import os
import json
import pandas as pd
import numpy as np
from datetime import datetime, timedelta
from typing import List, Dict, Any, Optional
import warnings
warnings.filterwarnings('ignore')

# Core imports
import gradio as gr
import chromadb
from sentence_transformers import SentenceTransformer
from langchain.text_splitter import RecursiveCharacterTextSplitter
import joblib
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
import plotly.graph_objects as go
import plotly.express as px
from plotly.subplots import make_subplots
import re
import uuid
from dataclasses import dataclass
from pathlib import Path

# Set up paths for different deployment environments
CHROMA_DB_PATH = os.getenv("CHROMA_DB_PATH", "./chroma_db")
PERSIST_DIR = os.getenv("PERSIST_DIR", CHROMA_DB_PATH)
Path(PERSIST_DIR).mkdir(parents=True, exist_ok=True)

print(f"🗄️ ChromaDB will be stored at: {PERSIST_DIR}")

# Data Models
@dataclass
class StartupIdea:
    """Data model for startup ideas"""
    name: str
    description: str
    industry: str
    target_market: str
    problem_statement: str
    solution: str
    unique_value_proposition: str

@dataclass
class BusinessPlan:
    """Comprehensive business plan structure"""
    executive_summary: str
    company_description: str
    market_analysis: str
    organization_management: str
    service_product_line: str
    marketing_sales: str
    funding_request: str
    financial_projections: Dict[str, Any]

@dataclass
class Flashcard:
    """Learning flashcard structure"""
    id: str
    front: str
    back: str
    category: str
    difficulty: str
    tags: List[str]

@dataclass
class RoadmapMilestone:
    """Roadmap milestone structure"""
    id: str
    title: str
    description: str
    timeline: str
    dependencies: List[str]
    priority: str
    category: str

# RAG System Implementation
class RAGSystem:
    """Retrieval-Augmented Generation system using ChromaDB"""
    
    def __init__(self, model_name: str = "all-MiniLM-L6-v2"):
        print("🧠 Initializing RAG System...")
        try:
            self.embedding_model = SentenceTransformer(model_name)
            self.chroma_client = chromadb.PersistentClient(path=PERSIST_DIR)
            self.collection_name = "startup_knowledge"
            self.collection = None
            self.text_splitter = RecursiveCharacterTextSplitter(
                chunk_size=1000,
                chunk_overlap=200,
                length_function=len
            )
            print("✅ RAG System initialized successfully")
        except Exception as e:
            print(f"❌ Error initializing RAG System: {e}")
            raise

    def initialize_collection(self):
        """Initialize or get existing collection"""
        try:
            collections = self.chroma_client.list_collections()
            existing_collection = next((c for c in collections if c.name == self.collection_name), None)
            
            if existing_collection:
                self.collection = self.chroma_client.get_collection(self.collection_name)
                print(f"📚 Found existing collection with {self.collection.count()} documents")
            else:
                self.collection = self.chroma_client.create_collection(
                    name=self.collection_name,
                    metadata={"description": "Startup knowledge base"}
                )
                print("📚 Created new collection")
            
            return self.collection
            
        except Exception as e:
            print(f"❌ Error initializing collection: {e}")
            try:
                self.collection = self.chroma_client.create_collection(
                    name=f"{self.collection_name}_{uuid.uuid4().hex[:8]}",
                    metadata={"description": "Startup knowledge base"}
                )
                print("📚 Created fallback collection")
                return self.collection
            except Exception as e2:
                print(f"❌ Fatal error creating collection: {e2}")
                raise

    def add_documents(self, documents: List[str], metadatas: List[Dict] = None):
        """Add documents to the knowledge base"""
        if not self.collection:
            self.initialize_collection()
        
        try:
            all_chunks = []
            all_metadatas = []
            
            for i, doc in enumerate(documents):
                chunks = self.text_splitter.split_text(doc)
                all_chunks.extend(chunks)
                
                doc_metadata = metadatas[i] if metadatas and i < len(metadatas) else {}
                for chunk in chunks:
                    all_metadatas.append({
                        **doc_metadata,
                        "chunk_id": str(uuid.uuid4()),
                        "timestamp": datetime.now().isoformat()
                    })
            
