Update app.py

app.py

@@ -11,20 +11,107 @@ import plotly.graph_objects as go
 import tempfile
 import os
 from datetime import datetime
+from dotenv import load_dotenv
 
-# Configure Gemini API (replace with actual key in production)
-GEMINI_API_KEY = os.getenv("gemini_api") 
+# Load environment variables
+load_dotenv()
+
+# Configure Gemini API
+GEMINI_API_KEY = os.getenv("gemini_api")
 genai.configure(api_key=GEMINI_API_KEY)
-model = genai.GenerativeModel('gemini-pro')
-chat_model = genai.GenerativeModel('gemini-pro')
+generation_config = {
+  "temperature": 1,
+  "top_p": 0.95,
+  "top_k": 64,
+  "max_output_tokens": 8192,
+  "response_mime_type": "text/plain",
+}
+
+model = genai.GenerativeModel(
+  model_name="gemini-2.0-pro-exp-02-05",
+  generation_config=generation_config,
+)
+
+chat_model = genai.GenerativeModel('"gemini-2.0-pro-exp-02-05"')
+
+# Custom CSS styling
+CUSTOM_CSS = """
+.gradio-container {
+    max-width: 1200px !important;
+    margin: auto !important;
+    padding: 20px !important;
+    background-color: #f8f9fa !important;
+}
+
+.main-header {
+    background: linear-gradient(90deg, #2C3E50, #3498DB);
+    color: white !important;
+    padding: 20px !important;
+    border-radius: 10px !important;
+    margin-bottom: 20px !important;
+    text-align: center !important;
+}
+
+.tab-content {
+    background: white !important;
+    padding: 20px !important;
+    border-radius: 10px !important;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1) !important;
+}
+
+.action-button {
+    background: #3498DB !important;
+    color: white !important;
+    border: none !important;
+    padding: 10px 20px !important;
+    border-radius: 5px !important;
+    cursor: pointer !important;
+    transition: all 0.3s ease !important;
+}
+
+.action-button:hover {
+    background: #2980B9 !important;
+    transform: translateY(-2px) !important;
+}
 
-# Load the XGBoost model
-model_path = "optimized_xgboost_model.pkl"
-freight_model = None
-try:
-    freight_model = joblib.load(model_path)
-except:
-    print(f"Warning: Could not load freight prediction model from {model_path}")
+.status-box {
+    background: #E8F4F8 !important;
+    border-left: 4px solid #3498DB !important;
+    padding: 15px !important;
+    margin: 10px 0 !important;
+    border-radius: 0 5px 5px 0 !important;
+}
+
+.chart-container {
+    background: white !important;
+    padding: 20px !important;
+    border-radius: 10px !important;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.1) !important;
+}
+
+.chat-container {
+    height: 400px !important;
+    overflow-y: auto !important;
+    border: 1px solid #dee2e6 !important;
+    border-radius: 10px !important;
+    padding: 15px !important;
+}
+
+.file-upload {
+    border: 2px dashed #dee2e6 !important;
+    border-radius: 10px !important;
+    padding: 20px !important;
+    text-align: center !important;
+}
+
+.result-box {
+    background: #f8f9fa !important;
+    border: 1px solid #dee2e6 !important;
+    border-radius: 10px !important;
+    padding: 20px !important;
+    margin-top: 15px !important;
+}
+"""
 
 class SupplyChainState:
     def __init__(self):
@@ -35,12 +122,19 @@ class SupplyChainState:
         self.analysis_results = {}
         self.freight_predictions = []
 
