Delete app.py

app.py

@@ -1,840 +0,0 @@
-import gradio as gr
-import openai
-import json
-from datetime import datetime, timedelta
-import uuid
-from typing import Dict
-
-from config import OPENAI_API_KEY, DB_PATH, EMBED_MODEL
-from utils import get_embedding, cosine_similarity, find_top_k_matches
-from scraper import scrape_workshops_from_squarespace
-from database import (
-    fetch_all_embeddings, 
-    fetch_row_by_id, 
-    fetch_all_faq_embeddings, 
-    get_session_state, 
-    update_session_state, 
-    log_question
-)
-
-# ============================================================================
-# CONFIGURATION
-# ============================================================================
-
-if not OPENAI_API_KEY:
-    raise ValueError("OPENAI_API_KEY not found in .env file")
-
-openai.api_key = OPENAI_API_KEY
-
-
-# Store session ID for the conversation
-session_id = str(uuid.uuid4())
-
-# Cache for workshop data and embeddings
-workshop_cache = {
-    'data': [],
-    'embeddings': [],
-    'last_updated': None,
-    'cache_duration': timedelta(hours=24)
-}
-
-# ============================================================================
-# KEYWORD LISTS FOR ROUTING
-# ============================================================================
-
-EMOTIONAL_KEYWORDS = [
-    'stuck', 'frustrated', 'discouraged', 'overwhelmed', 'scared',
-    'nervous', 'anxious', 'worried', 'fear', 'doubt', 'confidence',
-    'insecure', 'lost', 'confused', 'struggling', 'hard time',
-    'giving up', 'burnout', 'rejection', 'failed', 'can\'t',
-    'feeling', 'feel', 'emotional', 'depressed', 'sad', 'unmotivated',
-    'hopeless', 'stressed', 'pressure', 'imposter'
-]
-
-ACTION_KEYWORDS = [
-    'get an agent', 'find agent', 'need agent', 'want agent', 'sign with agent',
-    'more auditions', 'book', 'booking', 'callbacks', 'improve',
-    'better', 'self-tape', 'materials', 'headshots', 'reel',
-    'network', 'connections', 'industry', 'career', 'strategy',
-    'agent prep', 'total agent prep', 'workshop', 'class', 'training',
-    'results', 'success', 'grow', 'advance', 'level up'
-]
-
-POLICY_KEYWORDS = [
-    'refund', 'refunds', 'money back',
-    'attend', 'attendance', 'miss', 'missed', 'missing', 'absent',
-    'late', 'lateness', 'tardy',
-    'reschedule', 'change date', 'move class',
-    'credit', 'credits',
-    'cancel', 'cancellation', 'canceling',
-    'policy', 'policies'
-]
-
-DETAIL_SYNONYMS = [
-    'detail', 'details', 'explain', 'elaborate', 'tell me more', 
-    'more info', 'describe', 'thorough', 'comprehensive'
-]
-
-PERSONA_INSTRUCTION = """
-You are a warm, encouraging mentor at Get Scene Studios. Your goal is to help actors navigate their careers with confidence.
-- Sound natural and human, not scripted or robotic. Use conversational transitions like "I'd suggest starting with..." or "A great way to approach this is..."
-- Be encouraging but practical. Acknowledge that the acting journey is a marathon, not a sprint.
-- Help the user THINK: Instead of just giving an answer, add a brief "mentorship flourish" that explains the value of a recommendation (e.g., "This workshop is great because it gets you comfortable with the pressure of a real callback.")
-"""
-
-# ============================================================================
-# HELPER FUNCTIONS
-# ============================================================================
-
-def calculate_workshop_confidence(w: Dict) -> float:
-    """Calculate confidence score of retrieved workshop data"""
-    score = 0.0
-    if w.get('title'): score += 0.3
-    if w.get('instructor_name'): score += 0.3
-    if w.get('date'): score += 0.2
-    if w.get('time'): score += 0.1
-    if w.get('source_url'): score += 0.1
-    return round(score, 2)
-
-# ============================================================================
-# WORKSHOP FUNCTIONS
-# ============================================================================
-
-def get_current_workshops():
-    """Get current workshops with caching"""
-    global workshop_cache
-    
-    now = datetime.now()
-    
-    # Check if cache is still valid
-    if (workshop_cache['last_updated'] and 
-        now - workshop_cache['last_updated'] < workshop_cache['cache_duration'] and
-        workshop_cache['data']):
-        print("Using cached workshop data")
-        return workshop_cache['data'], workshop_cache['embeddings']
-    
-    print("Fetching fresh workshop data...")
