Upload app.py

app.py

@@ -0,0 +1,1169 @@
+# -*- coding: utf-8 -*-
+"""Untitled23.ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1B696PzN1xnipZQ6zfEJqphJFVadAYh3B
+"""
+
+""""
+Complete Standalone Resume Matcher for Google Colab
+No external dependencies required - just paste and run!
+"""
+
+import gradio as gr
+import json
+import re
+from datetime import datetime
+from typing import Tuple, List, Dict, Any
+from collections import Counter
+import math
+
+class TextProfileParser:
+    """Simple text profile parser."""
+
+    def parse(self, profile_text: str) -> Dict:
+        """Parse profile text into structured data."""
+        sections = {
+            "education": [],
+            "experience": [],
+            "skills": [],
+            "projects": [],
+            "achievements": [],
+            "certificates": []
+        }
+
+        lines = profile_text.split('\n')
+        current_section = None
+
+        for line in lines:
+            line = line.strip()
+            if not line:
+                continue
+
+            # Detect section headers
+            line_lower = line.lower()
+            if any(keyword in line_lower for keyword in ['education', 'academic']):
+                current_section = 'education'
+            elif any(keyword in line_lower for keyword in ['experience', 'work', 'employment']):
+                current_section = 'experience'
+            elif any(keyword in line_lower for keyword in ['skill', 'technical', 'competenc']):
+                current_section = 'skills'
+            elif any(keyword in line_lower for keyword in ['project', 'portfolio']):
+                current_section = 'projects'
+            elif any(keyword in line_lower for keyword in ['achievement', 'award', 'honor', 'certificate']):
+                current_section = 'achievements'
+            elif current_section and line:
+                sections[current_section].append(line)
+
+        return sections
+
+class StandaloneResumeMatcherApp:
+    """Complete standalone resume matcher with no external dependencies."""
+
+    def __init__(self):
+        print("Initializing Standalone Resume Matcher for Google Colab...")
+
+        # Initialize basic components
+        self.text_profile_parser = TextProfileParser()
+
+        # Create comprehensive role database
+        self.role_database = self._create_comprehensive_role_database()
+
+        # Create skill database for better matching
+        self.skill_database = self._create_skill_database()
+
+        print("✅ Standalone application initialized successfully!")
+
+    def _create_comprehensive_role_database(self):
+        """Create a comprehensive role database with detailed information."""
+        return {
+            # Analytics Category
+            "Business Analytics": {
+                "category": "Analytics",
+                "domain": "analytics",
+                "required_skills": ["SQL", "Excel", "Python", "Tableau", "Power BI", "Statistics", "Data Analysis", "Business Intelligence", "KPI", "Dashboard", "R", "Google Analytics"],
+                "description": "Analyze business data to identify trends, patterns, and insights that drive strategic decision-making and business growth",
+                "experience_level": "Mid-level",
+                "keywords": ["analytics", "business intelligence", "dashboard", "kpi", "metrics", "reporting", "data analysis", "insights", "visualization"],
+                "responsibilities": ["Create dashboards", "Analyze KPIs", "Generate reports", "Data visualization", "Business insights", "Trend analysis"],
+                "salary_range": "$70,000 - $120,000"
+            },
+            "Data Scientist": {
+                "category": "Analytics",
+                "domain": "data_science",
+                "required_skills": ["Python", "Machine Learning", "Statistics", "SQL", "Pandas", "Scikit-learn", "TensorFlow", "PyTorch", "Jupyter", "Data Mining", "Predictive Modeling"],
+                "description": "Build predictive models and analyze complex datasets to extract actionable insights",
+                "experience_level": "Senior-level",
+                "keywords": ["machine learning", "data science", "predictive modeling", "algorithms", "statistical analysis", "deep learning"],
+                "responsibilities": ["Model development", "Data analysis", "Algorithm design", "Statistical modeling", "Research"],
+                "salary_range": "$90,000 - $160,000"
+            },
+            "Data Visualisation": {
+                "category": "Analytics",
+                "domain": "analytics",
+                "required_skills": ["Tableau", "Power BI", "D3.js", "Python", "R", "Excel", "SQL", "Data Storytelling", "Dashboard Design", "Qlik", "Looker"],
+                "description": "Create compelling visual representations of data to communicate insights effectively to stakeholders",
+                "experience_level": "Mid-level",
+                "keywords": ["visualization", "dashboard", "charts", "graphs", "storytelling", "tableau", "power bi", "design", "infographics"],
+                "responsibilities": ["Design dashboards", "Create visualizations", "Data storytelling", "User experience design", "Interactive reports"],
+                "salary_range": "$65,000 - $110,000"
+            },
+
+            # Capital Markets Category
+            "Equity Research": {
+                "category": "Capital Markets",
+                "domain": "finance",
+                "required_skills": ["Financial Modeling", "Valuation", "Excel", "Bloomberg Terminal", "Equity Analysis", "DCF", "Comparable Analysis", "Industry Research", "Financial Statements"],
+                "description": "Analyze equity securities and provide investment recommendations based on fundamental and technical analysis",
+                "experience_level": "Mid-level",
+                "keywords": ["equity", "research", "valuation", "stocks", "investment", "analysis", "recommendations", "financial modeling"],
+                "responsibilities": ["Company analysis", "Financial modeling", "Investment recommendations", "Research reports", "Market analysis"],
+                "salary_range": "$80,000 - $150,000"
+            },
+            "Investment Banking": {
+                "category": "Capital Markets",
+                "domain": "finance",
+                "required_skills": ["Financial Modeling", "Valuation", "M&A", "Excel", "PowerPoint", "Bloomberg", "Capital Markets", "Due Diligence", "Pitch Books", "LBO Modeling"],
+                "description": "Provide financial advisory services for mergers, acquisitions, capital raising, and other corporate finance transactions",
+                "experience_level": "Senior-level",
+                "keywords": ["investment banking", "m&a", "ipo", "capital markets", "advisory", "transactions", "valuation", "financing"],
+                "responsibilities": ["M&A advisory", "Capital raising", "Financial modeling", "Pitch preparation", "Due diligence"],
+                "salary_range": "$100,000 - $200,000"
+            },
+            "Risk Management": {
+                "category": "Capital Markets",
+                "domain": "finance",
+                "required_skills": ["Risk Analysis", "VaR", "Monte Carlo", "Python", "R", "Excel", "Derivatives", "Credit Risk", "Market Risk", "Operational Risk"],
+                "description": "Identify, assess, and mitigate financial risks across trading, credit, and operational activities",
+                "experience_level": "Senior-level",
+                "keywords": ["risk", "var", "credit risk", "market risk", "compliance", "derivatives", "hedging", "portfolio"],
+                "responsibilities": ["Risk assessment", "Model development", "Regulatory reporting", "Portfolio monitoring", "Stress testing"],
+                "salary_range": "$90,000 - $160,000"
+            },
+
+            # Technology Category
+            "Software Engineer": {
+                "category": "Technology",
+                "domain": "technology",
+                "required_skills": ["Python", "JavaScript", "SQL", "Git", "APIs", "Web Development", "React", "Node.js", "Database Design", "Agile", "Problem Solving"],
+                "description": "Develop and maintain software applications using modern programming languages and frameworks",