            print(f"🔄 Generating embeddings for {len(all_chunks)} chunks...")
            embeddings = self.embedding_model.encode(all_chunks).tolist()
            
            ids = [str(uuid.uuid4()) for _ in all_chunks]
            self.collection.add(
                documents=all_chunks,
                embeddings=embeddings,
                metadatas=all_metadatas,
                ids=ids
            )
            
            print(f"✅ Added {len(all_chunks)} chunks to knowledge base")
            return len(all_chunks)
            
        except Exception as e:
            print(f"❌ Error adding documents: {e}")
            return 0

    def retrieve_context(self, query: str, n_results: int = 5) -> List[Dict]:
        """Retrieve relevant context for a query"""
        if not self.collection:
            self.initialize_collection()
            
        try:
            query_embedding = self.embedding_model.encode([query]).tolist()[0]
            
            results = self.collection.query(
                query_embeddings=[query_embedding],
                n_results=min(n_results, max(1, self.collection.count()))
            )
            
            contexts = []
            if results['documents'][0]:
                for i, doc in enumerate(results['documents'][0]):
                    contexts.append({
                        "content": doc,
                        "metadata": results['metadatas'][0][i] if results['metadatas'][0] else {},
                        "distance": results['distances'][0][i] if results['distances'] and results['distances'][0] else 0
                    })
            
            return contexts
            
        except Exception as e:
            print(f"❌ Error retrieving context: {e}")
            return []

    def generate_response(self, query: str, context: List[Dict]) -> str:
        """Generate response using retrieved context"""
        try:
            context_text = "\n".join([ctx["content"] for ctx in context])
            return self._generate_structured_response(query, context_text)
        except Exception as e:
            print(f"❌ Error generating response: {e}")
            return "I apologize, but I encountered an error generating a response. Please try again."

    def _generate_structured_response(self, query: str, context: str) -> str:
        """Generate structured response based on query type"""
        query_lower = query.lower()
        
        if "market research" in query_lower or "competition" in query_lower:
            return f"""**Market Analysis Framework:**

Based on startup best practices:
{context[:500]}...

**Key Recommendations:**
- Conduct thorough competitive analysis using TAM/SAM/SOM framework
- Identify unique value propositions that differentiate your solution  
- Analyze market size and growth potential with real data
"""
            
        elif "business plan" in query_lower:
            return f"""**Business Plan Development:**

Essential components:
{context[:500]}...

**Core Sections:**
- Executive Summary
- Market Analysis
- Financial Projections
"""
            
        else:
            return f"""**Strategic Guidance:**

{context[:400]}...

**Key Considerations:**
- Validate assumptions with market data
- Focus on solving genuine problems
- Build strong unit economics
"""

# Startup Knowledge Base
STARTUP_KNOWLEDGE_BASE = [
    """
IDEA VALIDATION AND MARKET RESEARCH

Before building any product, entrepreneurs must prove market demand exists. This involves:

1. Problem Identification: Identify genuine problems that specific customer segments face daily.

2. Market Analysis: Determine total addressable market (TAM) size. Use TAM/SAM/SOM framework:
   - TAM (Total Addressable Market): Total market demand
   - SAM (Serviceable Addressable Market): Portion targeted by your products  
   - SOM (Serviceable Obtainable Market): Portion you can realistically capture

3. Competitive Research: Analyze competitors' offerings, pricing, strengths, weaknesses.

4. Customer Validation: Conduct 50+ interviews to validate core assumptions.

Key metrics: CAC, LTV, market penetration rate, NPS.
""",

    """
BUSINESS PLAN DEVELOPMENT

A comprehensive business plan serves as roadmap and investor communication tool:

1. Executive Summary: Mission, product, market, competitive advantages, funding needs.

2. Company Description: Business model, legal structure, value proposition.

3. Market Analysis: Industry overview, target market, competitive landscape.

4. Organization & Management: Team, advisors, hiring plans.

5. Financial Projections: 3-5 year forecasts, cash flow, break-even analysis.

6. Funding Requirements: Capital needs, use of funds, expected ROI.
""",

    """
FUNDING AND FINANCIAL MANAGEMENT

Securing and managing finances strategically:

