from omnidimension import Client

client = Client("your_api_key_here")

real_estate_agent = client.agent.create(
    name="Sarah - Premier Properties Assistant",
    welcome_message="Hello! This is Sarah from Premier Properties. I'm here to help you find your dream home or assist with any property inquiries. How can I help you today?",
    context_breakdown=[
        {
            "title": "Available Properties",
            "body": """RESIDENTIAL PROPERTIES:
- 3BR Luxury Condo: $450,000 | 2,200 sq ft | Downtown
- 4BR Family Home: $650,000 | 3,500 sq ft | Suburbs
- 2BR Starter Home: $325,000 | 1,800 sq ft | City Center

RENTAL PROPERTIES:
- 2BR Apartment: $2,200/month | 1,200 sq ft | Downtown
- 3BR Townhouse: $3,500/month | 2,000 sq ft | Suburbs
- 1BR Studio: $1,500/month | 800 sq ft | City Center

COMMERCIAL PROPERTIES:
- Office Space: $25/sq ft | 5,000 sq ft | Business District
- Retail Space: $30/sq ft | 3,000 sq ft | Shopping Center
- Warehouse: $15/sq ft | 10,000 sq ft | Industrial Zone"""
        },
        {
            "title": "Inquiry Process",
            "body": "1. Greet client professionally 2. Understand property requirements 3. Match with available listings 4. Schedule viewings if interested 5. Collect contact information 6. Provide market information"
        },
        {
            "title": "Service Areas",
            "body": "We serve the entire metropolitan area including Downtown, Suburbs, and surrounding neighborhoods. Our agents specialize in residential, commercial, and rental properties."
        }
    ],
    call_type="Incoming",
    voice={
        "provider": "eleven_labs",
        "voice_id": "EXAVITQu4vr4xnSDxMaL"
    },
    model={
        "provider": "anthropic",
        "model": "gpt-4o-mini",
        "temperature": 0.6
    }
)

agent_id = real_estate_agent["json"]["id"]
print(f"Real estate agent created with ID: {agent_id}")

import base64

def upload_property_documentation(agent_id, brochure_path):
    """Upload property brochure to knowledge base and attach to agent"""
    
    # Read and encode the PDF file
    with open(brochure_path, "rb") as file:
        file_data = base64.b64encode(file.read()).decode('utf-8')
    
    # Upload to knowledge base
    kb_response = client.knowledge_base.create(file_data, "Property_Brochure.pdf")
    file_id = kb_response["json"]["file"]["id"]
    
    # Attach to agent
    attach_response = client.knowledge_base.attach([file_id], agent_id)
    
    print(f"Property documentation uploaded successfully. File ID: {file_id}")
    return file_id

# Upload your property brochure
brochure_file_id = upload_property_documentation(agent_id, "property_brochure.pdf")

def get_real_estate_analytics(agent_id, days=7):
    """Get comprehensive analytics for real estate agent"""
    
    # Get recent call logs
    call_logs = client.call.get_call_logs(agent_id=agent_id, page_size=100)
    calls_data = call_logs.get('data', [])
    
    # Calculate metrics
    total_calls = len(calls_data)
    successful_calls = sum(1 for call in calls_data if call.get('status') == 'completed')
    average_duration = sum(call.get('duration', 0) for call in calls_data) / total_calls if total_calls > 0 else 0
    
    # Generate report
    analytics_report = {
        "period_days": days,
        "total_calls": total_calls,
        "successful_calls": successful_calls,
        "completion_rate": f"{(successful_calls/total_calls*100):.1f}%" if total_calls > 0 else "0%",
        "average_call_duration": f"{average_duration:.1f} seconds",
        "recent_calls": calls_data[:5]  # Last 5 calls
    }
    
    return analytics_report

# Get weekly performance report
weekly_report = get_real_estate_analytics(agent_id, days=7)

print("Real Estate Agent Performance Report")
print(f"Total Calls: {weekly_report['total_calls']}")
print(f"Successful Calls: {weekly_report['successful_calls']}")
print(f"Completion Rate: {weekly_report['completion_rate']}")
print(f"Average Call Duration: {weekly_report['average_call_duration']}")

def update_agent_details(agent_id, **kwargs):
    """Update agent configuration"""
    response = client.agent.update(agent_id, **kwargs)
    print(f"Agent updated successfully")
    return response

# Update welcome message for weekend hours
update_agent_details(
    agent_id,
    welcome_message="Good morning! Welcome to Premier Properties. Our weekend open houses are ready! How can I help you find your dream home?"
)