-def predict_freight_cost(
-    weight, line_item_value, cost_per_kg,
-    shipment_mode, air_charter_weight, ocean_weight, truck_weight,
-    air_charter_value, ocean_value, truck_value
-):
-    if freight_model is None:
+        # Load the XGBoost model
+        self.model_path = "optimized_xgboost_model.pkl"
+        try:
+            self.freight_model = joblib.load(self.model_path)
+        except:
+            print(f"Warning: Could not load freight prediction model from {self.model_path}")
+            self.freight_model = None
+
+def predict_freight_cost(state, weight, line_item_value, cost_per_kg,
+                       shipment_mode, air_charter_weight, ocean_weight, truck_weight,
+                       air_charter_value, ocean_value, truck_value):
+    """Predict freight cost using the loaded model"""
+    if state.freight_model is None:
         return "Error: Freight prediction model not loaded"
         
     features = {
@@ -57,13 +151,13 @@ def predict_freight_cost(
     input_data = pd.DataFrame([features])
     
     try:
-        prediction = freight_model.predict(input_data)
-        return round(prediction[0], 2)
+        prediction = state.freight_model.predict(input_data)
+        return round(float(prediction[0]), 2)
     except Exception as e:
         return f"Error making prediction: {str(e)}"
 
 def process_uploaded_data(state, sales_file, supplier_file, text_data):
-    """Process uploaded files and return DataFrames"""
+    """Process uploaded files and store in state"""
     try:
         if sales_file is not None:
             state.sales_df = pd.read_csv(sales_file.name)
@@ -72,9 +166,9 @@ def process_uploaded_data(state, sales_file, supplier_file, text_data):
             state.supplier_df = pd.read_excel(supplier_file.name)
             
         state.text_data = text_data
-        return "Data processed successfully"
+        return "✅ Data processed successfully"
     except Exception as e:
-        return f'Error processing data: {str(e)}'
+        return f'❌ Error processing data: {str(e)}'
 
 def perform_demand_forecasting(state):
     """Perform demand forecasting using Gemini"""
@@ -95,11 +189,20 @@ def perform_demand_forecasting(state):
 
         response = model.generate_content(prompt)
         analysis_text = response.text
+        
+        # Create an enhanced visualization
         fig = px.line(state.sales_df, title='Historical Sales Data and Forecast')
+        fig.update_layout(
+            template='plotly_white',
+            title_x=0.5,
+            title_font_size=20,
+            showlegend=True,
+            hovermode='x'
+        )
         
-        return analysis_text, fig, "Analysis completed successfully"
+        return analysis_text, fig, "✅ Analysis completed successfully"
     except Exception as e:
-        return f"Error in demand forecasting: {str(e)}", None, "Analysis failed"
+        return f"❌ Error in demand forecasting: {str(e)}", None, "Analysis failed"
 
 def perform_risk_assessment(state):
     """Perform risk assessment using Gemini"""
@@ -123,11 +226,20 @@ def perform_risk_assessment(state):
 
         response = model.generate_content(prompt)
         analysis_text = response.text
+
+        # Create an enhanced risk visualization
         fig = px.scatter(state.supplier_df, title='Supplier Risk Assessment')
+        fig.update_layout(
+            template='plotly_white',
+            title_x=0.5,
+            title_font_size=20,
+            showlegend=True,
+            hovermode='closest'
+        )
         
-        return analysis_text, fig, "Risk assessment completed"
+        return analysis_text, fig, "✅ Risk assessment completed"
     except Exception as e:
-        return f"Error in risk assessment: {str(e)}", None, "Assessment failed"
+        return f"❌ Error in risk assessment: {str(e)}", None, "Assessment failed"
 
 def chat_with_navigator(state, message):
     """Handle chat interactions with the SupplyChainAI Navigator"""
@@ -141,7 +253,7 @@ def chat_with_navigator(state, message):
         if state.text_data:
             context += "- Additional context from text data\n"
         if state.freight_predictions:
-            context += f"- Recent freight cost predictions: {state.freight_predictions[-5:]}\n"
+            context += f"- Recent freight predictions: {state.freight_predictions[-5:]}\n"
         
