
+            for warning in data['warnings']:
+                output += f"- {warning}\n"
+        
+        # Add alternatives
+        if data.get('alternatives'):
+            output += "\n\n### 🔄 Alternative Options\n\n"
+            for alt in data['alternatives'][:3]:
+                output += f"- **{alt['card']}:** ${alt['rewards']:.2f} ({alt['rate']})\n"
+        
+        # Create visualization (your existing chart code)
+        chart = create_rewards_comparison_chart(data)
+        
+        return output, chart
+        
+    except Exception as e:
+        return f"❌ Error: {str(e)}", None
+
+
+def get_analytics_with_insights(user_id):
+    """Get analytics with LLM-generated insights"""
+    
+    try:
+        # Get analytics data
+        result = client.get_user_analytics(user_id)
+        
+        if not result.get('success'):
+            return f"❌ Error: {result.get('error', 'Unknown error')}", None, None, None
+        
+        data = result['data']
+        
+        # Generate AI insights if enabled
+        ai_insights = ""
+        if config.LLM_ENABLED:
+            try:
+                ai_insights = llm.generate_spending_insights(
+                    user_id=user_id,
+                    total_spending=data['total_spending'],
+                    total_rewards=data['total_rewards'],
+                    optimization_score=data['optimization_score'],
+                    top_categories=data.get('category_breakdown', []),
+                    recommendations_count=data.get('optimized_count', 0)
+                )
+            except Exception as e:
+                print(f"AI insights generation failed: {e}")
+                ai_insights = ""
+        
+        # Format metrics
+        metrics = f"""
+## 📊 Your Rewards Analytics
+
+### Key Metrics
+
+- **💰 Total Rewards:** ${data['total_rewards']:.2f}
+- **📈 Potential Savings:** ${data['potential_savings']:.2f}/year
+- **⭐ Optimization Score:** {data['optimization_score']}/100
+- **✅ Optimized Transactions:** {data.get('optimized_count', 0)}
+"""
+        
+        # Add AI insights
+        if ai_insights:
+            metrics += f"""
+### 🤖 Personalized Insights
+
+{ai_insights}
+
+---
+"""
+        
+        # Create charts (your existing chart code)
+        spending_chart = create_spending_chart(data)
+        rewards_chart = create_rewards_distribution_chart(data)
+        optimization_chart = create_optimization_gauge(data['optimization_score'])
+        
+        return metrics, spending_chart, rewards_chart, optimization_chart
+        
+    except Exception as e:
+        return f"❌ Error: {str(e)}", None, None, None
+
 # ===================== Sample Transaction Examples =====================
 EXAMPLES = [
     ["u_alice", "Groceries", "Whole Foods", 125.50, False, "", "2025-01-15"],
@@ -193,6 +348,10 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
 ---
 """
     )
+    # LLM Status Indicator
+    llm_status = "🤖 **AI Explanations:** ✅ Enabled" if config.LLM_ENABLED else "⚠️ **AI Explanations:** Disabled (using rule-based mode)"
+    gr.Markdown(llm_status)
+    
     
     # Ensure all tabs are siblings at the same level
     with gr.Tabs():
@@ -297,25 +456,12 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                     gr.Markdown("### 🔄 Card Comparison")
                     comparison_output = gr.Markdown()
             
-            # Connect button to function
+            
             recommend_btn.click(
-                fn=get_recommendation,
-                inputs=[
-                    user_dropdown,
-                    merchant_dropdown,
-                    category_dropdown,
-                    amount_input,
-                    use_custom_mcc,
-                    custom_mcc_input,
-                    date_input
-                ],
-                outputs=[
-                    recommendation_output,
-                    comparison_output,
-                    stats_output
-                ]
+                fn=get_recommendation_with_ai,
+                inputs=[user_input, merchant_input, category_input, amount_input],
+                outputs=[recommendation_output, recommendation_chart]
             )
-            
             # Examples
             gr.Markdown("### 📝 Example Transactions")
             gr.Examples(
@@ -579,7 +725,65 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
                 analytics_status
             ]
         )
-        
+        # Tab 3: Chat (NEW!)
+        with gr.Tab("💬 Ask AI"):
+            gr.Markdown("## Chat with RewardPilot AI")
+            gr.Markdown("*Ask questions about credit cards, rewards, and your spending*")
+            
+            chatbot = gr.Chatbot(height=400, label="AI Assistant")
+            with gr.Row():
+                msg = gr.Textbox(
+                    placeholder="Ask me anything about credit cards...",
+                    label="Your Question",
+                    scale=4
+                )
+                send_btn = gr.Button("Send", variant="primary", scale=1)
+            
+            chat_user = gr.Dropdown(
+                choices=["u_alice", "u_bob", "u_charlie"],
+                label="Your Profile",
+                value="u_alice",
+                visible=True
+            )
+            
+            def respond(message, chat_history, user_id):
+                """Handle chat responses"""
+                if not message.strip():
+                    return "", chat_history
+                
+                # Get user context
+                try:
+                    analytics = client.get_user_analytics(user_id)
+                    user_context = {
+                        'cards': analytics.get('data', {}).get('cards', []),
+                        'monthly_spending': analytics.get('data', {}).get('total_spending', 0),
+                        'top_category': analytics.get('data', {}).get('top_category', 'Unknown')
+                    }
+                except:
+                    user_context = {}
+                
+                # Generate AI response
+                if config.LLM_ENABLED:
+                    bot_response = llm.chat_response(message, user_context, chat_history)
+                else:
+                    bot_response = "I'm currently in fallback mode. Please ask specific questions about your cards or transactions."
+                
+                chat_history.append((message, bot_response))
+                return "", chat_history
+            
+            msg.submit(respond, [msg, chatbot, chat_user], [msg, chatbot])
+            send_btn.click(respond, [msg, chatbot, chat_user], [msg, chatbot])
+            
+            # Example questions
+            gr.Examples(
+                examples=[
+                    ["Which card should I use at Costco?"],
+                    ["How can I maximize my grocery rewards?"],
+                    ["What's the best travel card for international trips?"],
+                    ["Am I close to any spending caps?"],
+                ],
+                inputs=[msg]
+            )
         # ========== Tab 3: About ==========
         with gr.Tab("ℹ️ About"):
             gr.Markdown(
@@ -589,6 +793,20 @@ Get AI-powered credit card recommendations that maximize your rewards based on:
 RewardPilot is an AI-powered credit card recommendation system built using the **Model Context Protocol (MCP)** architecture.
 
 ### 🏗️ Architecture
+- 🎯 **Model Context Protocol (MCP)** architecture
+- 🤖 **LLM-powered explanations** using Llama 3.2
+- 📚 **RAG (Retrieval-Augmented Generation)** for card benefits
+- 📈 **ML-based spending forecasts**
+- 📊 **Interactive visualizations**
+
+### Features
+
+- Smart card recommendations for every purchase
+- AI-generated personalized insights
+- Visual analytics dashboard
+- Conversational AI assistant
+- Real-time cap warnings
+- Multi-card comparison
 
 The system consists of multiple microservices: