Update app.py

app.py

@@ -6,82 +6,181 @@ import re
 def format_project_response(project: dict, indent_level: int = 0) -> str:
     """Format project details with proper indentation and spacing"""
     indent = "  " * indent_level
-    response = [f"\n{indent}• {project['name']}:"]
     
-    # Add description with proper indentation
-    description_lines = project['description'].split('. ')
-    response.extend([f"{indent}  {line.strip()}." for line in description_lines])
+    response = [f"{indent}• {project['name']}"]
+    response.append(f"{indent}  {project['description']}")
     
-    # Add technologies with proper line break
     if 'skills_used' in project:
-        response.append(f"\n{indent}  Technologies: {', '.join(project['skills_used'])}")
+        response.append(f"{indent}  Technologies: {', '.join(project['skills_used'])}")
     
-    # Add status and notes
     if 'status' in project:
         status = project['status']
         if 'development' in status.lower() or 'progress' in status.lower():
-            response.append(f"\n{indent}  Status: {status}")
+            response.append(f"{indent}  Status: {status}")
             if 'confidentiality_note' in project:
                 response.append(f"{indent}  Note: {project['confidentiality_note']}")
     
-    return '\n'.join(response) + '\n'
+    return '\n'.join(response) + '\n'  # Add extra newline for spacing
 
-def analyze_job_requirements(text: str, knowledge_base: dict) -> Dict[str, List[str]]:
-    """Analyze job requirements and match with skills"""
-    text_lower = text.lower()
+def format_skills_response(skills: dict) -> str:
+    """Format skills with proper hierarchy and spacing"""
+    response = ["My Technical Expertise:\n"]
+    
+    categories = {
+        'Machine Learning & AI': ['core', 'frameworks', 'focus_areas'],
+        'Programming': ['primary', 'libraries', 'tools'],
+        'Data & Analytics': ['databases', 'visualization', 'processing']
+    }
+    
+    for category, subcategories in categories.items():
+        response.append(f"• {category}")
+        for subcat in subcategories:
+            if subcat in skills['machine_learning']:
+                items = skills['machine_learning'][subcat]
+                response.append(f"  - {subcat.title()}: {', '.join(items)}")
+        response.append("")  # Add spacing between categories
+    
+    return '\n'.join(response)
+
+def analyze_job_description(text: str, knowledge_base: dict) -> str:
+    """Analyze job description and provide detailed alignment"""
+    # Extract key requirements
+    requirements = {
+        'technical_tools': set(),
+        'soft_skills': set(),
+        'responsibilities': set()
+    }
     
-    # Common ML/AI related keywords
+    # Common technical tools and skills
     tech_keywords = {
-        'machine learning': ['ml', 'machine learning', 'deep learning', 'neural networks'],
-        'data science': ['data science', 'data analysis', 'analytics', 'statistics'],
-        'programming': ['python', 'sql', 'programming', 'coding'],
-        'tools': ['tableau', 'powerbi', 'visualization', 'git'],
-        'cloud': ['aws', 'azure', 'cloud', 'deployment']
+        'data science', 'analytics', 'visualization', 'tableau', 'python', 
+        'machine learning', 'modeling', 'automation', 'sql', 'data analysis'
     }
     
-    # Extract matches from knowledge base
-    matches = {category: [] for category in tech_keywords}
-    my_skills = {
-        skill.lower() 
-        for skill_type in knowledge_base['skills']['technical_skills'].values() 
-        for skill_list in skill_type.values() 
-        for skill in skill_list
+    # Common soft skills
+    soft_keywords = {
+        'collaborate', 'communicate', 'analyze', 'design', 'implement',
+        'produce insights', 'improve', 'support'
     }
     