1. Funding Sources:
   - Bootstrapping: Personal savings
   - Angels: $25K-$100K early stage
   - VC: $1M+ for high-growth potential
   - Crowdfunding: Product launches
   - Grants: SBIR/STTR programs

2. Key Metrics:
   - Burn Rate: Monthly cash expenditure
   - Runway: Months of cash remaining
   - CAC: Total marketing cost ÷ new customers
   - LTV: Average revenue × margin × lifespan
   - LTV/CAC should be 3:1 or higher

3. Best Practices:
   - Separate business and personal finances
   - Maintain 6-12 months cash reserves
   - Track MRR, ARR, gross margins
""",

    """
LEGAL STRUCTURE AND COMPLIANCE

Choosing the right legal foundation:

1. Business Structures:
   - Sole Proprietorship: Simple, personal liability
   - LLC: Asset protection, flexible taxes
   - C-Corp: Best for VC funding, stock issuance
   - Delaware C-Corp advantages for startups

2. Essential Documents:
   - Articles of Incorporation
   - Founders' Agreement with vesting
   - Employee NDAs and IP assignments
   - Terms of service, privacy policy

3. IP Protection:
   - Trademarks: Brand names, logos
   - Patents: Unique inventions
   - Copyrights: Creative works
   - Trade Secrets: Proprietary processes

4. Compliance:
   - Federal EIN
   - Business licenses
   - Industry permits
   - Data privacy (GDPR, CCPA)
""",

    """
TEAM BUILDING AND OPERATIONS

Building the right team:

1. Founding Team:
   - Complementary skills: technical, business, domain
   - Aligned vision and values
   - Equity split reflects contribution

2. Hiring Strategy:
   - Hire for adaptability and culture fit
   - Focus on critical roles first
   - 4-year vesting with 1-year cliff
   - 0.1%-10% equity based on role

3. Key Metrics by Function:
   - Product: DAU/MAU, retention, feature adoption
   - Sales: Conversion rates, cycle length, ACV
   - Marketing: CPL, MQLs, brand awareness
   - Finance: Revenue growth, margins, working capital

4. Operational Excellence:
   - Build MVP with core features
   - Define and track KPIs
   - Create scalable processes
   - Implement feedback loops
""",

    """
BRAND DEVELOPMENT AND MARKETING

Strong branding drives growth:

1. Brand Identity:
   - Define values, personality, voice
   - Create unique selling proposition
   - Develop consistent visual identity
   - Establish market positioning

2. Digital Presence:
   - Professional website with clear CTA
   - SEO optimization
   - Social media strategy
   - Content marketing calendar

3. Acquisition Channels:
   - Content Marketing: Thought leadership
   - Social Media: Platform-specific strategies
   - SEM: Targeted Google Ads
   - Email: Drip campaigns, newsletters
   - Partnerships: Co-marketing, affiliates

4. Key Metrics:
   - Website traffic and conversion rates
   - CAC by channel
   - LTV by acquisition source
   - NPS and customer satisfaction
   - Brand awareness and consideration

5. Customer Success:
   - Feedback loops and surveys
   - Customer success programs
   - Community building
   - Referral programs
"""
]

KNOWLEDGE_METADATA = [
    {"category": "validation", "topic": "market_research", "importance": "high"},
    {"category": "planning", "topic": "business_plan", "importance": "high"},
    {"category": "finance", "topic": "funding", "importance": "high"},
    {"category": "legal", "topic": "structure", "importance": "medium"},
    {"category": "operations", "topic": "team_building", "importance": "high"},
    {"category": "marketing", "topic": "branding", "importance": "medium"},
]

# Business Plan Generator
class StartupBlueprintGenerator:
    """Main class for generating comprehensive startup blueprints"""
    
    def __init__(self, rag_system: RAGSystem):
        self.rag = rag_system
        self.templates = self._load_templates()
        self.model_data = {}

    def _load_templates(self) -> Dict[str, str]:
        """Load template structures"""
        return {
            "executive_summary": """## Executive Summary