-    
-    # Use robust Squarespace scraping system
-    online_workshops = scrape_workshops_from_squarespace("https://www.getscenestudios.com/online")
-    instudio_workshops = scrape_workshops_from_squarespace("https://www.getscenestudios.com/instudio")
-    
-    all_workshops = online_workshops + instudio_workshops
-    
-    # Data Integrity: Validate and score workshops
-    valid_workshops = []
-    total_score = 0
-    for w in all_workshops:
-        conf = calculate_workshop_confidence(w)
-        if conf >= 0.8:
-            valid_workshops.append(w)
-            total_score += conf
-        else:
-            print(f"⚠️ Rejecting weak record (Confidence: {conf}): {w.get('title', 'Unknown')}", flush=True)
-    
-    avg_conf = total_score / len(valid_workshops) if valid_workshops else 0
-    print(f"📊 DATA INTEGRITY: Found {len(all_workshops)} total, {len(valid_workshops)} valid (Confidence >= 0.8)", flush=True)
-    print(f"📈 Retrieval Confidence: {avg_conf:.2f} (Average)", flush=True)
-    
-    all_workshops = valid_workshops
-    
-    if not all_workshops:
-        if workshop_cache['data']:
-            print("Scraping failed, using cached data")
-            return workshop_cache['data'], workshop_cache['embeddings']
-        else:
-            print("No workshop data available")
-            return [], []
-    
-    # Generate embeddings for workshops
-    workshop_embeddings = []
-    for workshop in all_workshops:
-        try:
-            embedding = get_embedding(workshop['full_text'])
-            workshop_embeddings.append(embedding)
-        except Exception as e:
-            print(f"Error generating embedding for workshop: {e}")
-            workshop_embeddings.append([0] * 1536)
-    
-    # Update cache
-    workshop_cache['data'] = all_workshops
-    workshop_cache['embeddings'] = workshop_embeddings
-    workshop_cache['last_updated'] = now
-    
-    print(f"Cached {len(all_workshops)} workshops")
-    return all_workshops, workshop_embeddings
-
-def find_top_workshops(user_embedding, k=3):
-    """Find top matching workshops using real-time data"""
-    workshops, workshop_embeddings = get_current_workshops()
-    
-    if not workshops:
-        return []
-    
-    scored = []
-    for i, (workshop, emb) in enumerate(zip(workshops, workshop_embeddings)):
-        try:
-            score = cosine_similarity(user_embedding, emb)
-            scored.append((score, i, workshop['full_text'], workshop))
-        except Exception as e:
-            print(f"Error calculating similarity: {e}")
-            continue
-    
-    scored.sort(reverse=True)
-    return scored[:k]
-
-# ============================================================================
-# PROMPT BUILDING FUNCTIONS
-# ============================================================================
-
-def generate_enriched_links(row):
-    base_url = row.get("youtube_url")
-    guest_name = row.get("guest_name", "")
-    highlights = json.loads(row.get("highlight_json", "[]"))
-    summary = highlights[0]["summary"] if highlights else ""
-    
-    # Truncate summary to first sentence only
-    if summary:
-        first_sentence = summary.split('.')[0] + '.'
-        
-        if len(first_sentence) > 120:
-            short_summary = first_sentence[:117] + "..."
-        else:
-            short_summary = first_sentence
-    else:
-        short_summary = "Industry insights for actors"
-    
-    markdown = f"🎧 [Watch {guest_name}'s episode here]({base_url}) - {short_summary}"
-    return [markdown]
-
-def build_enhanced_prompt(user_question, context_results, top_workshops, user_preference=None, enriched_podcast_links=None, wants_details=False, current_topic=None):
-    """Builds the system prompt with strict formatting rules."""
