import gradio as gr
import anthropic
import os
import json
import asyncio
from typing import Dict, List
from datetime import datetime
from PIL import Image
import io
import base64
from dotenv import load_dotenv
from mcpserver import MCPOrchestrator
from llamaindex_rag import LlamaIndexEnvironmentalRAG

load_dotenv() 
# Initialize Anthropic client and MCP Orchestrator
client = anthropic.Anthropic(api_key=os.environ.get("ANTHROPIC_API_KEY"))
mcp = MCPOrchestrator(api_key=os.environ.get("ANTHROPIC_API_KEY"))
llamaindex_rag = LlamaIndexEnvironmentalRAG()

# ===== AUTONOMOUS AGENT SYSTEM =====
class EcoAgent:
    """Autonomous agent with planning, reasoning, and execution phases"""
    
    def __init__(self):
        self.execution_log = []
        self.plan = []
        
    def plan_assessment(self, product_name: str) -> List[str]:
        """PHASE 1: PLANNING - Agent creates execution plan"""
        # Optimized: Return static plan to save time
        self.plan = [
            "Identify product category",
            "Analyze materials and composition",
            "Calculate lifecycle carbon footprint",
            "Assess environmental issues",
            "Find sustainable alternatives",
            "Generate recommendations"
        ]
        self.execution_log.append(f"Plan created: {len(self.plan)} steps")
        return self.plan
    
    def reason_about_product(self, product_name: str) -> str:
        """PHASE 2: REASONING - Agent reasons about product context"""
        reasoning_prompt = f"""As an environmental expert, reason about this product: {product_name}

Analyze:
1. What category does this product belong to?
2. What are the likely materials and manufacturing processes?
3. What environmental concerns are most critical?
4. What lifecycle stage has the most impact?

Provide a concise reasoning summary (3-4 sentences)."""

        try:
            message = client.messages.create(
                model="claude-sonnet-4-20250514",
                max_tokens=600,
                messages=[{"role": "user", "content": reasoning_prompt}]
            )
            
            reasoning = message.content[0].text.strip()
            self.execution_log.append(f"Reasoning completed")
            return reasoning
        except Exception as e:
            return f"Product requires environmental assessment with focus on materials and lifecycle."

# ===== RAG COMPONENT: RETRIEVAL AUGMENTED GENERATION =====
def retrieve_environmental_knowledge(product_name: str, reasoning: str) -> str:
    """RAG: Retrieve relevant environmental knowledge using LlamaIndex semantic search"""
    
    print(f"🔍 LlamaIndex searching for: {product_name}")
    
    # Use LlamaIndex for advanced semantic search
    knowledge = llamaindex_rag.retrieve_knowledge(product_name, top_k=2)
    
    return f"**LlamaIndex Retrieved Knowledge:**\n\n{knowledge}"

# ===== IMPROVED MCP INTEGRATION: VISION ANALYSIS =====
def analyze_image_with_mcp(image) -> tuple:
    """Use MCP Vision Server for deep image analysis with improved fallback"""
    if image is None:
        return "", None
    
    try:
        img_copy = image.copy()
        max_size = (1568, 1568)
        img_copy.thumbnail(max_size, Image.Resampling.LANCZOS)
        
        buffered = io.BytesIO()
        img_copy.save(buffered, format="JPEG", quality=85)
        image_base64 = base64.b64encode(buffered.getvalue()).decode()
        
        # Try MCP first
        try:
            mcp_result = mcp.call_mcp_tool(
                "vision",
                "analyze_product_image",
                image_base64=image_base64,
                query="Identify product and materials for environmental assessment"
            )
            
            if mcp_result.get("status") == "success":
                analysis = mcp_result.get("analysis", {})
                product_type = analysis.get("product_type", "")
                
                # Check if we got a valid product name (not generic placeholder)
                if product_type and product_type.lower() not in ["unknown", "unknown product", "product", "item"]:
                    return product_type, mcp_result
        except:
            pass
        
        # Always use direct Claude Vision as primary method for reliability
        message = client.messages.create(
            model="claude-sonnet-4-20250514",
            max_tokens=500,
            messages=[{
                "role": "user",
                "content": [
                    {
                        "type": "image",
                        "source": {
                            "type": "base64",
                            "media_type": "image/jpeg",
                            "data": image_base64,
                        },
                    },
                    {
                        "type": "text",
                        "text": """What is this product? Identify it clearly and specifically.