**Company:** {company_name}  
**Industry:** {industry}  
**Mission:** {mission}

### Problem Statement
{problem_statement}

### Solution
{solution}

### Market Opportunity  
{market_opportunity}

### Financial Highlights
- Projected Revenue Year 3: {projected_revenue}
- Funding Requirement: {funding_needed}  
- Break-even Timeline: {breakeven_timeline}
""",
        }

    def generate_business_plan(self, startup_idea: StartupIdea) -> BusinessPlan:
        """Generate comprehensive business plan"""
        try:
            print(f"📊 Generating business plan for {startup_idea.name}...")
            
            exec_context = self.rag.retrieve_context(
                f"executive summary for {startup_idea.industry} startup", 
                n_results=3
            )
            
            executive_summary = self.templates["executive_summary"].format(
                company_name=startup_idea.name,
                industry=startup_idea.industry,
                mission=f"To solve {startup_idea.problem_statement} for {startup_idea.target_market}",
                problem_statement=startup_idea.problem_statement,
                solution=startup_idea.solution,
                market_opportunity=f"Significant opportunity in the {startup_idea.industry} market",
                projected_revenue="$1M - $5M",
                funding_needed="$250K - $1M",
                breakeven_timeline="18-24 months"
            )

            business_plan = BusinessPlan(
                executive_summary=executive_summary,
                company_description=f"{startup_idea.name} - {startup_idea.description}",
                market_analysis=f"The {startup_idea.industry} market presents significant opportunities.",
                organization_management="Founding team with complementary skills.",
                service_product_line=startup_idea.solution,
                marketing_sales="Multi-channel customer acquisition strategy.",
                funding_request="Seeking seed funding for product development and market expansion.",
                financial_projections={
                    "revenue_forecast": {"year_1": 100000, "year_2": 500000, "year_3": 1500000},
                    "key_metrics": {"cac": 50, "ltv": 500}
                }
            )

            print("✅ Business plan generated")
            return business_plan
            
        except Exception as e:
            print(f"❌ Error: {e}")
            return self._generate_fallback_plan(startup_idea)

    def _generate_fallback_plan(self, idea: StartupIdea) -> BusinessPlan:
        """Fallback business plan"""
        return BusinessPlan(
            executive_summary=f"**{idea.name}** addresses {idea.problem_statement}.",
            company_description=f"{idea.name} serves {idea.target_market}.",
            market_analysis=f"The {idea.industry} market has growth opportunities.",
            organization_management="Experienced founding team.",
            service_product_line=idea.solution,
            marketing_sales="Digital marketing focused strategy.",
            funding_request="Seeking seed funding.",
            financial_projections={"revenue_forecast": {"year_1": 100000}}
        )

# Flashcards Generator  
class FlashcardsGenerator:
    """Generate learning flashcards"""
    
    def __init__(self, rag_system: RAGSystem):
        self.rag = rag_system
        self.flashcards_db = []

    def generate_flashcards(self, topic: str, count: int = 10) -> List[Flashcard]:
        """Generate flashcards for topic"""
        try:
            print(f"📚 Generating {count} flashcards for {topic}...")
            
            qa_patterns = self._get_qa_patterns(topic)
            flashcards = []
            
            for pattern in qa_patterns[:count]:
                flashcard = Flashcard(
                    id=str(uuid.uuid4()),
                    front=pattern['question'],
                    back=pattern['answer'],
                    category=topic,
                    difficulty=pattern['difficulty'],
                    tags=pattern['tags']
                )
                flashcards.append(flashcard)
            
            self.flashcards_db.extend(flashcards)
            print(f"✅ Generated {len(flashcards)} flashcards")
            return flashcards
            
        except Exception as e:
            print(f"❌ Error: {e}")
            return []

    def _get_qa_patterns(self, topic: str) -> List[Dict]:
        """Get Q&A patterns"""
        patterns = {
            'SaaS': [
                {
                    'question': 'What are key SaaS metrics?',
                    'answer': 'MRR, ARR, CAC, LTV, Churn Rate, NPS',
                    'difficulty': 'Medium',
                    'tags': ['saas', 'metrics']
                },
            ],
            'Market Research': [
                {
                    'question': 'What is TAM/SAM/SOM?',
                    'answer': 'Total Addressable Market, Serviceable Addressable Market, Serviceable Obtainable Market',
                    'difficulty': 'Medium', 
                    'tags': ['market-sizing']
                },
            ]
        }
        
        default = [
            {
                'question': 'What are startup funding stages?',
                'answer': 'Pre-seed, Seed, Series A, Series B, Series C+',
                'difficulty': 'Easy',
                'tags': ['funding']
            }
        ]
        
        return patterns.get(topic, default) + default[:5]