-    # Find matching skills in each category
-    for category, keywords in tech_keywords.items():
-        for keyword in keywords:
-            if keyword in text_lower and any(skill in keyword or keyword in skill for skill in my_skills):
-                matches[category].append(keyword)
+    text_lower = text.lower()
+    
+    # Extract company name if present
+    companies = ['rbc', 'shopify', 'google', 'microsoft', 'amazon']
+    company_name = next((company.upper() for company in companies if company in text_lower), None)
+    
+    # Extract requirements
+    for word in tech_keywords:
+        if word in text_lower:
+            requirements['technical_tools'].add(word)
+    
+    for word in soft_keywords:
+        if word in text_lower:
+            requirements['soft_skills'].add(word)
+            
+    # Build response
+    response_parts = []
+    
+    # Company-specific introduction if applicable
+    if company_name:
+        response_parts.append(f"Here's how I align with {company_name}'s requirements:\n")
+    else:
+        response_parts.append("Based on the job requirements, here's how I align:\n")
+
+    # Technical Skills Alignment
+    response_parts.append("• Technical Skills Match:")
+    my_relevant_skills = []
+    if 'visualization' in requirements['technical_tools'] or 'tableau' in requirements['technical_tools']:
+        my_relevant_skills.append("  - Proficient in Tableau and data visualization (used in multiple projects)")
+    if 'data analysis' in requirements['technical_tools']:
+        my_relevant_skills.append("  - Strong data analysis skills demonstrated in projects like LoanTap Credit Assessment")
+    if 'machine learning' in requirements['technical_tools'] or 'modeling' in requirements['technical_tools']:
+        my_relevant_skills.append("  - Experienced in building ML models from scratch (demonstrated in algorithm practice projects)")
+    
+    response_parts.extend(my_relevant_skills)
+    response_parts.append("")  # Add spacing
+    
+    # Business Understanding
+    response_parts.append("• Business Acumen:")
+    response_parts.append("  - Commerce background provides strong understanding of business requirements")
+    response_parts.append("  - Experience in translating business needs into technical solutions")
+    response_parts.append("  - Proven ability to communicate technical findings to business stakeholders")
+    response_parts.append("")  # Add spacing
+    
+    # Project Experience
+    response_parts.append("• Relevant Project Experience:")
+    relevant_projects = []
+    if 'automation' in requirements['technical_tools']:
+        relevant_projects.append("  - Developed AI-powered POS system with automated operations")
+    if 'data analysis' in requirements['technical_tools']:
+        relevant_projects.append("  - Built credit assessment model for LoanTap using comprehensive data analysis")
+    if 'machine learning' in requirements['technical_tools']:
+        relevant_projects.append("  - Created multiple ML models from scratch, including predictive analytics for Ola")
+    
+    response_parts.extend(relevant_projects)
+    response_parts.append("")  # Add spacing
+    
+    # Education and Additional Qualifications
+    response_parts.append("• Additional Strengths:")
+    response_parts.append("  - Currently pursuing advanced AI/ML education in Canada")
+    response_parts.append("  - Strong foundation in both technical implementation and business analysis")
+    response_parts.append("  - Experience in end-to-end project delivery and deployment")
+    
+    return '\n'.join(response_parts)
+
+def format_story_response(knowledge_base: dict) -> str:
+    """Format background story with proper structure"""
+    response_parts = ["My Journey from Commerce to ML/AI:\n"]
+    
+    # Education Background
+    response_parts.append("• Education Background:")
+    response_parts.append(f"  - Commerce degree from {knowledge_base['education']['undergraduate']['institution']}")
+    response_parts.append(f"  - Currently at {knowledge_base['education']['postgraduate'][0]['institution']}")
+    response_parts.append(f"  - Also enrolled at {knowledge_base['education']['postgraduate'][1]['institution']}")
+    response_parts.append("")  # Add spacing
+    
+    # Career Transition
+    response_parts.append("• Career Transition:")
+    transition = next((qa['answer'] for qa in knowledge_base['frequently_asked_questions'] 
+                      if 'transition' in qa['question'].lower()), '')
+    response_parts.append(f"  - {transition[:200]}...")  # Truncate for readability
+    response_parts.append("")  # Add spacing
+    
+    # Current Focus
+    response_parts.append("• Current Focus:")
+    response_parts.append("  - Building practical ML projects")
+    response_parts.append("  - Advancing AI/ML education in Canada")
+    response_parts.append("")  # Add spacing
     
-    return matches
+    # Goals
+    response_parts.append("• Future Goals:")
+    response_parts.append("  - Secure ML Engineering role in Canada")
+    response_parts.append("  - Develop innovative AI solutions")
+    response_parts.append("  - Contribute to cutting-edge ML projects")
+    
+    return '\n'.join(response_parts)
 