Examples of good responses:
- "wireless headphones"
- "plastic water bottle"
- "laptop computer"
- "smartphone"
- "coffee mug"
- "running shoes"
- "cotton t-shirt"

Return ONLY the product name in 2-5 words. Be specific about the actual product, not generic terms."""
                    }
                ]
            }]
        )
        
        product_name = message.content[0].text.strip().strip('"').strip("'").lower()
        
        # Create simple vision data for direct Claude response
        vision_data = {
            "status": "success",
            "analysis": {
                "product_type": product_name,
                "detection_method": "direct_vision"
            }
        }
        
        return product_name, vision_data
        
    except Exception as e:
        return f"Error: {str(e)}", None

# ===== MCP INTEGRATION: LIFECYCLE ASSESSMENT =====
def mcp_lifecycle_assessment(product_name: str, product_data: Dict) -> Dict:
    """Use MCP Reasoning Server for lifecycle analysis"""
    try:
        # MCP TOOL CALL: Lifecycle Impact Calculation
        lifecycle_result = mcp.call_mcp_tool(
            "reasoning",
            "calculate_lifecycle_impact",
            product_data=product_data
        )
        return lifecycle_result
    except Exception as e:
        return {"status": "error", "error": str(e)}

# ===== PHASE 3: EXECUTION WITH CONTEXT ENGINEERING =====
def execute_assessment(agent: EcoAgent, product_name: str, vision_data: Dict = None) -> Dict:
    """PHASE 3: EXECUTION - Agent executes assessment with RAG and MCP"""
    
    # Step 1: Retrieve knowledge (RAG)
    reasoning = agent.reason_about_product(product_name)
    rag_context = retrieve_environmental_knowledge(product_name, reasoning)
    agent.execution_log.append(f"Retrieved environmental knowledge (RAG)")
    
    # Step 2: Prepare product data
    product_data = {"name": product_name, "query": product_name}
    
    if vision_data and vision_data.get("status") == "success":
        analysis = vision_data.get("analysis", {})
        # Only add materials if they're meaningful (not generic placeholders)
        materials = analysis.get("materials", [])
        if materials and not any("material" in str(m).lower() for m in materials):
            product_data["materials"] = materials
        
        packaging = analysis.get("packaging_materials", [])
        if packaging:
            product_data["packaging"] = packaging
            
        category = analysis.get("product_category", "")
        if category:
            product_data["category"] = category
            
        agent.execution_log.append(f"Vision analysis integrated")
    
    # Step 3: MCP Lifecycle Assessment
    lifecycle_result = mcp_lifecycle_assessment(product_name, product_data)
    if lifecycle_result.get("status") == "success":
        agent.execution_log.append(f"Lifecycle assessment completed via MCP")
    else:
        agent.execution_log.append(f"MCP lifecycle assessment skipped")
    
    # Step 4: CONTEXT ENGINEERING - Comprehensive prompt with all context
    engineered_prompt = f"""You are an environmental assessment expert. Assess this product: {product_name}

**AGENT REASONING:**
{reasoning}

**RETRIEVED KNOWLEDGE (RAG):**
{rag_context}

**MCP LIFECYCLE ANALYSIS:**
{json.dumps(lifecycle_result, indent=2) if lifecycle_result.get("status") == "success" else "Pending detailed analysis"}