# Roadmap Generator
class RoadmapGenerator:
    """Generate startup roadmaps"""
    
    def __init__(self, rag_system: RAGSystem):
        self.rag = rag_system
        self.roadmap_templates = self._load_templates()

    def _load_templates(self) -> Dict[str, List[Dict]]:
        """Load roadmap templates"""
        return {
            'pre_launch': [
                {
                    'phase': 'Ideation & Validation',
                    'duration': '1-2 months',
                    'milestones': [
                        'Problem identification',
                        'Market research',
                        'Customer interviews',
                        'MVP wireframes'
                    ]
                },
            ],
            'launch': [
                {
                    'phase': 'Go-to-Market',
                    'duration': '2-3 months',
                    'milestones': [
                        'Brand development',
                        'Marketing strategy',
                        'Sales process',
                        'Launch campaign'
                    ]
                },
            ],
        }

    def generate_roadmap(self, startup_idea: StartupIdea, phases: List[str] = None) -> Dict[str, Any]:
        """Generate roadmap"""
        try:
            print(f"🗺️ Generating roadmap for {startup_idea.name}...")
            
            if phases is None:
                phases = ['pre_launch', 'launch']

            roadmap = {
                'startup_name': startup_idea.name,
                'industry': startup_idea.industry,  
                'phases': [],
                'total_timeline': '6-12 months',
                'key_metrics': ['CAC', 'LTV', 'MRR']
            }

            current_month = 0
            for phase_name in phases:
                if phase_name in self.roadmap_templates:
                    for phase in self.roadmap_templates[phase_name]:
                        phase['start_month'] = current_month
                        phase['end_month'] = current_month + 2
                        current_month = phase['end_month']
                        roadmap['phases'].append(phase)

            print("✅ Roadmap generated")
            return roadmap
            
        except Exception as e:
            print(f"❌ Error: {e}")
            return self._generate_fallback(startup_idea)

    def _generate_fallback(self, idea: StartupIdea) -> Dict[str, Any]:
        """Fallback roadmap"""
        return {
            'startup_name': idea.name,
            'industry': idea.industry,
            'phases': [
                {
                    'phase': 'Planning',
                    'duration': '1-2 months',
                    'milestones': ['Research', 'Planning'],
                    'start_month': 0,
                    'end_month': 2
                }
            ],
            'total_timeline': '3-6 months',
            'key_metrics': ['Revenue', 'Customers']
        }

    def export_roadmap(self, roadmap_data: Dict[str, Any], format: str = 'markdown') -> str:
        """Export roadmap"""
        if format == 'markdown':
            md = f"# 🗺️ {roadmap_data['startup_name']} Roadmap\n\n"
            md += f"**Industry:** {roadmap_data['industry']}\n\n"
            
            for phase in roadmap_data['phases']:
                md += f"## {phase['phase']}\n"
                md += f"**Duration:** {phase['duration']}\n\n"
                md += "**Milestones:**\n"
                for milestone in phase['milestones']:
                    md += f"- {milestone}\n"
                md += "\n"
                    
            return md
        return json.dumps(roadmap_data, indent=2)

# Initialize Global Systems
print("🚀 Starting AI Startup Roadmap Generator...")

try:
    rag_system = RAGSystem()
    rag_system.initialize_collection()
    
    if rag_system.collection and rag_system.collection.count() == 0:
        print("📚 Populating knowledge base...")
        chunks_added = rag_system.add_documents(STARTUP_KNOWLEDGE_BASE, KNOWLEDGE_METADATA)
        print(f"✅ Added {chunks_added} chunks")
    else:
        count = rag_system.collection.count() if rag_system.collection else 0
        print(f"📚 Using existing knowledge base with {count} documents")
        
except Exception as e:
    print(f"❌ Error initializing RAG: {e}")
    rag_system = None

try:
    blueprint_generator = StartupBlueprintGenerator(rag_system) if rag_system else None
    flashcards_gen = FlashcardsGenerator(rag_system) if rag_system else None  
    roadmap_gen = RoadmapGenerator(rag_system) if rag_system else None
    print("✅ Generators initialized")
except Exception as e:
    print(f"❌ Error initializing generators: {e}")