+                "experience_level": "Mid-level",
+                "keywords": ["programming", "software development", "coding", "web development", "full stack", "backend", "frontend"],
+                "responsibilities": ["Code development", "Software design", "Testing", "Debugging", "Code reviews"],
+                "salary_range": "$75,000 - $140,000"
+            },
+            "Product Manager": {
+                "category": "Technology",
+                "domain": "product",
+                "required_skills": ["Product Strategy", "Roadmapping", "User Research", "Analytics", "Agile", "A/B Testing", "Stakeholder Management", "Market Research", "Feature Prioritization"],
+                "description": "Define product strategy, roadmap, and features based on market research and user needs",
+                "experience_level": "Senior-level",
+                "keywords": ["product management", "strategy", "roadmap", "user research", "agile", "features", "analytics"],
+                "responsibilities": ["Product strategy", "Roadmap planning", "Feature definition", "User research", "Stakeholder management"],
+                "salary_range": "$90,000 - $160,000"
+            },
+            "IT Business Analyst": {
+                "category": "Technology",
+                "domain": "technology",
+                "required_skills": ["Business Analysis", "Requirements Gathering", "Process Mapping", "SQL", "Agile", "JIRA", "Documentation", "Stakeholder Management", "Testing"],
+                "description": "Bridge business and technology teams by analyzing requirements and ensuring IT solutions meet business needs",
+                "experience_level": "Mid-level",
+                "keywords": ["business analyst", "requirements", "process analysis", "agile", "documentation", "stakeholder management"],
+                "responsibilities": ["Requirements analysis", "Process documentation", "Stakeholder coordination", "Solution design", "Testing support"],
+                "salary_range": "$70,000 - $110,000"
+            },
+
+            # Marketing Category
+            "Digital Marketing": {
+                "category": "Marketing",
+                "domain": "marketing",
+                "required_skills": ["SEO", "SEM", "Google Analytics", "Social Media", "Content Marketing", "PPC", "Email Marketing", "Facebook Ads", "Google Ads", "Marketing Automation"],
+                "description": "Develop and execute digital marketing campaigns across online channels to drive brand awareness and conversions",
+                "experience_level": "Mid-level",
+                "keywords": ["digital marketing", "seo", "sem", "social media", "google ads", "facebook", "content marketing", "ppc", "email"],
+                "responsibilities": ["Campaign management", "SEO optimization", "Social media strategy", "Content creation", "Analytics"],
+                "salary_range": "$55,000 - $95,000"
+            },
+            "Market Research": {
+                "category": "Marketing",
+                "domain": "marketing",
+                "required_skills": ["Survey Design", "Statistical Analysis", "SPSS", "R", "Excel", "Focus Groups", "Data Collection", "Consumer Insights", "Competitive Analysis"],
+                "description": "Conduct market research to understand consumer behavior, market trends, and competitive landscape",
+                "experience_level": "Mid-level",
+                "keywords": ["market research", "surveys", "consumer insights", "analysis", "trends", "competitive intelligence", "focus groups"],
+                "responsibilities": ["Research design", "Data collection", "Statistical analysis", "Insights generation", "Report presentation"],
+                "salary_range": "$60,000 - $100,000"
+            },
+            "Performance Marketing": {
+                "category": "Marketing",
+                "domain": "marketing",
+                "required_skills": ["Paid Advertising", "Google Ads", "Facebook Ads", "Analytics", "Conversion Tracking", "A/B Testing", "ROI Analysis", "Attribution Modeling"],
+                "description": "Drive measurable marketing results through data-driven paid advertising and performance optimization",
+                "experience_level": "Mid-level",
+                "keywords": ["performance marketing", "paid ads", "roi", "conversion", "optimization", "attribution", "programmatic"],
+                "responsibilities": ["Campaign optimization", "Performance analysis", "A/B testing", "Budget allocation", "ROI maximization"],
+                "salary_range": "$65,000 - $110,000"
+            },
+
+            # Sales Category
+            "B2B Sales": {
+                "category": "Sales",
+                "domain": "sales",
+                "required_skills": ["B2B Sales", "CRM", "Salesforce", "Lead Generation", "Negotiation", "Account Management", "Sales Process", "Pipeline Management", "Presentation"],
+                "description": "Drive business-to-business sales through relationship building, lead generation, and strategic account management",
+                "experience_level": "Mid-level",
+                "keywords": ["b2b sales", "enterprise sales", "account management", "lead generation", "crm", "pipeline", "negotiation"],
+                "responsibilities": ["Lead generation", "Account management", "Sales presentations", "Contract negotiation", "Relationship building"],
+                "salary_range": "$60,000 - $120,000"
+            },
+            "Technology Sales": {
+                "category": "Sales",
+                "domain": "sales",
+                "required_skills": ["Technology Products", "SaaS", "Software Sales", "Technical Knowledge", "Solution Selling", "CRM", "Salesforce", "Presentation", "ROI Analysis"],
+                "description": "Sell technology products and solutions by understanding customer technical requirements and demonstrating value",
+                "experience_level": "Mid-level",
+                "keywords": ["technology sales", "saas", "software", "solution selling", "technical sales", "enterprise software"],
+                "responsibilities": ["Technical sales", "Solution design", "Product demos", "ROI analysis", "Customer consultation"],
+                "salary_range": "$70,000 - $140,000"
+            },
+
+            # Human Resources Category
+            "HR Generalist": {
+                "category": "Human Resources",
+                "domain": "hr",
+                "required_skills": ["Recruitment", "Employee Relations", "HRIS", "Training", "Compliance", "Communication", "Performance Management", "Benefits Administration"],
+                "description": "Manage various HR functions including recruitment, employee relations, and policy implementation",
+                "experience_level": "Mid-level",
+                "keywords": ["human resources", "recruitment", "employee relations", "training", "compliance", "hr", "hiring", "benefits"],
+                "responsibilities": ["Recruitment", "Employee relations", "Training coordination", "Policy implementation", "Compliance"],
+                "salary_range": "$55,000 - $85,000"
+            },
+            "Talent Acquisition": {
+                "category": "Human Resources",
+                "domain": "hr",
+                "required_skills": ["Recruiting", "Sourcing", "Interviewing", "ATS", "LinkedIn Recruiter", "Boolean Search", "Employer Branding", "Candidate Experience"],
+                "description": "Source, attract, and hire top talent through strategic recruitment and talent acquisition strategies",
+                "experience_level": "Mid-level",
+                "keywords": ["recruiting", "talent acquisition", "sourcing", "hiring", "candidates", "interviews", "ats", "linkedin"],
+                "responsibilities": ["Candidate sourcing", "Interview coordination", "Talent pipeline management", "Employer branding", "Recruitment strategy"],
+                "salary_range": "$60,000 - $95,000"
+            },
+
+            # Operations Category
+            "Customer Success": {
+                "category": "Operations",
+                "domain": "operations",
+                "required_skills": ["Customer Relationship Management", "CRM", "Account Management", "Communication", "Problem Solving", "Analytics", "Retention Strategy", "Onboarding"],