**VISION ANALYSIS:**
{json.dumps(vision_data.get("analysis", {}), indent=2) if vision_data else "No image data"}

Using ALL the above context, provide a comprehensive assessment in this EXACT JSON format:
{{
    "name": "{product_name}",
    "eco_score": 5.5,
    "carbon": "XX kg CO2e or XX g CO2e",
    "issues": "Main environmental concerns separated by commas",
    "alternative": "Best eco-friendly alternative with score (X.X/10) - Key benefit",
    "lifecycle_insights": "Key insights from lifecycle analysis",
    "materials_analysis": "Summary of materials and their impact"
}}

IMPORTANT:
- name MUST be: {product_name}
- eco_score: realistic number 1-10 for THIS SPECIFIC product
- alternative: Recommend ONLY NEW sustainable products (NOT second-hand, vintage, used, refurbished, or pre-owned items). Focus on eco-friendly materials, sustainable manufacturing, certifications, or innovative green technologies
- Be specific and accurate based on the context provided
- Return ONLY valid JSON, no extra text.

Examples of good alternatives:
- For shoes: "Vegan leather shoes made from recycled materials with score (8.5/10) - Zero animal products and 70% lower carbon footprint"
- For electronics: "Energy Star certified laptop with modular design with score (7.8/10) - 50% longer lifespan and easy repair"
- For clothing: "Organic cotton t-shirt with Fair Trade certification with score (8.2/10) - Pesticide-free farming and ethical production"

DO NOT recommend: second-hand, vintage, used, refurbished, pre-owned, thrift store items."""

    try:
        message = client.messages.create(
            model="claude-sonnet-4-20250514",
            max_tokens=2000,
            messages=[{"role": "user", "content": engineered_prompt}]
        )
        
        response_text = message.content[0].text.strip()
        
        if "```json" in response_text:
            response_text = response_text.split("```json")[1].split("```")[0].strip()
        elif "```" in response_text:
            response_text = response_text.split("```")[1].split("```")[0].strip()
        
        product_assessment = json.loads(response_text)
        product_assessment["name"] = product_name.title()
        
        if isinstance(product_assessment.get("eco_score"), str):
            product_assessment["eco_score"] = float(product_assessment["eco_score"])
        
        agent.execution_log.append(f"Final assessment generated")
        
        return {
            "assessment": product_assessment,
            "reasoning": reasoning,
            "rag_context": rag_context,
            "lifecycle": lifecycle_result,
            "execution_log": agent.execution_log.copy()
        }
        
    except Exception as e:
        agent.execution_log.append(f"Error: {str(e)}")
        return {
            "assessment": {
                "name": product_name.title(),
                "eco_score": 5.0,
                "carbon": "Data unavailable",
                "issues": "Assessment in progress",
                "alternative": "Consult environmental guidelines",
                "lifecycle_insights": "Analysis pending"
            },
            "execution_log": agent.execution_log.copy()
        }

def format_score(score) -> str:
    """Format eco score with emoji"""
    try:
        score_num = float(score)
    except (ValueError, TypeError):
        score_num = 5.0
    
    if score_num >= 8:
        return f"{score_num}/10 Excellent"
    elif score_num >= 6:
        return f"{score_num}/10 Good"
    elif score_num >= 4:
        return f"{score_num}/10 Moderate"
    else:
        return f"{score_num}/10 Poor"


# ===== GRADIO 6 FEATURE: Progress Tracking =====
def assess_product_agentic(image: str, progress=gr.Progress()) -> str:
    """Main assessment with Gradio 6 Progress tracking"""
    
    try:
        progress(0, desc="Initializing agent...")
        agent = EcoAgent()
        