         # Add analysis results
         if state.analysis_results:
@@ -181,18 +293,26 @@ def generate_pdf_report(state, analysis_options):
         styles = getSampleStyleSheet()
         story = []
         
+        # Enhanced title style
         title_style = ParagraphStyle(
             'CustomTitle',
             parent=styles['Heading1'],
             fontSize=24,
-            spaceAfter=30
+            spaceAfter=30,
+            textColor=colors.HexColor('#2C3E50')
         )
+        
+        # Add company logo if available
+        # story.append(Image("logo.png", width=100, height=50))
+        
         story.append(Paragraph("SupplyChainAI Navigator Report", title_style))
         story.append(Spacer(1, 12))
         
-        story.append(Paragraph(f"Generated on: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}", 
-                             styles["Normal"]))
-        story.append(Spacer(1, 12))
+        # Add executive summary
+        story.append(Paragraph("Executive Summary", styles['Heading2']))
+        summary_text = "This report provides a comprehensive analysis of supply chain data..."
+        story.append(Paragraph(summary_text, styles['Normal']))
+        story.append(Spacer(1, 20))
         
         # Analysis results
         for analysis_type, results in state.analysis_results.items():
@@ -213,8 +333,27 @@ def generate_pdf_report(state, analysis_options):
         if state.freight_predictions:
             story.append(Paragraph("Recent Freight Cost Predictions", styles['Heading2']))
             story.append(Spacer(1, 12))
-            for pred in state.freight_predictions[-5:]:
-                story.append(Paragraph(f"Predicted Cost: ${pred}", styles['Normal']))
+            
+            # Create a table for predictions
+            pred_data = [["Prediction #", "Cost (USD)"]]
+            for i, pred in enumerate(state.freight_predictions[-5:], 1):
+                pred_data.append([f"Prediction {i}", f"${pred:,.2f}"])
+            
+            table = Table(pred_data)
+            table.setStyle(TableStyle([
+                ('BACKGROUND', (0, 0), (-1, 0), colors.HexColor('#3498DB')),
+                ('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
+                ('ALIGN', (0, 0), (-1, -1), 'CENTER'),
+                ('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
+                ('FONTSIZE', (0, 0), (-1, 0), 14),
+                ('BOTTOMPADDING', (0, 0), (-1, 0), 12),
+                ('BACKGROUND', (0, 1), (-1, -1), colors.whitesmoke),
+                ('TEXTCOLOR', (0, 1), (-1, -1), colors.black),
+                ('FONTNAME', (0, 1), (-1, -1), 'Helvetica'),
+                ('FONTSIZE', (0, 1), (-1, -1), 12),
+                ('GRID', (0, 0), (-1, -1), 1, colors.black)
+            ]))
+            story.append(table)
             story.append(Spacer(1, 20))
         
         # Chat history
@@ -225,200 +364,271 @@ def generate_pdf_report(state, analysis_options):
                 story.append(Paragraph(f"{msg_type.title()}: {msg}", styles['Normal']))
                 story.append(Spacer(1, 6))
         
+        # Build PDF
         doc.build(story)
         return pdf_path
     except Exception as e:
+        print(f"Error generating PDF: {str(e)}")
         return None
 
 def create_interface():
-    """Create Gradio interface"""
+    """Create Gradio interface with enhanced UI"""
     state = SupplyChainState()
     