+                "description": "Ensure customer satisfaction, retention, and growth through proactive relationship management and support",
+                "experience_level": "Mid-level",
+                "keywords": ["customer success", "retention", "account management", "onboarding", "satisfaction", "growth", "relationships"],
+                "responsibilities": ["Customer onboarding", "Relationship management", "Retention strategies", "Success metrics", "Account growth"],
+                "salary_range": "$60,000 - $100,000"
+            },
+            "Supply Chain Management": {
+                "category": "Operations",
+                "domain": "operations",
+                "required_skills": ["Supply Chain", "Logistics", "Procurement", "Inventory Management", "ERP", "SAP", "Vendor Management", "Forecasting", "Cost Optimization"],
+                "description": "Optimize supply chain operations including procurement, logistics, and inventory management",
+                "experience_level": "Senior-level",
+                "keywords": ["supply chain", "logistics", "procurement", "inventory", "vendor management", "optimization"],
+                "responsibilities": ["Supply planning", "Vendor management", "Inventory optimization", "Cost reduction", "Process improvement"],
+                "salary_range": "$75,000 - $130,000"
+            },
+
+            # Strategy Category
+            "Business Consulting": {
+                "category": "Strategy",
+                "domain": "consulting",
+                "required_skills": ["Strategy", "Business Analysis", "Problem Solving", "Presentation", "Excel", "PowerPoint", "Project Management", "Stakeholder Management"],
+                "description": "Provide strategic business advice and solutions to help organizations improve performance and achieve goals",
+                "experience_level": "Senior-level",
+                "keywords": ["consulting", "strategy", "business analysis", "problem solving", "advisory", "transformation"],
+                "responsibilities": ["Strategy development", "Business analysis", "Client advisory", "Project management", "Solution implementation"],
+                "salary_range": "$80,000 - $150,000"
+            },
+            "Corporate Strategy": {
+                "category": "Strategy",
+                "domain": "strategy",
+                "required_skills": ["Strategic Planning", "Business Analysis", "Financial Modeling", "M&A", "Market Analysis", "Competitive Intelligence", "Executive Presentation"],
+                "description": "Develop and execute corporate strategy including growth initiatives, M&A, and strategic planning",
+                "experience_level": "Senior-level",
+                "keywords": ["corporate strategy", "strategic planning", "m&a", "growth", "competitive analysis", "business development"],
+                "responsibilities": ["Strategy formulation", "M&A analysis", "Strategic planning", "Competitive analysis", "Executive reporting"],
+                "salary_range": "$90,000 - $160,000"
+            },
+
+            # Finance Category
+            "Financial Analyst": {
+                "category": "Finance",
+                "domain": "finance",
+                "required_skills": ["Excel", "Financial Modeling", "SQL", "Analytics", "Accounting", "Valuation", "Financial Reporting", "Budgeting", "Forecasting"],
+                "description": "Analyze financial data and create reports to support business decision-making",
+                "experience_level": "Mid-level",
+                "keywords": ["financial analysis", "modeling", "budgeting", "forecasting", "reporting", "excel", "accounting"],
+                "responsibilities": ["Financial analysis", "Model building", "Report generation", "Budget planning", "Variance analysis"],
+                "salary_range": "$65,000 - $110,000"
+            },
+            "Corporate Finance": {
+                "category": "Finance",
+                "domain": "finance",
+                "required_skills": ["Financial Modeling", "Valuation", "M&A", "Excel", "Capital Structure", "Treasury", "Financial Planning", "Investment Analysis"],
+                "description": "Manage corporate financial strategy, capital structure, and major financial transactions",
+                "experience_level": "Senior-level",
+                "keywords": ["corporate finance", "capital structure", "treasury", "m&a", "valuation", "strategy", "financing"],
+                "responsibilities": ["Capital planning", "M&A analysis", "Treasury management", "Financial strategy", "Investor relations"],
+                "salary_range": "$85,000 - $150,000"
+            }
+        }
+
+    def _create_skill_database(self):
+        """Create a comprehensive skill database with categories."""
+        return {
+            "programming": ["Python", "Java", "JavaScript", "C++", "C#", "R", "SQL", "HTML", "CSS", "PHP", "Ruby", "Go", "Rust", "Swift", "Kotlin", "Scala", "MATLAB"],
+            "data_science": ["Machine Learning", "Statistics", "Data Analysis", "Pandas", "NumPy", "Scikit-learn", "TensorFlow", "PyTorch", "Jupyter", "Data Mining", "Predictive Modeling", "Statistical Analysis"],
+            "web_development": ["React", "Angular", "Vue.js", "Node.js", "Django", "Flask", "Spring", "Express", "Bootstrap", "jQuery", "REST APIs", "GraphQL"],
+            "databases": ["MySQL", "PostgreSQL", "MongoDB", "Redis", "Oracle", "SQL Server", "Cassandra", "DynamoDB", "NoSQL", "Database Design"],
+            "cloud": ["AWS", "Azure", "Google Cloud", "Docker", "Kubernetes", "Terraform", "Jenkins", "CI/CD", "DevOps", "Microservices"],
+            "analytics": ["Tableau", "Power BI", "Google Analytics", "Excel", "SPSS", "SAS", "Looker", "Qlik", "D3.js", "Data Visualization", "Dashboard Design"],
+            "marketing": ["SEO", "SEM", "Google Ads", "Facebook Ads", "Content Marketing", "Email Marketing", "Social Media", "PPC", "Marketing Automation", "Conversion Optimization", "A/B Testing"],
+            "design": ["Figma", "Adobe Creative Suite", "Sketch", "InVision", "Photoshop", "Illustrator", "UI/UX Design", "Prototyping", "Wireframing", "User Research"],
+            "project_management": ["Agile", "Scrum", "Kanban", "JIRA", "Trello", "Asana", "Project Planning", "Risk Management", "PMP", "Waterfall", "Stakeholder Management"],
+            "finance": ["Financial Modeling", "Valuation", "Accounting", "Budgeting", "Forecasting", "Excel", "Bloomberg", "Financial Reporting", "GAAP", "IFRS", "DCF", "LBO"],
+            "capital_markets": ["Bloomberg Terminal", "Capital IQ", "Equity Research", "Fixed Income", "Derivatives", "Trading", "Portfolio Management", "Risk Management", "VaR", "Credit Analysis"],
+            "sales": ["CRM", "Salesforce", "Lead Generation", "Account Management", "Pipeline Management", "Negotiation", "B2B Sales", "B2C Sales", "Channel Sales", "Sales Process"],
+            "hr": ["Recruitment", "Talent Acquisition", "HRIS", "Employee Relations", "Performance Management", "Benefits Administration", "Training", "Compliance", "ATS", "LinkedIn Recruiter"],
+            "operations": ["Supply Chain", "Logistics", "Process Improvement", "Quality Management", "Vendor Management", "Inventory Management", "ERP", "SAP", "Lean Six Sigma", "ITIL"],
+            "consulting": ["Strategy", "Business Analysis", "Problem Solving", "Client Management", "Change Management", "Process Optimization", "Digital Transformation", "Management Consulting"],
+            "technology": ["Software Development", "System Architecture", "Technical Leadership", "Cybersecurity", "Network Administration", "IT Support", "Database Administration", "Solution Architecture"],
+            "research": ["Market Research", "Competitive Analysis", "Survey Design", "Focus Groups", "Statistical Analysis", "Research Methodology", "Data Collection", "Consumer Insights"],
+            "soft_skills": ["Leadership", "Communication", "Problem Solving", "Team Management", "Critical Thinking", "Negotiation", "Presentation", "Analytical Thinking", "Strategic Thinking", "Relationship Building"]
+        }
+
+    def _extract_skills_from_text(self, text: str) -> List[str]:
+        """Extract skills from text using keyword matching."""