        # Get product query
        query = ""
        source = ""
        vision_data = None
        
        if image is not None:
            progress(0.1, desc="Analyzing image...")
            query, vision_data = analyze_image_with_mcp(image)
            # Don't stop if image analysis fails, just log it
            if query and not query.startswith("Error"):
                source = f"**Detected:** {query}\n\n"
                if vision_data and vision_data.get("status") == "success":
                    analysis = vision_data.get("analysis", {})
                    materials = analysis.get("materials", [])
                    if materials and not any("material" in str(m).lower() for m in materials):
                        source += f"**Materials:** {', '.join(materials)}\n\n"
            else:
                # Image analysis failed, clear query so text input can be used
                query = ""
        
       
        
        # Only return error if BOTH image and text are missing/invalid
        if not query:
            return "**Take a photo** or type a product name to get started!"
        
        # PHASE 1: PLANNING
        progress(0.3, desc="Agent planning assessment...")
        plan = agent.plan_assessment(query)
        
        # PHASE 2: REASONING
        progress(0.5, desc="Agent reasoning...")
        
        # PHASE 3: EXECUTION
        progress(0.7, desc="Executing assessment...")
        result = execute_assessment(agent, query, vision_data)
        
        progress(0.9, desc="Formatting results...")
        product = result["assessment"]
        
        # Get score for color coding
        eco_score = float(product.get('eco_score', 5.0))
        
        # Determine score color based on value
        if eco_score < 5:
            score_color = "#ef4444"  # Red
            score_label = "Poor"
            score_bg = "#fee2e2"
        elif eco_score < 7:
            score_color = "#f59e0b"  # Amber
            score_label = "Moderate"
            score_bg = "#fef3c7"
        else:
            score_color = "#10b981"  # Green
            score_label = "Good"
            score_bg = "#d1fae5"
        
        # Format main output with styled HTML
        main_output = f"""
<div style="background: white; border-radius: 16px; padding: 2rem; box-shadow: 0 1px 3px rgba(0,0,0,0.1);">
    <div style="text-align: center; margin-bottom: 2rem;">
        <div style="display: inline-block; background: {score_bg}; padding: 1.5rem 2.5rem; border-radius: 16px; margin-bottom: 1rem;">
            <div style="font-size: 3.5rem; font-weight: 800; color: {score_color}; margin-bottom: 0.5rem;">{eco_score}/10</div>
            <div style="font-size: 1.2rem; font-weight: 600; color: {score_color}; text-transform: uppercase; letter-spacing: 0.05em;">{score_label}</div>
        </div>
        <h1 style="font-size: 2rem; font-weight: 700; color: #1e293b; margin: 1rem 0;">{product['name']}</h1>
    </div>
    
    <div style="display: grid; gap: 1.5rem;">
        <div style="background: #f8fafc; border-left: 4px solid #10b981; padding: 1.5rem; border-radius: 8px;">
            <h3 style="font-size: 1.1rem; font-weight: 600; color: #059669; margin: 0 0 0.75rem 0;">🌱 Carbon Footprint</h3>
            <p style="font-size: 1rem; color: #475569; margin: 0; line-height: 1.6;">{product.get('carbon', 'N/A')}</p>
        </div>
        
        <div style="background: #f8fafc; border-left: 4px solid #ef4444; padding: 1.5rem; border-radius: 8px;">
            <h3 style="font-size: 1.1rem; font-weight: 600; color: #dc2626; margin: 0 0 0.75rem 0;">⚠️ Environmental Issues</h3>
            <p style="font-size: 1rem; color: #475569; margin: 0; line-height: 1.6;">{product.get('issues', 'N/A')}</p>
        </div>
        
        {"<div style='background: #f8fafc; border-left: 4px solid #3b82f6; padding: 1.5rem; border-radius: 8px;'><h3 style='font-size: 1.1rem; font-weight: 600; color: #2563eb; margin: 0 0 0.75rem 0;'>🔬 Materials Analysis</h3><p style='font-size: 1rem; color: #475569; margin: 0; line-height: 1.6;'>" + product['materials_analysis'] + "</p></div>" if 'materials_analysis' in product else ""}
        