-def handle_perspective_query(query: str, knowledge_base: dict) -> str:
-    """Handle philosophical or perspective-based queries"""
+def add_relevant_links(response: str, query: str, knowledge_base: dict) -> str:
+    """Add relevant links based on query context"""
     query_lower = query.lower()
-    perspectives = knowledge_base.get('perspectives', {})
-    
-    # Market-related queries
-    if any(word in query_lower for word in ['market', 'opportunity', 'job', 'hiring']):
-        if any(word in query_lower for word in ['down', 'bad', 'difficult', 'tough']):
-            response_parts = [
-                "• My Perspective on the Current Market:",
-                f"  {perspectives['market_outlook']['job_market']}",
-                "",
-                "• My Strategic Approach:",
-                f"  {perspectives['market_outlook']['strategy']}",
-                "",
-                "• My Unique Value Proposition:",
-                f"  {perspectives['market_outlook']['value_proposition']}"
-            ]
-            return '\n'.join(response_parts)
-    
-    # Learning and growth queries
-    elif any(word in query_lower for word in ['learn', 'study', 'growth']):
-        return f"• My Learning Philosophy:\n  {perspectives['learning_philosophy']}"
-    
-    # Handle non-portfolio queries gracefully
-    return knowledge_base['common_queries']['general']
+    links = []
+    
+    # Add links strategically based on context
+    if any(word in query_lower for word in ['project', 'portfolio', 'work']):
+        links.append(f"\nView my complete portfolio: {knowledge_base['personal_details']['online_presence']['portfolio']}")
+    
+    if any(word in query_lower for word in ['background', 'experience', 'work']):
+        links.append(f"\nConnect with me: {knowledge_base['personal_details']['online_presence']['linkedin']}")
+    
+    for post in knowledge_base['personal_details']['online_presence']['blog_posts']:
+        if 'link' in post and any(word in query_lower for word in post['title'].lower().split()):
+            links.append(f"\nRelated blog post: {post['link']}")
+            break
+    
+    if links:
+        response += '\n' + '\n'.join(links)
+    
+    return response
 
 def generate_response(query: str, knowledge_base: dict) -> str:
     """Generate enhanced responses using the knowledge base"""
@@ -89,15 +188,15 @@ def generate_response(query: str, knowledge_base: dict) -> str:
     
     # Handle project listing requests
     if any(word in query_lower for word in ['list', 'project', 'portfolio', 'built', 'created', 'developed']):
-        response_parts = ["Here are my key projects:"]
+        response_parts = ["Here are my key projects:\n"]
         
         # Major Projects (under development)
-        response_parts.append("\nMajor Projects (In Development):")
+        response_parts.append("Major Projects (In Development):")
         for project in knowledge_base['projects']['major_projects']:
             response_parts.append(format_project_response(project, indent_level=1))
         
         # Algorithm Implementation Projects
-        response_parts.append("\nCompleted Algorithm Implementation Projects:")
+        response_parts.append("Completed Algorithm Implementation Projects:")
         for project in knowledge_base['projects']['algorithm_practice_projects']:
             response_parts.append(format_project_response(project, indent_level=1))
         
@@ -107,52 +206,51 @@ def generate_response(query: str, knowledge_base: dict) -> str:
     # Handle job description analysis
     elif len(query.split()) > 20 and any(phrase in query_lower for phrase in 
         ['requirements', 'qualifications', 'looking for', 'job description']):
+        return analyze_job_description(query, knowledge_base)
+    
+    # Handle background/story queries
+    elif any(word in query_lower for word in ['background', 'journey', 'story', 'transition']):
+        return format_story_response(knowledge_base)
+    
+    # Handle skill-specific queries
+    elif any(word in query_lower for word in ['skill', 'know', 'technology', 'stack']):
+        return format_skills_response(knowledge_base['skills']['technical_skills'])
+    
+    # Handle standout/unique qualities queries
+    elif any(word in query_lower for word in ['stand out', 'unique', 'different', 'special']):
+        response_parts = ["What Makes Me Stand Out:\n"]
+        response_parts.append("• Unique Background:")
+        response_parts.append("  - Successfully transitioned from commerce to tech")
+        response_parts.append("  - Blend of business acumen and technical expertise")
+        response_parts.append("")
         
-        matches = analyze_job_requirements(query, knowledge_base)
-        relevant_projects = find_relevant_projects(query, knowledge_base['projects']['major_projects'])
-        
-        response_parts = ["Based on the job requirements, here's how my profile aligns:\n"]
-        
-        # Technical Skills Match
-        if any(matches.values()):
-            response_parts.append("• Technical Skills Alignment:")
-            for category, skills in matches.items():
-                if skills:
-                    response_parts.append(f"  - Strong {category} skills: {', '.join(skills)}")
-            response_parts.append("")
+        response_parts.append("• Practical Experience:")
+        response_parts.append("  - Built multiple ML projects from scratch")
+        response_parts.append("  - Focus on real-world applications")
+        response_parts.append("")
         