+        text_lower = text.lower()
+        found_skills = []
+
+        # Check all skill categories
+        for category, skills in self.skill_database.items():
+            for skill in skills:
+                # Check for exact match or partial match
+                skill_lower = skill.lower()
+                if skill_lower in text_lower or any(word in text_lower for word in skill_lower.split()):
+                    if skill not in found_skills:
+                        found_skills.append(skill)
+
+        return found_skills
+
+    def _calculate_text_similarity(self, text1: str, text2: str) -> float:
+        """Calculate similarity between two texts using TF-IDF-like approach."""
+        # Simple tokenization
+        def tokenize(text):
+            return re.findall(r'\b\w+\b', text.lower())
+
+        tokens1 = tokenize(text1)
+        tokens2 = tokenize(text2)
+
+        # Calculate term frequencies
+        tf1 = Counter(tokens1)
+        tf2 = Counter(tokens2)
+
+        # Get all unique terms
+        all_terms = set(tokens1 + tokens2)
+
+        # Calculate cosine similarity
+        dot_product = sum(tf1[term] * tf2[term] for term in all_terms)
+        magnitude1 = math.sqrt(sum(tf1[term]**2 for term in all_terms))
+        magnitude2 = math.sqrt(sum(tf2[term]**2 for term in all_terms))
+
+        if magnitude1 == 0 or magnitude2 == 0:
+            return 0.0
+
+        return dot_product / (magnitude1 * magnitude2)
+
+    def _classify_domain(self, text: str) -> Tuple[str, float]:
+        """Simple domain classification based on keywords."""
+        domain_keywords = {
+            "analytics": ["analytics", "data analysis", "business intelligence", "dashboard", "visualization", "tableau", "power bi", "insights"],
+            "finance": ["financial", "accounting", "budget", "investment", "revenue", "profit", "banking", "capital markets", "equity", "valuation"],
+            "technology": ["programming", "software", "development", "coding", "web", "api", "database", "it", "technical", "system"],
+            "marketing": ["marketing", "seo", "social media", "advertising", "campaign", "brand", "digital marketing", "content"],
+            "hr": ["human resources", "recruitment", "hiring", "employee", "training", "hr", "talent acquisition", "benefits"],
+            "sales": ["sales", "revenue", "customer", "client", "negotiation", "crm", "b2b", "b2c", "channel"],
+            "operations": ["operations", "process", "supply chain", "logistics", "quality", "service", "customer success"],
+            "consulting": ["consulting", "strategy", "advisory", "business", "transformation", "research"],
+            "product": ["product", "roadmap", "user", "feature", "requirements", "product management"],
+            "data_science": ["machine learning", "data science", "predictive modeling", "algorithms", "statistical analysis"]
+        }
+
+        text_lower = text.lower()
+        domain_scores = {}
+
+        for domain, keywords in domain_keywords.items():
+            score = sum(1 for keyword in keywords if keyword in text_lower)
+            if score > 0:
+                domain_scores[domain] = score / len(keywords)
+
+        if domain_scores:
+            best_domain = max(domain_scores, key=domain_scores.get)
+            confidence = domain_scores[best_domain]
+            return best_domain, confidence
+
+        return "technology", 0.1  # Default
+
+    def enhanced_profile_analysis(self, profile_text: str) -> Tuple[str, str, str]:
+        """Enhanced profile analysis using standalone algorithms."""
+        if not profile_text.strip():
+            return "Please enter a profile text.", "", ""
+
+        try:
+            # 1. Basic profile parsing
+            parsed_profile = self.text_profile_parser.parse(profile_text)
+
+            # 2. Extract skills from profile
+            profile_skills = self._extract_skills_from_text(profile_text)
+
+            # 3. Domain classification
+            domain, domain_conf = self._classify_domain(profile_text)
+
+            # 4. Role matching
+            role_matches = self._find_role_matches(profile_text, profile_skills)
+
+            # 5. Get best role prediction
+            if role_matches:
+                predicted_role = role_matches[0]["role"]
+                predicted_category = role_matches[0]["category"]
+                predicted_domain = role_matches[0]["domain"]
+                confidence = role_matches[0]["similarity_score"]
+            else:
+                predicted_role = "Software Engineer"
+                predicted_category = "Technology"
+                predicted_domain = "technology"
+                confidence = 0.1
+
+            # 6. Skill gap analysis
+            gap_analysis = self._analyze_skill_gaps(profile_text, profile_skills, predicted_role)
+
+            # Prepare results
+            role_analysis = {
+                "predicted_role": predicted_role,
+                "predicted_category": predicted_category,
+                "predicted_domain": predicted_domain,
+                "confidence_scores": {"overall": confidence, "domain": domain_conf},
+                "top_role_matches": [
+                    {
+                        "role": match["role"],
+                        "category": match["category"],
+                        "similarity": f"{match['similarity_score']:.2%}",
+                        "confidence": f"{match['confidence']:.2%}",
+                        "matched_skills": match["matched_skills"],
+                        "reasoning": match["reasoning"]
+                    }
+                    for match in role_matches[:5]
+                ],
+                "domain_analysis": {
+                    "detected_domain": domain,
+                    "confidence": f"{domain_conf:.2%}",
+                    "profile_skills": profile_skills[:15]  # Top 15 skills
+                },
+                "profile_sections": {
+                    "education_count": len(parsed_profile.get("education", [])),
+                    "experience_count": len(parsed_profile.get("experience", [])),
+                    "projects_count": len(parsed_profile.get("projects", [])),
+                    "achievements_count": len(parsed_profile.get("achievements", [])),
+                    "certificates_count": len(parsed_profile.get("certificates", []))
+                },
+                "system_status": {
+                    "mode": "Google Colab Standalone Mode",
+                    "dependencies": "Zero external dependencies"
+                }
+            }
+
+            # Career recommendations HTML
+            career_recommendations = self._generate_career_recommendations_html(
+                predicted_role, predicted_category, predicted_domain, role_matches, gap_analysis
+            )
+
+            return (
+                json.dumps(role_analysis, indent=2),
+                json.dumps(gap_analysis, indent=2),
+                career_recommendations
+            )
+
+        except Exception as e:
+            error_msg = f"Error in profile analysis: {str(e)}"
+            return error_msg, "", ""
+
+    def _find_role_matches(self, profile_text: str, profile_skills: List[str]) -> List[Dict]:
+        """Find role matches using multiple scoring methods."""