        {"<div style='background: #f8fafc; border-left: 4px solid #8b5cf6; padding: 1.5rem; border-radius: 8px;'><h3 style='font-size: 1.1rem; font-weight: 600; color: #7c3aed; margin: 0 0 0.75rem 0;'>♻️ Lifecycle Insights</h3><p style='font-size: 1rem; color: #475569; margin: 0; line-height: 1.6;'>" + product['lifecycle_insights'] + "</p></div>" if 'lifecycle_insights' in product else ""}
        
        <div style="background: linear-gradient(135deg, #10b981 0%, #059669 100%); padding: 2rem; border-radius: 12px; margin-top: 1rem;">
            <h3 style="font-size: 1.3rem; font-weight: 700; color: white; margin: 0 0 1rem 0; display: flex; align-items: center; gap: 0.5rem;">
                <span style="font-size: 1.5rem;">✨</span> Better Alternative
            </h3>
            <p style="font-size: 1.05rem; color: white; margin: 0; line-height: 1.7; font-weight: 500;">{product.get('alternative', 'N/A')}</p>
        </div>
    </div>
</div>
"""
        
        progress(1.0, desc="Complete!")
        return main_output
    
    except Exception as e:
        import traceback
        return f"**Error:**\n\n{str(e)}\n\n```\n{traceback.format_exc()}\n```"

# ===== ECO SAGE ADVISOR INSPIRED DESIGN =====
eco_sage_css = """
/* Eco Sage Advisor Inspired Design */
@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700;800;900&display=swap');

* {
    font-family: 'Inter', -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
}

:root {
    --primary: #10b981;
    --primary-dark: #059669;
    --danger: #ef4444;
    --warning: #f59e0b;
    --info: #3b82f6;
}

body {
    background: #f9fafb;
    margin: 0;
    padding: 0;
}

.gradio-container {
    max-width: 1200px !important;
    margin: 0 auto !important;
    padding: 2rem 1rem !important;
}

/* Hero Section */
.hero-section {
    text-align: center;
    padding: 3rem 1rem;
    background: rgba(255, 255, 255, 0.95);
    border-radius: 24px;
    margin-bottom: 2rem;
    box-shadow: 0 20px 25px -5px rgba(0, 0, 0, 0.1), 0 10px 10px -5px rgba(0, 0, 0, 0.04);
}

/* Blocks/Cards */
.block {
    background: rgba(255, 255, 255, 0.98) !important;
    border: none !important;
    border-radius: 20px !important;
    padding: 2rem !important;
    box-shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.1), 0 4px 6px -2px rgba(0, 0, 0, 0.05) !important;
    backdrop-filter: blur(10px);
}

/* Input Fields */
input, textarea {
    background: #ffffff !important;
    border: 2px solid #e5e7eb !important;
    border-radius: 12px !important;
    padding: 14px 18px !important;
    font-size: 16px !important;
    color: #1f2937 !important;
    transition: all 0.3s cubic-bezier(0.4, 0, 0.2, 1);
}

input:focus, textarea:focus {
    border-color: var(--primary) !important;
    box-shadow: 0 0 0 4px rgba(16, 185, 129, 0.1) !important;
    outline: none !important;
    transform: translateY(-1px);
}

input::placeholder, textarea::placeholder {
    color: #9ca3af !important;
}

/* Primary Button - Hero Style */
#assess-btn {
    background: linear-gradient(135deg, #10b981 0%, #059669 100%) !important;
    color: white !important;
    border: none !important;
    border-radius: 16px !important;
    padding: 18px 36px !important;
    font-weight: 700 !important;
    font-size: 1.15rem !important;
    letter-spacing: 0.02em;
    cursor: pointer !important;
    transition: all 0.3s cubic-bezier(0.4, 0, 0.2, 1);
    box-shadow: 0 10px 25px -5px rgba(16, 185, 129, 0.4), 0 10px 10px -5px rgba(16, 185, 129, 0.04) !important;
    text-transform: none !important;
    width: 100% !important;
}