-    # Tooltip explanations
-    tooltips = {
-        "Weight (kg)": "The total weight of the shipment in kilograms (1-10,000 kg).",
-        "Line Item Value": "The total value of the line item in USD (1-1,000,000 USD).",
-        "Cost per Kilogram": "The cost incurred per kilogram for the shipment in USD (0-500 USD).",
-        "Air Charter Weight": "Weight of the shipment when using Air Charter as the mode (0-10,000 kg).",
-        "Ocean Weight": "Weight of the shipment when using Ocean as the mode (0-10,000 kg).",
-        "Truck Weight": "Weight of the shipment when using Truck as the mode (0-10,000 kg).",
-        "Air Charter Line Item Value": "Value of the shipment when using Air Charter as the mode (0-1,000,000 USD).",
-        "Ocean Line Item Value": "Value of the shipment when using Ocean as the mode (0-1,000,000 USD).",
-        "Truck Line Item Value": "Value of the shipment when using Truck as the mode (0-1,000,000 USD)."
-    }
-    
-    with gr.Blocks(title="SupplyChainAI Navigator by Aditya Ratan") as demo:
-        gr.Markdown("# SupplyChainAI Navigator")
-        
-        with gr.Tab("Data Upload"):
-            sales_data_upload = gr.File(
-                file_types=[".csv"],
-                label="Upload Sales Data (CSV)"
-            )
-            supplier_data_upload = gr.File(
-                file_types=[".xlsx", ".xls"],
-                label="Upload Supplier Data (Excel)"
-            )
-            text_input_area = gr.Textbox(
-                label="Paste Additional Context (e.g., News Articles, Market Updates)",
-                lines=5
-            )
-            upload_status = gr.Textbox(label="Upload Status")
-            upload_button = gr.Button("Process Uploaded Data")
-            
-        with gr.Tab("Analysis Selection"):
-            analysis_options = gr.CheckboxGroup(
-                choices=["Demand Forecasting", "Risk Assessment",
-                        "Inventory Optimization", "Supplier Performance Analysis",
-                        "Sustainability Analysis"],
-                label="Select Analysis Options"
-            )
-            analyze_button = gr.Button("Run Analysis")
-            
-        with gr.Tab("Results & Insights"):
-            analysis_output = gr.Textbox(label="Analysis Results")
-            plot_output = gr.Plot(label="Visualization")
-            raw_output = gr.Textbox(label="Processing Status")
-            
-        with gr.Tab("Freight Cost Prediction"):
+    with gr.Blocks(css=CUSTOM_CSS, title="SupplyChainAI Navigator") as demo:
+        # Header
+        with gr.Row(elem_classes="main-header"):
             gr.Markdown("""
-                ### Freight Cost Prediction Tool
-                Predict shipping costs based on shipment details and mode of transport.
+                # 🚢 SupplyChainAI Navigator
+                ### Intelligent Supply Chain Analysis & Optimization
+                An AI-powered platform for comprehensive supply chain analytics
             """)
-            
-            with gr.Row():
-                shipment_mode = gr.Dropdown(
-                    choices=["Air", "Ocean", "Truck"],
-                    label="Shipment Mode",
-                    info="Select the mode of shipment"
-                )
-            
-            with gr.Row():
-                weight = gr.Slider(
-                    label="Weight (kg)", minimum=1, maximum=10000, step=1, value=1000,
-                    info=tooltips["Weight (kg)"]
-                )
-                line_item_value = gr.Slider(
-                    label="Line Item Value", minimum=1, maximum=1000000, step=1, value=10000,
-                    info=tooltips["Line Item Value"]
-                )
-                cost_per_kg = gr.Slider(
-                    label="Cost per Kilogram", minimum=0, maximum=500, step=0.1, value=50,
-                    info=tooltips["Cost per Kilogram"]
+        
+        # Main Content Tabs
+        with gr.Tabs() as tabs:
+            # Data Upload Tab
+            with gr.Tab("📊 Data Upload", elem_classes="tab-content"):
+                with gr.Row():
+                    gr.Markdown("""
+                        ### Upload Your Supply Chain Data
+                        Start by uploading your data files and providing additional context.
+                    """)
+                
+                with gr.Row():
+                    with gr.Column(scale=1):
+                        sales_data_upload = gr.File(
+                            file_types=[".csv"],
+                            label="📈 Sales Data (CSV)",
+                            elem_classes="file-upload"
+                        )
+                    with gr.Column(scale=1):
+                        supplier_data_upload = gr.File(
+                            file_types=[".xlsx", ".xls"],
+                            label="🏭 Supplier Data (Excel)",
+                            elem_classes="file-upload"
+                        )
+                
+                text_input_area = gr.Textbox(
+                    label="📝 Additional Context",
+                    placeholder="Add market updates, news, or other relevant information...",
+                    lines=5
                 )
+                
+                with gr.Row():
+                    upload_status = gr.Textbox(
+                        label="Status",
+                        elem_classes="status-box"
+                    )
+                    upload_button = gr.Button(
+                        "🔄 Process Data",
+                        variant="primary",
+                        elem_classes="action-button"
+                    )
             