+        matches = []
+
+        for role, data in self.role_database.items():
+            # 1. Skill-based scoring
+            matched_skills = []
+            for skill in data["required_skills"]:
+                if skill in profile_skills:
+                    matched_skills.append(skill)
+
+            skill_score = len(matched_skills) / len(data["required_skills"]) if data["required_skills"] else 0
+
+            # 2. Keyword-based scoring
+            keyword_score = 0
+            for keyword in data["keywords"]:
+                if keyword.lower() in profile_text.lower():
+                    keyword_score += 1
+            keyword_score = keyword_score / len(data["keywords"]) if data["keywords"] else 0
+
+            # 3. Text similarity scoring
+            role_text = f"{data['description']} {' '.join(data['required_skills'])} {' '.join(data['keywords'])}"
+            text_similarity = self._calculate_text_similarity(profile_text, role_text)
+
+            # 4. Combined scoring
+            combined_score = (skill_score * 0.4) + (keyword_score * 0.3) + (text_similarity * 0.3)
+
+            # 5. Confidence calculation
+            confidence = min(combined_score + (len(matched_skills) * 0.05), 1.0)
+
+            # 6. Reasoning
+            reasoning = f"Skills: {len(matched_skills)}/{len(data['required_skills'])}, Keywords: {int(keyword_score * len(data['keywords']))}/{len(data['keywords'])}, Text similarity: {text_similarity:.2%}"
+
+            matches.append({
+                "role": role,
+                "category": data["category"],
+                "domain": data["domain"],
+                "similarity_score": combined_score,
+                "confidence": confidence,
+                "matched_skills": matched_skills,
+                "reasoning": reasoning,
+                "salary_range": data.get("salary_range", "Not specified")
+            })
+
+        # Sort by combined score
+        matches.sort(key=lambda x: x["similarity_score"], reverse=True)
+        return matches
+
+    def _analyze_skill_gaps(self, profile_text: str, profile_skills: List[str], target_role: str) -> Dict:
+        """Analyze skill gaps for the target role."""
+        if target_role not in self.role_database:
+            return {"error": f"Role '{target_role}' not found"}
+
+        role_data = self.role_database[target_role]
+        required_skills = set(role_data["required_skills"])
+        current_skills = set(profile_skills)
+
+        matching_skills = list(required_skills & current_skills)
+        missing_skills = list(required_skills - current_skills)
+
+        # Generate recommendations
+        recommendations = []
+        skill_learning_map = {
+            "python": "Complete Python programming courses on Coursera or edX",
+            "sql": "Practice SQL queries on HackerRank or LeetCode",
+            "tableau": "Get Tableau certification through official Tableau training",
+            "power bi": "Complete Microsoft Power BI certification path",
+            "machine learning": "Take Andrew Ng's Machine Learning course on Coursera",
+            "aws": "Pursue AWS certification starting with Cloud Practitioner",
+            "javascript": "Complete JavaScript fundamentals on freeCodeCamp",
+            "react": "Build projects using React through official React tutorial",
+            "excel": "Complete advanced Excel courses focusing on data analysis",
+            "agile": "Consider Scrum Master or Product Owner certification",
+            "google analytics": "Complete Google Analytics certification",
+            "seo": "Take SEO courses on Moz Academy or SEMrush",
+            "financial modeling": "Complete financial modeling courses on Wall Street Prep",
+            "bloomberg terminal": "Get Bloomberg Market Concepts (BMC) certification",
+            "salesforce": "Pursue Salesforce Administrator certification",
+            "crm": "Learn CRM best practices through HubSpot Academy"
+        }
+
+        for skill in missing_skills[:8]:  # Top 8 missing skills
+            skill_lower = skill.lower()
+            recommendation = skill_learning_map.get(skill_lower, f"Seek online courses or tutorials for {skill}")
+
+            # Determine priority
+            if skill_lower in ["python", "sql", "excel", "javascript"]:
+                priority = "High"
+            elif skill_lower in ["tableau", "power bi", "aws", "react"]:
+                priority = "Medium"
+            else:
+                priority = "Low"
+
+            recommendations.append({
+                "skill": skill,
+                "recommendation": recommendation,
+                "priority": priority,
+                "estimated_time": "2-4 weeks" if priority == "High" else "1-2 weeks"
+            })
+
+        # Calculate match percentage
+        match_percentage = len(matching_skills) / len(required_skills) if required_skills else 0
+
+        return {
+            "target_role": target_role,
+            "current_match": f"{match_percentage:.1%}",
+            "matching_skills": matching_skills,
+            "skill_gaps": missing_skills,
+            "recommendations": recommendations,
+            "role_info": {
+                "description": role_data["description"],
+                "experience_level": role_data["experience_level"],
+                "salary_range": role_data.get("salary_range", "Not specified"),
+                "key_responsibilities": role_data.get("responsibilities", [])
+            }
+        }
+
+    def _generate_career_recommendations_html(self, predicted_role: str, predicted_category: str,
+                                            predicted_domain: str, role_matches: List[Dict],
+                                            gap_analysis: Dict) -> str:
+        """Generate comprehensive HTML for career recommendations."""
+
+        best_match = role_matches[0] if role_matches else None
+
+        html = f"""
+        <div style="font-family: Arial, sans-serif; max-width: 900px; color: white;">
+            <h2 style="color: white; border-bottom: 2px solid #D1C4E9; padding-bottom: 10px;">
+                🎯 Career Recommendations & Analysis
+            </h2>
+
+            <div style="background: #7E57C2; padding: 20px; border-radius: 10px; margin: 20px 0;">
+                <h3 style="color: white; margin-top: 0;">
+                    🏆 Best Role Match: {predicted_role}
+                </h3>
+                <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 15px; color: #F3E5F5;">
+                    <div>
+                        <p><strong>Category:</strong> {predicted_category}</p>
+                        <p><strong>Domain:</strong> {predicted_domain}</p>
+                    </div>
+                    <div>
+                        <p><strong>Match Score:</strong> {best_match['similarity_score']:.1%}</p>
+                        <p><strong>Salary Range:</strong> {best_match.get('salary_range', 'Not specified')}</p>
+                    </div>
+                </div>
+            </div>
+
+            <div style="background: #5E35B1; padding: 20px; border-radius: 10px; margin: 20px 0;">
+                <h3 style="color: white; margin-top: 0;">📈 Top Alternative Roles</h3>
+                <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 10px;">
+        """
+
+        for i, match in enumerate(role_matches[1:5], 1):  # Top 4 alternatives
+            html += f"""
+                <div style="background: #7E57C2; color: white; padding: 10px; border-radius: 5px; border-left: 3px solid #D1C4E9;">
+                    <strong>{match['role']}</strong><br>
+                    <small style="color: #F3E5F5;">Category: {match['category']} | Score: {match['similarity_score']:.1%}</small>
+                </div>
+            """
+
+        html += """
+                </div>
+            </div>
+        """
+
+        # Skill recommendations
+        if gap_analysis.get("recommendations"):
+            html += """
+            <div style="background: #5E35B1; padding: 20px; border-radius: 10px; margin: 20px 0;">
+                <h3 style="color: white; margin-top: 0;">🎓 Skill Development Roadmap</h3>
+                <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 15px;">
+            """