#assess-btn:hover {
    transform: translateY(-3px) scale(1.02);
    box-shadow: 0 20px 35px -5px rgba(16, 185, 129, 0.5), 0 10px 10px -5px rgba(16, 185, 129, 0.08) !important;
    background: linear-gradient(135deg, #059669 0%, #047857 100%) !important;
}

#assess-btn:active {
    transform: translateY(-1px) scale(0.98);
}

/* Result Box */
#result-box {
    background: transparent !important;
    border: none !important;
    padding: 0 !important;
    box-shadow: none !important;
}

#result-box > div {
    background: transparent !important;
}

/* Image Upload Area - FIXED SIZE */
# .image-container {
#     border: 3px dashed #d1d5db !important;
#     border-radius: 20px !important;
#     background: linear-gradient(135deg, #f9fafb 0%, #ffffff 100%) !important;
#     transition: all 0.3s ease;
# }

.image-container:hover {
    border-color: var(--primary) !important;
    background: linear-gradient(135deg, #ecfdf5 0%, #f0fdf4 100%) !important;
    transform: scale(1.01);
}

/* Hide large upload icon */
.image-container .upload-icon {
    display: none !important;
}

/* Resize upload text and icon */
.image-container button {
    font-size: 0.95rem !important;
    padding: 0.75rem 1.5rem !important;
}

/* Make upload area more compact */
.image-container > div {
    padding: 1rem !important;
}

/* Hide the huge center icon in Gradio Image component */
.image-container svg {
    width: 40px !important;
    height: 40px !important;
    opacity: 0.5;
}

.image-container .wrap {
    min-height: 250px !important;
}

/* Labels */
label {
    color: #374151 !important;
    font-weight: 500 !important;
    font-size: 1rem !important;
    margin-bottom: 0.75rem !important;
    display: block !important;
}

/* Progress Bar */
.progress-bar {
    background: linear-gradient(90deg, #10b981 0%, #059669 100%) !important;
    border-radius: 9999px !important;
}

.progress-bar-wrap {
    background: rgba(16, 185, 129, 0.1) !important;
    border-radius: 9999px !important;
}

/* OR Divider */
.or-divider {
    text-align: center;
    margin: 1.5rem 0;
    position: relative;
}

.or-divider::before,
.or-divider::after {
    content: '';
    position: absolute;
    top: 50%;
    width: 40%;
    height: 2px;
    background: linear-gradient(to right, transparent, #d1d5db, transparent);
}

.or-divider::before {
    left: 0;
}

.or-divider::after {
    right: 0;
}

/* Toast/Info Messages */
.toast {
    background: white !important;
    border-left: 4px solid var(--primary) !important;
    border-radius: 12px !important;
    box-shadow: 0 10px 25px -5px rgba(0, 0, 0, 0.1) !important;
}

/* Scrollbar */
::-webkit-scrollbar {
    width: 10px;
}

::-webkit-scrollbar-track {
    background: #f1f5f9;
    border-radius: 10px;
}

::-webkit-scrollbar-thumb {
    background: linear-gradient(180deg, #10b981, #059669);
    border-radius: 10px;
}

::-webkit-scrollbar-thumb:hover {
    background: linear-gradient(180deg, #059669, #047857);
}

/* Mobile Responsive */
@media (max-width: 768px) {
    .gradio-container {
        padding: 1rem 0.5rem !important;
    }
    
    .hero-section {
        padding: 2rem 1rem;
    }
    
    .block {
        padding: 1.5rem !important;
    }
    
    #assess-btn {
        padding: 16px 28px !important;
        font-size: 1rem !important;
    }
}

/* Animations */
@keyframes fadeIn {
    from {
        opacity: 0;
        transform: translateY(10px);
    }
    to {
        opacity: 1;
        transform: translateY(0);
    }
}