-        # Project Experience
-        if relevant_projects:
-            response_parts.append("• Relevant Project Experience:")
-            for project in relevant_projects:
-                desc = f"  - {project['name']}: {project['description']}"
-                response_parts.append(desc)
-            response_parts.append("")
+        response_parts.append("• Technical Depth:")
+        response_parts.append("  - Strong foundation in ML/AI principles")
+        response_parts.append("  - Experience with end-to-end project implementation")
+        response_parts.append("")
         
-        # Education and Background
-        response_parts.extend([
-            "• Education and Background:",
-            "  - Advanced AI/ML education in Canada",
-            "  - Unique commerce background providing business perspective",
-            "  - Strong foundation in practical ML implementation",
-            ""
-        ])
+        response_parts.append("• Innovation Focus:")
+        response_parts.append("  - Developing novel solutions in ML/AI")
+        response_parts.append("  - Emphasis on practical impact")
         
         return '\n'.join(response_parts)
     
-    # Handle perspective/philosophical queries
-    elif any(word in query_lower for word in ['market', 'think', 'believe', 'opinion', 'weather']):
-        return handle_perspective_query(query, knowledge_base)
-    
-    # Handle story/background queries
-    elif any(word in query_lower for word in ['background', 'journey', 'story', 'transition']):
-        return format_story_response(knowledge_base)
-    
     # Default response
-    return format_default_response(knowledge_base)
+    return (f"I'm {knowledge_base['personal_details']['professional_summary']}\n\n"
+            "You can ask me about:\n"
+            "• My projects and portfolio\n"
+            "• My journey from commerce to ML/AI\n"
+            "• My technical skills and experience\n"
+            "• My fit for ML/AI roles\n"
+            "Or paste a job description to see how my profile matches!")
 
 def main():
-    st.title("💬 Chat with Manyue's AI Assistant")
+    st.title("💬 Chat with Manyue's Portfolio")
     
     # Initialize session state
     if "messages" not in st.session_state:
@@ -172,36 +270,34 @@ def main():
         - My journey from commerce to ML/AI
         - My technical skills and projects
         - My fit for ML/AI roles
-        - My perspective on the tech industry
         - You can also paste job descriptions to see how my profile matches!
         """)
         st.session_state.displayed_welcome = True
-
+    
     # Create two columns
     col1, col2 = st.columns([3, 1])
     
     with col1:
-        # Display existing messages
+        # Display chat messages
         for message in st.session_state.messages:
             with st.chat_message(message["role"]):
                 st.markdown(message["content"])
         
-        # Handle input - IMPORTANT: This needs to be outside any button handlers
+        # Chat input
         if prompt := st.chat_input("Ask me anything or paste a job description..."):
-            with st.chat_message("user"):
-                st.markdown(prompt)
-            
-            # Add user message to session state
+            # Add user message
             st.session_state.messages.append({"role": "user", "content": prompt})
             
-            # Generate and display response
-            with st.chat_message("assistant"):
-                try:
+            try:
+                # Generate and display response
+                with st.chat_message("assistant"):
                     response = generate_response(prompt, st.session_state.knowledge_base)
                     st.markdown(response)
                     st.session_state.messages.append({"role": "assistant", "content": response})
-                except Exception as e:
-                    st.error(f"An error occurred: {str(e)}")
+            except Exception as e:
+                st.error(f"An error occurred: {str(e)}")
+            
+            st.rerun()
     
     with col2:
         st.subheader("Quick Questions")
@@ -210,28 +306,16 @@ def main():
             "What are your technical skills?",
             "What makes you stand out?",
             "What's your journey into ML?",
-            "Your view on the current market?"
+            "Paste a job description to see how I match!"
         ]
         
-        # Handle quick question buttons
         for question in example_questions:
-            if st.button(question, key=f"btn_{question}"):  # Add unique keys
-                with st.chat_message("user"):
-                    st.markdown(question)
+            if st.button(question):
                 st.session_state.messages.append({"role": "user", "content": question})
-                
-                with st.chat_message("assistant"):
-                    try:
-                        response = generate_response(question, st.session_state.knowledge_base)
-                        st.markdown(response)
-                        st.session_state.messages.append({"role": "assistant", "content": response})
-                    except Exception as e:
-                        st.error(f"An error occurred: {str(e)}")
-                
                 st.rerun()
         
         st.markdown("---")
-        if st.button("Clear Chat", key="clear_chat"):  # Add unique key
+        if st.button("Clear Chat"):
             st.session_state.messages = []
             st.rerun()