+
+            high_priority = [rec for rec in gap_analysis["recommendations"] if rec["priority"] == "High"]
+            medium_priority = [rec for rec in gap_analysis["recommendations"] if rec["priority"] == "Medium"]
+
+            html += """
+                <div>
+                    <h4 style="color: white; margin-top: 0;">🔥 High Priority Skills</h4>
+            """
+
+            for rec in high_priority[:3]:
+                html += f"""
+                    <div style="margin: 10px 0; padding: 10px; background: #7E57C2; color: white; border-radius: 5px; border-left: 3px solid #D1C4E9;">
+                        <strong>{rec['skill']}</strong>
+                        <br><small style="color: #F3E5F5;">⏱️ {rec.get('estimated_time', '2-4 weeks')}</small>
+                        <br><small style="color: #F3E5F5;">💡 {rec['recommendation']}</small>
+                    </div>
+                """
+
+            html += """
+                </div>
+                <div>
+                    <h4 style="color: white; margin-top: 0;">⭐ Medium Priority Skills</h4>
+            """
+
+            for rec in medium_priority[:3]:
+                html += f"""
+                    <div style="margin: 10px 0; padding: 10px; background: #7E57C2; color: white; border-radius: 5px; border-left: 3px solid #D1C4E9;">
+                        <strong>{rec['skill']}</strong>
+                        <br><small style="color: #F3E5F5;">⏱️ {rec.get('estimated_time', '1-2 weeks')}</small>
+                        <br><small style="color: #F3E5F5;">💡 {rec['recommendation']}</small>
+                    </div>
+                """
+
+            html += """
+                </div>
+            </div>
+            </div>
+            """
+
+        # Career path suggestions
+        html += f"""
+            <div style="background: #512DA8; padding: 20px; border-radius: 10px; margin: 20px 0;">
+                <h3 style="color: white; margin-top: 0;">🚀 Career Development Path</h3>
+                <div style="display: grid; grid-template-columns: 1fr 1fr 1fr; gap: 15px;">
+                    <div style="background: #673AB7; color: white; padding: 15px; border-radius: 8px;">
+                        <h4 style="color: white; margin-top: 0;">📚 Immediate (1-3 months)</h4>
+                        <ul style="margin: 0; padding-left: 20px; font-size: 14px; color: #F3E5F5;">
+                            <li>Focus on high-priority skills</li>
+                            <li>Complete online certifications</li>
+                            <li>Build portfolio projects</li>
+                            <li>Network in {predicted_domain} domain</li>
+                        </ul>
+                    </div>
+                    <div style="background: #673AB7; color: white; padding: 15px; border-radius: 8px;">
+                        <h4 style="color: white; margin-top: 0;">🎯 Short-term (3-12 months)</h4>
+                        <ul style="margin: 0; padding-left: 20px; font-size: 14px; color: #F3E5F5;">
+                            <li>Apply for {predicted_role} positions</li>
+                            <li>Gain hands-on experience</li>
+                            <li>Develop medium-priority skills</li>
+                            <li>Seek mentorship opportunities</li>
+                        </ul>
+                    </div>
+                    <div style="background: #673AB7; color: white; padding: 15px; border-radius: 8px;">
+                        <h4 style="color: white; margin-top: 0;">🌟 Long-term (1-2 years)</h4>
+                        <ul style="margin: 0; padding-left: 20px; font-size: 14px; color: #F3E5F5;">
+                            <li>Target senior roles in {predicted_category}</li>
+                            <li>Develop leadership skills</li>
+                            <li>Consider specialization</li>
+                            <li>Explore management tracks</li>
+                        </ul>
+                    </div>
+                </div>
+            </div>
+        </div>
+        """
+
+        return html
+
+    def compare_profile_with_jd(self, profile_text: str, job_description: str) -> str:
+        """Compare a profile with a job description and provide detailed analysis."""
+        if not profile_text.strip() or not job_description.strip():
+            return "Please provide both profile and job description for comparison."
+
+        try:
+            # Analyze the profile
+            profile_analysis = self.enhanced_profile_analysis(profile_text)
+            role_analysis = json.loads(profile_analysis[0])
+
+            # Extract skills from profile and JD
+            profile_skills = set(role_analysis["domain_analysis"]["profile_skills"])
+            jd_skills = self._extract_skills_from_text(job_description)
+            jd_skills_set = set(jd_skills)
+
+            # Calculate text similarity between profile and JD
+            text_similarity = self._calculate_text_similarity(profile_text, job_description)
+
+            # Find matching and missing skills
+            matching_skills = list(profile_skills & jd_skills_set)
+            missing_skills = list(jd_skills_set - profile_skills)
+            extra_skills = list(profile_skills - jd_skills_set)
+
+            # Calculate overall match score
+            skill_match_score = len(matching_skills) / len(jd_skills_set) if jd_skills_set else 0
+            overall_score = (skill_match_score * 0.6) + (text_similarity * 0.4)
+
+            # Determine match level
+            if overall_score >= 0.8:
+                match_level = "Excellent Match"
+            elif overall_score >= 0.6:
+                match_level = "Good Match"
+            elif overall_score >= 0.4:
+                match_level = "Fair Match"
+            else:
+                match_level = "Poor Match"
+
+            # Extract key requirements from JD
+            jd_domain, jd_domain_conf = self._classify_domain(job_description)
+
+            comparison = {
+                "overall_match_score": f"{overall_score:.1%}",
+                "match_level": match_level,
+                "profile_analysis": {
+                    "predicted_role": role_analysis["predicted_role"],
+                    "category": role_analysis["predicted_category"],
+                    "domain": role_analysis["predicted_domain"],
+                    "confidence": role_analysis["confidence_scores"]["overall"],
+                    "total_skills": len(profile_skills)
+                },
+                "job_description_analysis": {
+                    "detected_domain": jd_domain,
+                    "domain_confidence": f"{jd_domain_conf:.1%}",
+                    "required_skills": jd_skills,
+                    "total_required_skills": len(jd_skills_set)
+                },
+                "skill_analysis": {
+                    "matching_skills": matching_skills,
+                    "matching_skills_count": len(matching_skills),
+                    "missing_skills": missing_skills[:10],  # Top 10 missing skills
+                    "missing_skills_count": len(missing_skills),
+                    "extra_skills": extra_skills[:5],  # Top 5 extra skills
+                    "skill_match_percentage": f"{skill_match_score:.1%}"
+                },
+                "compatibility_scores": {
+                    "skill_compatibility": f"{skill_match_score:.1%}",
+                    "text_similarity": f"{text_similarity:.1%}",
+                    "overall_score": f"{overall_score:.1%}"
+                },
+                "recommendations": {
+                    "should_apply": overall_score >= 0.5,
+                    "key_improvements": missing_skills[:5],
+                    "strengths": matching_skills[:5],
+                    "interview_readiness": "High" if overall_score >= 0.7 else "Medium" if overall_score >= 0.5 else "Low"
+                }
+            }
+
+            return json.dumps(comparison, indent=2)
+
+        except Exception as e:
+            return f"Error in profile vs JD comparison: {str(e)}"
+
+    def compare_profile_with_jd_detailed(self, profile_text: str, job_description: str) -> tuple:
+        """Compare profile with JD and return both JSON and detailed HTML analysis."""