# Switch back to incoming calls
update_agent_details(
    agent_id,
    call_type="Incoming"
)

from omnidimension import Client
import base64

class RealEstateVoiceAgent:
    def __init__(self, api_key):
        self.client = Client(api_key)
        self.agent_id = None
        
    def setup_complete_real_estate_agent(self):
        """Set up a complete real estate voice agent with all features"""
        
        # Create the main agent
        agent = self.client.agent.create(
            name="Premier Properties - Voice Assistant",
            welcome_message="Hello! This is Sarah from Premier Properties. I'm here to help you find your dream home or assist with any property inquiries. How can I help you today?",
            context_breakdown=[
                {
                    "title": "Complete Property Listings",
                    "body": """
                    RESIDENTIAL PROPERTIES:
                    - 3BR Luxury Condo: $450,000 | 2,200 sq ft | Downtown | Amenities: Pool, Gym, Doorman
                    - 4BR Family Home: $650,000 | 3,500 sq ft | Suburbs | Features: Large Yard, 2-Car Garage
                    - 2BR Starter Home: $325,000 | 1,800 sq ft | City Center | Features: Renovated Kitchen, Hardwood Floors
                    - 5BR Executive Home: $850,000 | 4,200 sq ft | Gated Community | Features: Home Office, Pool
                    
                    RENTAL PROPERTIES:
                    - 2BR Apartment: $2,200/month | 1,200 sq ft | Downtown | Utilities Included
                    - 3BR Townhouse: $3,500/month | 2,000 sq ft | Suburbs | Pet-Friendly
                    - 1BR Studio: $1,500/month | 800 sq ft | City Center | Furnished Option Available
                    - 4BR House: $4,000/month | 2,800 sq ft | Suburbs | 12-month Lease
                    
                    COMMERCIAL PROPERTIES:
                    - Office Space: $25/sq ft | 5,000 sq ft | Business District | Class A Building
                    - Retail Space: $30/sq ft | 3,000 sq ft | Shopping Center | High Foot Traffic
                    - Warehouse: $15/sq ft | 10,000 sq ft | Industrial Zone | Loading Docks
                    - Restaurant Space: $35/sq ft | 2,500 sq ft | Downtown | Former Restaurant
                    """
                },
                {
                    "title": "Client Service Guidelines",
                    "body": "Always be professional and helpful. Listen carefully to client requirements. Suggest properties that match their needs. Offer virtual tours when possible. Follow up within 24 hours of initial inquiry."
                },
                {
                    "title": "Operational Details",
                    "body": "Office hours: 9 AM - 7 PM weekdays, 10 AM - 5 PM weekends. Service areas: Downtown, Suburbs, and surrounding neighborhoods. Specialties: Residential, Commercial, and Rental properties. Viewing appointments: 1-hour slots."
                }
            ],
            call_type="Incoming",
            voice={
                "provider": "eleven_labs",
                "voice_id": "EXAVITQu4vr4xnSDxMaL"
            },
            model={
                "provider": "anthropic",
                "model": "gpt-4o-mini",
                "temperature": 0.6
            }
        )
        
        self.agent_id = agent["json"]["id"]
        print(f"Real estate agent created: {self.agent_id}")
        
        return self.agent_id
    
    def get_performance_summary(self):
        """Get a quick performance summary"""
        if not self.agent_id:
            return "No agent configured"
            
        calls = self.client.call.get_call_logs(agent_id=self.agent_id, page_size=50)
        total_calls = len(calls.get('data', []))
        
        return {
            "agent_id": self.agent_id,
            "total_calls_handled": total_calls,
            "status": "Active and ready for inquiries!"
        }
    
    def upload_property_brochure(self, brochure_path):
        """Upload property brochure to knowledge base"""
        if not self.agent_id:
            print("Please create agent first")
            return None
            
        with open(brochure_path, "rb") as file:
            file_data = base64.b64encode(file.read()).decode('utf-8')
        
        kb_response = self.client.knowledge_base.create(file_data, "Property_Brochure.pdf")
        file_id = kb_response["json"]["file"]["id"]
        
        self.client.knowledge_base.attach([file_id], self.agent_id)
        print(f"Property brochure uploaded: {file_id}")
        return file_id

# Initialize and deploy real estate agent
real_estate = RealEstateVoiceAgent("your_api_key_here")
agent_id = real_estate.setup_complete_real_estate_agent()

# Upload brochure if you have a PDF
# real_estate.upload_property_brochure("property_brochure.pdf")

print("
Your real estate voice agent is now live!")
print(f"Agent ID: {agent_id}")
print("Features enabled:")
print("Property inquiry handling")
print("Viewing scheduling")  
print("Call analytics and monitoring")
print("Property matching")
print("Agent configuration updates")

# Check status
summary = real_estate.get_performance_summary()
print(f"
Current Status: {summary['status']}")