-            with gr.Row():
-                air_charter_weight = gr.Slider(
-                    label="Air Charter Weight", minimum=0, maximum=10000, step=1,
-                    visible=False, value=0, info=tooltips["Air Charter Weight"]
-                )
-                ocean_weight = gr.Slider(
-                    label="Ocean Weight", minimum=0, maximum=10000, step=1,
-                    visible=False, value=0, info=tooltips["Ocean Weight"]
+            # Analysis Selection Tab
+            with gr.Tab("🔍 Analysis", elem_classes="tab-content"):
+                with gr.Row():
+                    gr.Markdown("### Select Analysis Types")
+                
+                analysis_options = gr.CheckboxGroup(
+                    choices=[
+                        "📈 Demand Forecasting",
+                        "⚠️ Risk Assessment",
+                        "📦 Inventory Optimization",
+                        "🤝 Supplier Performance",
+                        "🌿 Sustainability Analysis"
+                    ],
+                    label="Choose analyses to perform"
                 )
-                truck_weight = gr.Slider(
-                    label="Truck Weight", minimum=0, maximum=10000, step=1,
-                    visible=False, value=0, info=tooltips["Truck Weight"]
+                
+                analyze_button = gr.Button(
+                    "🚀 Run Analysis",
+                    variant="primary",
+                    elem_classes="action-button"
                 )
             
-            with gr.Row():
-                air_charter_value = gr.Slider(
-                    label="Air Charter Line Item Value", minimum=0, maximum=1000000, step=1,
-                    visible=False, value=0, info=tooltips["Air Charter Line Item Value"]
-                )
-                ocean_value = gr.Slider(
-                    label="Ocean Line Item Value", minimum=0, maximum=1000000, step=1,
-                    visible=False, value=0, info=tooltips["Ocean Line Item Value"]
-                )
-                truck_value = gr.Slider(
-                    label="Truck Line Item Value", minimum=0, maximum=1000000, step=1,
-                    visible=False, value=0, info=tooltips["Truck Line Item Value"]
+            # Results Tab
+            with gr.Tab("📊 Results", elem_classes="tab-content"):
+                with gr.Row():
+                    with gr.Column(scale=2):
+                        analysis_output = gr.Textbox(
+                            label="Analysis Results",
+                            elem_classes="result-box"
+                        )
+                    with gr.Column(scale=3):
+                        plot_output = gr.Plot(
+                            label="Visualization",
+                            elem_classes="chart-container"
+                        )
+                
+                raw_output = gr.Textbox(
+                    label="Processing Status",
+                    elem_classes="status-box"
                 )
             