+        if not profile_text.strip() or not job_description.strip():
+            return "Please provide both profile and job description for comparison.", ""
+
+        try:
+            # Get the basic comparison
+            comparison_json = self.compare_profile_with_jd(profile_text, job_description)
+            comparison_data = json.loads(comparison_json)
+
+            # Generate detailed HTML analysis
+            detailed_html = self._generate_jd_comparison_html(comparison_data)
+
+            return comparison_json, detailed_html
+
+        except Exception as e:
+            error_msg = f"Error in detailed profile vs JD comparison: {str(e)}"
+            return error_msg, ""
+
+    def _generate_jd_comparison_html(self, comparison_data: dict) -> str:
+        """Generate detailed HTML for profile vs JD comparison."""
+        overall_score = float(comparison_data["overall_match_score"].replace('%', '')) / 100
+        match_level = comparison_data["match_level"]
+
+        # Determine color based on match level - NEW PURPLE THEME
+        if overall_score >= 0.8:
+            score_color = "#673AB7"  # Bright Purple for Excellent
+        elif overall_score >= 0.6:
+            score_color = "#7E57C2"  # Medium Purple for Good
+        elif overall_score >= 0.4:
+            score_color = "#9575CD"  # Lighter Purple for Fair
+        else:
+            score_color = "#5E35B1"  # Darker Purple for Poor
+
+        html = f"""
+        <div style="font-family: Arial, sans-serif; max-width: 900px; color: white;">
+            <h2 style="color: white; border-bottom: 2px solid #D1C4E9; padding-bottom: 10px;">
+                📊 Profile vs Job Description Analysis
+            </h2>
+
+            <div style="background: {score_color}; padding: 20px; border-radius: 10px; margin: 20px 0; text-align: center;">
+                <h3 style="margin: 0; font-size: 24px; color: white;">
+                    {match_level}: {comparison_data['overall_match_score']}
+                </h3>
+                <p style="margin: 10px 0 0 0; font-size: 16px; color: #F3E5F5;">
+                    Interview Readiness: {comparison_data['recommendations']['interview_readiness']}
+                </p>
+            </div>
+
+            <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 20px; margin: 20px 0;">
+                <div style="background: #5E35B1; padding: 20px; border-radius: 10px;">
+                    <h3 style="color: white; margin-top: 0;">👤 Profile Analysis</h3>
+                    <p><strong>Predicted Role:</strong> {comparison_data['profile_analysis']['predicted_role']}</p>
+                    <p><strong>Category:</strong> {comparison_data['profile_analysis']['category']}</p>
+                    <p><strong>Domain:</strong> {comparison_data['profile_analysis']['domain']}</p>
+                    <p><strong>Total Skills:</strong> {comparison_data['profile_analysis']['total_skills']}</p>
+                </div>
+
+                <div style="background: #5E35B1; padding: 20px; border-radius: 10px;">
+                    <h3 style="color: white; margin-top: 0;">📄 Job Requirements</h3>
+                    <p><strong>Detected Domain:</strong> {comparison_data['job_description_analysis']['detected_domain']}</p>
+                    <p><strong>Domain Confidence:</strong> {comparison_data['job_description_analysis']['domain_confidence']}</p>
+                    <p><strong>Required Skills:</strong> {comparison_data['job_description_analysis']['total_required_skills']}</p>
+                </div>
+            </div>
+
+            <div style="background: #673AB7; padding: 20px; border-radius: 10px; margin: 20px 0;">
+                <h3 style="color: white; margin-top: 0;">✅ Matching Skills ({comparison_data['skill_analysis']['matching_skills_count']} skills)</h3>
+                <div style="display: flex; flex-wrap: wrap; gap: 8px;">
+        """
+
+        for skill in comparison_data['skill_analysis']['matching_skills']:
+            html += f'<span style="background: #512DA8; color: white; padding: 4px 8px; border-radius: 4px; font-size: 12px;">{skill}</span>'
+
+        html += """
+                </div>
+            </div>
+        """
+
+        if comparison_data['skill_analysis']['missing_skills']:
+            html += f"""
+            <div style="background: #7E57C2; padding: 20px; border-radius: 10px; margin: 20px 0;">
+                <h3 style="color: white; margin-top: 0;">❌ Missing Skills ({comparison_data['skill_analysis']['missing_skills_count']} skills)</h3>
+                <div style="display: flex; flex-wrap: wrap; gap: 8px;">
+            """
+
+            for skill in comparison_data['skill_analysis']['missing_skills']:
+                html += f'<span style="background: #9575CD; color: white; padding: 4px 8px; border-radius: 4px; font-size: 12px;">{skill}</span>'
+
+            html += """
+                </div>
+            </div>
+            """
+
+        html += f"""
+            <div style="background: #512DA8; padding: 20px; border-radius: 10px; margin: 20px 0;">
+                <h3 style="color: white; margin-top: 0;">📈 Compatibility Scores</h3>
+                <div style="display: grid; grid-template-columns: 1fr 1fr 1fr; gap: 15px; text-align: center;">
+                    <div>
+                        <h4 style="margin: 0;">Skill Match</h4>
+                        <p style="font-size: 18px; font-weight: bold; margin: 5px 0;">{comparison_data['compatibility_scores']['skill_compatibility']}</p>
+                    </div>
+                    <div>
+                        <h4 style="margin: 0;">Text Similarity</h4>
+                        <p style="font-size: 18px; font-weight: bold; margin: 5px 0;">{comparison_data['compatibility_scores']['text_similarity']}</p>
+                    </div>
+                    <div>
+                        <h4 style="margin: 0;">Overall Score</h4>
+                        <p style="font-size: 18px; font-weight: bold; margin: 5px 0;">{comparison_data['compatibility_scores']['overall_score']}</p>
+                    </div>
+                </div>
+            </div>
+
+            <div style="background: #4527A0; padding: 20px; border-radius: 10px; margin: 20px 0;">
+                <h3 style="color: white; margin-top: 0;">💡 Recommendations</h3>
+                <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 15px; color: #F3E5F5;">
+                    <div>
+                        <h4>Should Apply?</h4>
+                        <p style="font-weight: bold; color: white;">
+                            {"✅ Yes, good fit!" if comparison_data['recommendations']['should_apply'] else "❌ Consider improving skills first"}
+                        </p>
+
+                        <h4>Key Strengths:</h4>
+                        <ul>
+        """
+
+        for strength in comparison_data['recommendations']['strengths']:
+            html += f"<li>{strength}</li>"
+
+        html += f"""
+                        </ul>
+                    </div>
+                    <div>
+                        <h4>Priority Improvements:</h4>
+                        <ul>
+        """
+
+        for improvement in comparison_data['recommendations']['key_improvements']:
+            html += f"<li>{improvement}</li>"
+
+        html += """
+                        </ul>
+                    </div>
+                </div>
+            </div>
+        </div>
+        """
+
+        return html
+
+
+def create_colab_interface():
+    """Create Gradio interface optimized for Google Colab."""