.block {
    animation: fadeIn 0.5s ease-out;
}

/* Footer */
footer {
    background: rgba(255, 255, 255, 0.1) !important;
    backdrop-filter: blur(10px);
    border-radius: 16px;
    margin-top: 3rem;
    padding: 2rem;
}

footer p {
    color: white !important;
    text-shadow: 0 2px 4px rgba(0, 0, 0, 0.2);
}
"""

with gr.Blocks(title="Future Earth") as app:
    
    gr.HTML(f"""
        <style>
            {eco_sage_css}
        </style>
        
        <div class="hero-section">
            <!-- Logo and Title Row -->
            <div style="display: flex; align-items: center; justify-content: center; gap: 1rem; margin-bottom: 1.5rem;">
                <div style="display: flex; align-items: baseline; gap: 0.5rem;">
                    <h1 style="font-size: 2.5rem; font-weight: 800; color: #047857; margin: 0; line-height: 1;">Future Earth</h1>
                </div>
            </div>
            
            <!-- Main Heading -->
            <h2 style="font-size: 2.25rem; font-weight: 700; color: #111827; margin: 0 0 1rem 0; line-height: 1.2;">Agentic Eco Advisor</h2>
            
            <!-- Subtitle -->
            <p style="font-size: 1.125rem; color: #6b7280; margin: 0; font-weight: 400; max-width: 800px; margin-left: auto; margin-right: auto;">Analyze products instantly and discover their environmental footprint</p>
        </div>
    """)
    
    with gr.Column():
        image_input = gr.Image(
            label="Upload Product Image", 
            type="pil", 
            sources=["webcam", "upload"], 
            height=300, 
            elem_classes="image-container",
            show_label=True
        )
        
        
        assess_btn = gr.Button("🌱 Analyze Environmental Impact", elem_id="assess-btn", size="lg")
        
        result_output = gr.HTML(
            label="", 
            value="""
            <div style="background: white; border-radius: 20px; padding: 3rem; text-align: center; box-shadow: 0 10px 25px -5px rgba(0,0,0,0.1);">
                <div style="font-size: 4rem; margin-bottom: 1rem;">🌿</div>
                <h2 style="font-size: 1.5rem; font-weight: 700; color: #1e293b; margin-bottom: 1rem;">Ready to Analyze</h2>
                <p style="font-size: 1.1rem; color: #64748b; margin: 0;">Upload a product image or type a product name to get started with your environmental assessment</p>
            </div>
            """,
            elem_id="result-box"
        )
    
    gr.HTML("""
        <footer style="text-align: center;">
            <p style="font-size: 0.85rem; font-weight: 600; margin: 0; color: #1f2937 !important; text-shadow: none !important;">♻️ Powered by Advanced AI • MCP • RAG Technology</p>
            <p style="font-size: 0.85rem; margin-top: 0.75rem; opacity: 0.9; color: #374151 !important; text-shadow: none !important;">Building a sustainable future through intelligent environmental analysis</p>
            <div style="margin-top: 1.5rem; display: flex; justify-content: center; gap: 2rem; flex-wrap: wrap;">
                <span style="font-size: 0.85rem; color: #1f2937 !important;">🌱 Sustainable Products</span>
                <span style="font-size: 0.85rem; color: #1f2937 !important;">📊 Data-Driven Insights</span>
                <span style="font-size: 0.85rem; color: #1f2937 !important;">🔬 Scientific Analysis</span>
            </div>
        </footer>
    """)
    
    # Event handling
    assess_btn.click(
        fn=assess_product_agentic,
        inputs=[image_input],
        outputs=[result_output]
    ).then(
        fn=lambda: gr.Info("✅ Assessment Complete!"),
        inputs=None,
        outputs=None
    )

if __name__ == "__main__":
        app.launch()