-            predict_button = gr.Button("Predict Freight Cost")
-            freight_result = gr.Number(label="Predicted Freight Cost (USD)")
+            # Freight Cost Prediction Tab
+            with gr.Tab("💰 Cost Prediction", elem_classes="tab-content"):
+                with gr.Row():
+                    gr.Markdown("""
+                        ### 🚢 Freight Cost Prediction
+                        Estimate shipping costs based on your parameters
+                    """)
+                
+                with gr.Row():
+                    shipment_mode = gr.Dropdown(
+                        choices=["✈️ Air", "🚢 Ocean", "🚛 Truck"],
+                        label="Transport Mode",
+                        value="✈️ Air"
+                    )
+                
+                with gr.Row():
+                    with gr.Column():
+                        weight = gr.Slider(
+                            label="📦 Weight (kg)",
+                            minimum=1,
+                            maximum=10000,
+                            step=1,
+                            value=1000
+                        )
+                    with gr.Column():
+                        line_item_value = gr.Slider(
+                            label="💵 Item Value (USD)",
+                            minimum=1,
+                            maximum=1000000,
+                            step=1,
+                            value=10000
+                        )
+                    with gr.Column():
+                        cost_per_kg = gr.Slider(
+                            label="💰 Cost per kg (USD)",
+                            minimum=0,
+                            maximum=500,
+                            step=0.1,
+                            value=50
+                        )
+                
+                # Mode-specific values
+                with gr.Row(visible=False) as air_inputs:
+                    air_charter_weight = gr.Slider(
+                        label="Air Charter Weight",
+                        minimum=0,
+                        maximum=10000,
+                        step=1,
+                        value=0
+                    )
+                    air_charter_value = gr.Slider(
+                        label="Air Charter Value",
+                        minimum=0,
+                        maximum=1000000,
+                        step=1,
+                        value=0
+                    )
+                
+                with gr.Row(visible=False) as ocean_inputs:
+                    ocean_weight = gr.Slider(
+                        label="Ocean Weight",
+                        minimum=0,
+                        maximum=10000,
+                        step=1,
+                        value=0
+                    )
+                    ocean_value = gr.Slider(
+                        label="Ocean Value",
+                        minimum=0,
+                        maximum=1000000,
+                        step=1,
+                        value=0
+                    )
+                
+                with gr.Row(visible=False) as truck_inputs:
+                    truck_weight = gr.Slider(
+                        label="Truck Weight",
+                        minimum=0,
+                        maximum=10000,
+                        step=1,
+                        value=0
+                    )
+                    truck_value = gr.Slider(
+                        label="Truck Value",
+                        minimum=0,
+                        maximum=1000000,
+                        step=1,
+                        value=0
+                    )
+                
+                with gr.Row():
+                    predict_button = gr.Button(
+                        "🔍 Calculate Cost",
+                        variant="primary",
+                        elem_classes="action-button"
+                    )
+                    freight_result = gr.Number(
+                        label="Predicted Cost (USD)",
+                        elem_classes="result-box"
+                    )
             
-        with gr.Tab("Chat"):
-            chatbot = gr.Chatbot(label="Chat with SupplyChainAI Navigator")
-            msg = gr.Textbox(label="Type your message")
-            chat_button = gr.Button("Send")
+            # Chat Tab
+            with gr.Tab("💬 Chat", elem_classes="tab-content"):
+                chatbot = gr.Chatbot(
+                    label="Chat History",
+                    elem_classes="chat-container",
+                    height=400
+                )
+                with gr.Row():
+                    msg = gr.Textbox(
+                        label="Message",
+                        placeholder="Ask about your supply chain data...",
+                        scale=4
+                    )
+                    chat_button = gr.Button(
+                        "📤 Send",
+                        variant="primary",
+                        scale=1,
+                        elem_classes="action-button"
+                    )
             