# Gradio Interface Functions
def generate_startup_blueprint(name, industry, target_market, problem, solution, value_prop):
    """Main blueprint generation function"""
    
    if not all([name, industry, problem, solution]):
        return (
            "❌ **Error:** Please fill in all required fields.",
            "", "", ""
        )
    
    try:
        idea = StartupIdea(
            name=name,
            description=f"{name} - {solution}",
            industry=industry,
            target_market=target_market or f"{industry} customers",
            problem_statement=problem,
            solution=solution,
            unique_value_proposition=value_prop or "Innovative solution"
        )
        
        print(f"🚀 Processing {name}")
        
        if blueprint_generator:
            business_plan = blueprint_generator.generate_business_plan(idea)
            business_plan_text = business_plan.executive_summary
        else:
            business_plan_text = f"**{name}** addresses {problem} through {solution}."
        
        if flashcards_gen:
            flashcards = flashcards_gen.generate_flashcards(industry, 5)
            flashcards_text = "\n\n".join([
                f"**Q:** {fc.front}\n**A:** {fc.back}" 
                for fc in flashcards
            ])
        else:
            flashcards_text = "**Sample Flashcard**\n\n**Q:** What is product-market fit?\n**A:** When product satisfies strong market demand."
        
        if roadmap_gen:
            roadmap = roadmap_gen.generate_roadmap(idea)
            roadmap_text = roadmap_gen.export_roadmap(roadmap, 'markdown')
        else:
            roadmap_text = f"# Roadmap for {name}\n\n## Phase 1: Planning\n- Market research\n- Business plan"
        
        summary = f"""# 🚀 Blueprint Generated!

**Startup:** {name}  
**Industry:** {industry}  
**Target:** {target_market or f"{industry} customers"}

## 📊 Assessment: 85/100

### ✅ Strengths:
- Clear problem identification
- Well-defined solution
- Strong market positioning

### 💡 Next Steps:
1. Validate with 50+ customer interviews
2. Build MVP with core features
3. Track CAC and LTV metrics
4. Prepare for seed funding

*Generated: {datetime.now().strftime("%B %d, %Y")}*
"""
        
        print(f"✅ Blueprint complete for {name}")
        return summary, business_plan_text, flashcards_text, roadmap_text
        
    except Exception as e:
        error_msg = f"❌ **Error:** {str(e)}\n\nPlease try again."
        print(f"❌ Error: {e}")
        return error_msg, "", "", ""

def generate_flashcards_only(category):
    """Generate flashcards only"""
    try:
        if flashcards_gen:
            flashcards = flashcards_gen.generate_flashcards(category, 8)
            return "\n\n".join([
                f"**Q:** {fc.front}\n**A:** {fc.back}\n*Difficulty: {fc.difficulty}*" 
                for fc in flashcards
            ])
        else:
            return f"**{category} Flashcards**\n\n**Q:** Sample question\n**A:** Sample answer"
    except Exception as e:
        return f"❌ Error: {str(e)}"

def generate_roadmap_only(startup_name, industry_type):
    """Generate roadmap only"""
    try:
        idea = StartupIdea(
            name=startup_name or "Sample Startup",
            description="Sample",
            industry=industry_type,
            target_market="General",
            problem_statement="Problem",
            solution="Solution",
            unique_value_proposition="Value"
        )
        
        if roadmap_gen:
            roadmap = roadmap_gen.generate_roadmap(idea)
            return roadmap_gen.export_roadmap(roadmap, 'markdown')
        else:
            return f"# {startup_name} Roadmap\n\n## Planning Phase\n- Research\n- Development"
    except Exception as e:
        return f"❌ Error: {str(e)}"