+    app = StandaloneResumeMatcherApp()
+
+    with gr.Blocks(title="Resume Matcher for Google Colab", theme=gr.themes.Soft()) as interface:
+        gr.Markdown("# 🚀 Resume Matcher - Google Colab Edition")
+        gr.Markdown("""
+        **✅ Zero Dependencies | ⚡ Instant Results | 🎯 Advanced AI Analytics**
+
+        **Perfect for Google Colab - Just paste and run!**
+
+        **Key Features:**
+        - 🎯 **Smart Role Matching**: AI-powered role classification across 20+ roles
+        - 📊 **Skill Gap Analysis**: Identifies missing skills with learning roadmaps
+        - 📋 **Profile vs Job Matching**: Detailed compatibility scoring
+        - 💰 **Salary Insights**: Market salary ranges for different roles
+        - 🎓 **Learning Recommendations**: Personalized skill development plans
+        - 🚀 **Career Roadmaps**: Short-term and long-term career guidance
+        """)
+
+        with gr.Tabs():
+            # Tab 1: Profile Analysis
+            with gr.TabItem("🎯 Profile Analysis"):
+                with gr.Row():
+                    with gr.Column(scale=1):
+                        gr.Markdown("## 📝 Candidate Profile Input")
+                        profile_input = gr.Textbox(
+                            label="Paste Candidate Profile",
+                            placeholder="""Example format:
+
+Education:
+Master's in Computer Science - Stanford University - 3.8 GPA
+
+Experience:
+Google - Software Engineer - 2020-2023 - Developed web applications using React and Python
+Microsoft - Intern - 2019 - Built machine learning models for data analysis
+
+Skills:
+Python, JavaScript, React, SQL, Machine Learning, AWS, Git, Agile, Problem Solving
+
+Projects:
+E-commerce Platform - Built full-stack web application with React frontend and Django backend
+Data Analysis Tool - Created Python-based tool for analyzing customer behavior data
+
+Achievements:
+AWS Certified Developer, Published research paper on ML algorithms, Led team of 5 developers""",
+                            lines=20,
+                            max_lines=30
+                        )
+
+                        analyze_btn = gr.Button("🔍 Analyze Profile", variant="primary", size="lg")
+
+                    with gr.Column(scale=1):
+                        gr.Markdown("## 📊 Analysis Results")
+
+                        with gr.Tabs():
+                            with gr.TabItem("🎯 Role Classification"):
+                                role_analysis_output = gr.JSON(label="Detailed Role Analysis")
+
+                            with gr.TabItem("📈 Skill Gap Analysis"):
+                                skill_gap_output = gr.JSON(label="Skill Gap & Recommendations")
+
+                            with gr.TabItem("🚀 Career Roadmap"):
+                                career_recommendations_output = gr.HTML(label="Career Development Plan")
+
+                analyze_btn.click(
+                    fn=app.enhanced_profile_analysis,
+                    inputs=[profile_input],
+                    outputs=[role_analysis_output, skill_gap_output, career_recommendations_output]
+                )
+
+            # Tab 2: Profile vs Job Description
+            with gr.TabItem("📋 Profile vs Job Description"):
+                gr.Markdown("## 🎯 Compare Profile Against Job Description")
+
+                with gr.Row():
+                    with gr.Column():
+                        gr.Markdown("### 👤 Candidate Profile")
+                        profile_jd_input = gr.Textbox(
+                            label="Candidate Profile",
+                            lines=12,
+                            placeholder="Paste candidate profile here..."
+                        )
+
+                    with gr.Column():
+                        gr.Markdown("### 📄 Job Description")
+                        jd_input = gr.Textbox(
+                            label="Job Description",
+                            lines=12,
+                            placeholder="""Paste job description here...
+
+Example:
+We are looking for a Software Engineer to join our team.
+
+Requirements:
+- 3+ years of experience in Python or Java
+- Experience with web frameworks (Django, Flask, Spring)
+- Knowledge of databases (SQL, NoSQL)
+- Experience with cloud platforms (AWS, GCP, Azure)
+- Strong problem-solving skills
+- Bachelor's degree in Computer Science or related field
+
+Responsibilities:
+- Develop and maintain web applications
+- Collaborate with cross-functional teams
+- Write clean, maintainable code
+- Participate in code reviews
+- Debug and resolve technical issues"""
+                        )
+
+                compare_jd_btn = gr.Button("🔍 Analyze Match Score", variant="primary", size="lg")
+
+                with gr.Tabs():
+                    with gr.TabItem("📊 Match Score & Analysis"):
+                        jd_comparison_output = gr.JSON(label="Profile vs JD Analysis")
+
+                    with gr.TabItem("📈 Detailed Breakdown"):
+                        jd_detailed_output = gr.HTML(label="Detailed Match Analysis")
+
+                compare_jd_btn.click(
+                    fn=app.compare_profile_with_jd_detailed,
+                    inputs=[profile_jd_input, jd_input],
+                    outputs=[jd_comparison_output, jd_detailed_output]
+                )
+
+        with gr.Accordion("ℹ️ How to Use & Features", open=False):
+            gr.Markdown("""
+            ### 🚀 Quick Start Guide:
+
+            1. **Profile Analysis**: Paste a candidate's resume/profile in the first tab to get:
+               - AI-powered role predictions with confidence scores
+               - Skill gap analysis with priority levels
+               - Personalized learning recommendations
+               - Career development roadmap
+
+            2. **Profile vs Job Matching**: Compare a profile against a job description to get:
+               - Overall compatibility score
+               - Detailed skill matching analysis
+               - Interview readiness assessment
+               - Specific improvement recommendations
+
+            ### 🎯 What Makes This Special:
+
+            - **Zero Setup**: No installations, dependencies, or API keys needed
+            - **Instant Results**: Fast processing with immediate feedback
+            - **Comprehensive Analysis**: 20+ role types across 8 major categories
+            - **Smart Algorithms**: Multi-factor scoring (skills + keywords + text similarity)
+            - **Actionable Insights**: Specific learning paths and career guidance
+
+            ### 📊 Supported Roles:
+
+            **Analytics**: Business Analytics, Data Scientist, Data Visualization
+            **Technology**: Software Engineer, Product Manager, IT Business Analyst
+            **Finance**: Financial Analyst, Corporate Finance, Equity Research, Investment Banking
+            **Marketing**: Digital Marketing, Market Research, Performance Marketing
+            **Sales**: B2B Sales, Technology Sales
+            **HR**: HR Generalist, Talent Acquisition
+            **Operations**: Customer Success, Supply Chain Management
+            **Strategy**: Business Consulting, Corporate Strategy
+
+            ### 💡 Pro Tips:
+            - Include specific technologies, tools, and years of experience
+            - Mention quantifiable achievements (e.g., "Improved efficiency by 30%")
+            - Add both technical and soft skills
+            - Include relevant certifications and education details
+            """)
+
+    return interface
+
+
+# Main execution
+if __name__ == "__main__":
+    print("🚀 Starting Resume Matcher for Google Colab...")
+    print("✅ No external dependencies required!")
+    print("📊 Loading comprehensive role database...")
+
+    interface = create_colab_interface()
+
+    print("🎯 Ready to analyze resumes and match profiles!")
+    print("💡 Features: Role Classification | Skill Gap Analysis | Job Matching | Career Recommendations")
+
+    # Launch with Colab-optimized settings
+    interface.launch(
+        share=True,  # Creates public link for sharing
+        debug=True,  # Shows detailed error messages
+        show_error=True,  # Display errors in interface
+        quiet=False  # Show startup logs
+    )
+