-        with gr.Tab("Report Generation"):
-            report_button = gr.Button("Generate PDF Report")
-            report_download = gr.File(label="Download PDF Report")
-
-        # Update visibility of freight prediction inputs based on shipment mode
-        def update_freight_inputs_visibility(mode):
+            # Report Tab
+            with gr.Tab("📑 Report", elem_classes="tab-content"):
+                gr.Markdown("""
+                    ### Generate Comprehensive Report
+                    Create a detailed PDF report including all analyses and insights.
+                """)
+                
+                with gr.Row():
+                    report_button = gr.Button(
+                        "📄 Generate Report",
+                        variant="primary",
+                        elem_classes="action-button"
+                    )
+                    report_download = gr.File(
+                        label="Download Report"
+                    )
+        
+        # Event Handlers
+        def update_mode_inputs(mode):
             return {
-                air_charter_weight: gr.update(visible=(mode == "Air")),
-                ocean_weight: gr.update(visible=(mode == "Ocean")),
-                truck_weight: gr.update(visible=(mode == "Truck")),
-                air_charter_value: gr.update(visible=(mode == "Air")),
-                ocean_value: gr.update(visible=(mode == "Ocean")),
-                truck_value: gr.update(visible=(mode == "Truck")),
+                air_inputs: gr.update(visible=mode=="✈️ Air"),
+                ocean_inputs: gr.update(visible=mode=="🚢 Ocean"),
+                truck_inputs: gr.update(visible=mode=="🚛 Truck")
             }
-
-        # Connect all event handlers
-        # 1. Data Upload
+        
+        # Connect all components
         upload_button.click(
             fn=lambda *args: process_uploaded_data(state, *args),
             inputs=[sales_data_upload, supplier_data_upload, text_input_area],
             outputs=[upload_status]
         )
         
-        # 2. Analysis
-        def run_analyses(analysis_choices, sales_file, supplier_file, text_data):
-            # Update state with latest data
-            process_uploaded_data(state, sales_file, supplier_file, text_data)
-            
-            # Initialize results
-            current_results = []
-            current_plots = []
-            status_messages = []
-            
-            # Run selected analyses
-            for analysis in analysis_choices:
-                if analysis == "Demand Forecasting":
-                    text, fig, status = perform_demand_forecasting(state)
-                    state.analysis_results['Demand Forecasting'] = {'text': text, 'figure': fig}
-                    current_results.append(text)
-                    current_plots.append(fig)
-                    status_messages.append(status)
-                
-                elif analysis == "Risk Assessment":
-                    text, fig, status = perform_risk_assessment(state)
-                    state.analysis_results['Risk Assessment'] = {'text': text, 'figure': fig}
-                    current_results.append(text)
-                    current_plots.append(fig)
-                    status_messages.append(status)
-            
-            # Combine results
-            combined_text = "\n\n".join(current_results) if current_results else "No analyses performed"
-            latest_plot = current_plots[-1] if current_plots else None
-            status = " | ".join(status_messages) if status_messages else "No analyses run"
-            
-            return combined_text, latest_plot, status
-
         analyze_button.click(
-            fn=run_analyses,
+            fn=lambda choices, sales, supplier, text: run_analyses(state, choices, sales, supplier, text),
             inputs=[analysis_options, sales_data_upload, supplier_data_upload, text_input_area],
             outputs=[analysis_output, plot_output, raw_output]
         )
         
-        # 3. Freight Cost Prediction
-        def predict_and_store_freight(state, *args):
-            prediction = predict_freight_cost(*args)
-            if isinstance(prediction, (int, float)):
-                state.freight_predictions.append(prediction)
-            return prediction
-
         shipment_mode.change(
-            update_freight_inputs_visibility,
+            fn=update_mode_inputs,
             inputs=[shipment_mode],
-            outputs=[
-                air_charter_weight, ocean_weight, truck_weight,
-                air_charter_value, ocean_value, truck_value
-            ]
+            outputs=[air_inputs, ocean_inputs, truck_inputs]
         )
         
         predict_button.click(
@@ -431,17 +641,15 @@ def create_interface():
             outputs=[freight_result]
         )
         
-        # 4. Chat
         chat_button.click(
             fn=lambda message: chat_with_navigator(state, message),
             inputs=[msg],
             outputs=[chatbot]
         ).then(
-            fn=lambda: "",  # Clear input after sending
+            fn=lambda: "",
             outputs=[msg]
         )
         
-        # 5. Report Generation
         report_button.click(
             fn=lambda options: generate_pdf_report(state, options),
             inputs=[analysis_options],