# Create Gradio Interface
print("🎨 Creating interface...")

custom_css = """
.gradio-container {
    max-width: 1200px !important;
}
"""

with gr.Blocks(title="🚀 AI Startup Roadmap Generator", theme=gr.themes.Soft(), css=custom_css) as demo:
    
    gr.Markdown("""
# 🚀 AI Startup Roadmap Generator

### Transform Your Startup Ideas into Comprehensive Business Plans

**Powered by RAG Technology & ChromaDB**
    """)
    
    with gr.Tabs():
        with gr.TabItem("🏢 Complete Blueprint"):
            gr.Markdown("### 📝 Enter Startup Information")
            
            with gr.Row():
                with gr.Column():
                    startup_name = gr.Textbox(
                        label="Startup Name *",
                        placeholder="e.g., EcoTrack"
                    )
                    industry = gr.Dropdown(
                        choices=["SaaS", "E-commerce", "FinTech", "HealthTech", "EdTech", "Other"],
                        label="Industry *",
                        value="SaaS"
                    )
                    target_market = gr.Textbox(
                        label="Target Market",
                        placeholder="e.g., Small businesses",
                        lines=2
                    )
                
                with gr.Column():
                    problem_statement = gr.Textbox(
                        label="Problem Statement *",
                        placeholder="What problem do you solve?",
                        lines=3
                    )
                    solution = gr.Textbox(
                        label="Solution *", 
                        placeholder="How do you solve it?",
                        lines=3
                    )
                    value_proposition = gr.Textbox(
                        label="Unique Value Proposition",
                        placeholder="What makes you different?",
                        lines=2
                    )
            
            generate_btn = gr.Button("🚀 Generate Blueprint", variant="primary", size="lg")
            
            gr.Markdown("### 📊 Generated Blueprint")
            
            with gr.Row():
                with gr.Column():
                    summary_output = gr.Markdown(label="Summary")
                with gr.Column():
                    business_plan_output = gr.Markdown(label="Business Plan")
            
            with gr.Row():
                with gr.Column():
                    flashcards_output = gr.Markdown(label="Flashcards")
                with gr.Column():
                    roadmap_output = gr.Markdown(label="Roadmap")
            
            generate_btn.click(
                fn=generate_startup_blueprint,
                inputs=[startup_name, industry, target_market, problem_statement, solution, value_proposition],
                outputs=[summary_output, business_plan_output, flashcards_output, roadmap_output]
            )
        
        with gr.TabItem("📚 Flashcards"):
            gr.Markdown("### 📚 Learning Flashcards")
            
            flashcard_category = gr.Dropdown(
                choices=['Market Research', 'Business Planning', 'Financial Management', 'SaaS'],
                label="Category",
                value="Market Research"
            )
            flashcard_btn = gr.Button("📚 Generate", variant="primary")
            flashcard_only_output = gr.Markdown()
            
            flashcard_btn.click(
                fn=generate_flashcards_only,
                inputs=[flashcard_category],
                outputs=[flashcard_only_output]
            )
        
        with gr.TabItem("🗺️ Roadmap"):
            gr.Markdown("### 🗺️ Startup Roadmap")
            
            with gr.Row():
                roadmap_startup_name = gr.Textbox(label="Startup Name", value="My Startup")
                roadmap_industry = gr.Dropdown(
                    choices=["SaaS", "E-commerce", "FinTech"],
                    label="Industry", 
                    value="SaaS"
                )
            
            roadmap_btn = gr.Button("🗺️ Generate", variant="primary")
            roadmap_only_output = gr.Markdown()
            
            roadmap_btn.click(
                fn=generate_roadmap_only,
                inputs=[roadmap_startup_name, roadmap_industry],
                outputs=[roadmap_only_output]
            )
    
    gr.Markdown("""
---
**Disclaimer:** Educational guidance based on startup best practices. Consult professionals for specific advice.
    """)

# Launch Application
if __name__ == "__main__":
    port = int(os.getenv("PORT", 7860))
    
    print(f"""
🎉 AI Startup Roadmap Generator Ready!

🌐 Port: {port}
📊 RAG: {"✅ Active" if rag_system else "❌ Fallback"}

🚀 Launching...
""")
    
    demo.launch(
        server_name="0.0.0.0",
        server_port=port,
        share=False,
        show_error=True
    )