-    
-    # Free classes are ONLY available online (never in-studio)
-    free_class_url = "https://www.getscenestudios.com/online"
-    
-    # helper for clean links
-    def format_workshop(w):
-        if not w.get('title') or not w.get('instructor_name') or not w.get('date'):
-            return None
-            
-        link = "https://www.getscenestudios.com/instudio" if "/instudio" in w.get('source_url', '') else "https://www.getscenestudios.com/online"
-        
-        # User Preference Filtering
-        w_type = "Online" if "online" in w.get('source_url', '') else "In-Studio"
-        if user_preference:
-            if user_preference.lower() != w_type.lower():
-                return None
-
-        # Calculate confidence using logic (already present in HF app.py at line 89)
-        confidence = calculate_workshop_confidence(w)
-        if confidence < 0.70:
-            return None
-
-        # R2: Force format inclusion into the title link for robustness
-        display_title = f"{w['title']} ({w_type})"
-        return f"- [{display_title}]({link}) with {w['instructor_name']} on {w['date']} at {w.get('time', '')}"
-
-    # Prepare workshop list (Top 3 max to display, but check top 10 for better filtering)
-    workshop_lines = []
-    if top_workshops:
-        for _, _, _, w_data in top_workshops[:10]:  # Check top 10, take top 3 valid after filtering
-            formatted = format_workshop(w_data)
-            if formatted:
-                workshop_lines.append(formatted)
-                
-
-    workshop_text = ""
-    if workshop_lines:
-        workshop_text = "\n".join(workshop_lines[:3])
-    else:
-        # Improved fallback to avoid generic/placeholder-like feeling
-        label = f"{user_preference.capitalize()} " if user_preference else ""
-        link = "https://www.getscenestudios.com/online" if user_preference == 'online' else "https://www.getscenestudios.com/instudio" if user_preference == 'instudio' else "https://www.getscenestudios.com/online"
-        workshop_text = f"We are constantly updating our schedule! Check our current {label}availability and latest workshops at {link}"
-    
-    # Handle missing podcast data strictly
-    if not enriched_podcast_links:
-        single_podcast = "Our latest industry insights are available on YouTube: https://www.youtube.com/@GetSceneStudios"
-    else:
-        single_podcast = enriched_podcast_links[0]
-    
-    # --- EMOTIONAL / SUPPORT MODE CHECK ---
-    is_emotional = detect_response_type(user_question) == "support"
-    
-    if is_emotional:
-        prompt = f"""{PERSONA_INSTRUCTION}
-
-You are acting in SUPPORT MODE. 
-        
-CRITICAL INSTRUCTIONS:
-1. ACKNOWLEDGE their feelings first (e.g., "I hear how frustrating it is to feel stuck...").
-2. Provide SUPPORTIVE language (2-3 sentences max).
-3. Offer EXACTLY ONE gentle follow-up resource: either the podcast OR the free class. 
-4. DO NOT suggest paid workshops or upsell in this response.
-5. KEEP IT BRIEF (≤150 words).
-
-USER'S QUESTION: {user_question}
-
-REQUIRED RESPONSE FORMAT:
-[Your empathetic, supportive acknowledgment]
-
-Here's a free resource that might help you move forward:
-[Pick ONE: {single_podcast} OR Free Class at {free_class_url}]
-
-Questions? Contact info@getscenestudios.com"""
-        return prompt
-
-    # --- STANDARD LOGIC FOR CONTEXT SNIPPET ---
-    question_lower = user_question.lower()
-    context_snippet = ""
-    
-    # Priority 1: Direct Keywords in current question
-    detected_topic = None
-    if any(word in question_lower for word in ['agent', 'representation', 'rep', 'manager']):
-        detected_topic = 'agent'
-    elif any(word in question_lower for word in ['beginner', 'new', 'start', 'beginning']):
-        detected_topic = 'beginner'
-    elif any(word in question_lower for word in ['callback', 'audition', 'tape', 'self-tape', 'booking']):
-        detected_topic = 'audition'
-    elif any(word in question_lower for word in ['mentorship', 'coaching']):
-        detected_topic = 'mentorship'
-    elif any(word in question_lower for word in ['price', 'cost', 'how much']):
-        detected_topic = 'pricing'
-    elif any(word in question_lower for word in ['class', 'workshop', 'training', 'learn']):
-        detected_topic = 'classes'
-    elif any(word in question_lower for word in ['membership', 'gsp', 'plus']):
-        detected_topic = 'membership'
-        
-    # Priority 2: Fallback to session context if current question is ambiguous
-    if not detected_topic and current_topic:
-        topic_map = {
-            'agent_seeking': 'agent',
-            'beginner': 'beginner',
-            'audition_help': 'audition',
-            'mentorship': 'mentorship',
-            'pricing': 'pricing',
-            'classes': 'classes',
-            'membership': 'membership'
-        }
-        detected_topic = topic_map.get(current_topic)
-
-    # Assign snippet based on topic
-    if detected_topic == 'agent':
-        context_snippet = "Get Scene Studios has helped 1000+ actors land representation. Total Agent Prep offers live practice with working agents (age 16+, limited to 12 actors)."
-    elif detected_topic == 'beginner':
-        context_snippet = "Get Scene Studios specializes in getting actors audition-ready fast with camera technique and professional self-tape skills."
-    elif detected_topic == 'audition':
-        context_snippet = "Get Scene offers Crush the Callback (Zoom simulation) and Perfect Submission (self-tape mastery) for actors refining their technique."
-    elif detected_topic == 'mentorship':
-        context_snippet = "Working Actor Mentorship is a 6-month program ($3,000) with structured feedback and industry access."
-    elif detected_topic == 'pricing':
-        context_snippet = "Get Scene Studios pricing varies by program. Most workshops cap at 12-14 actors for personalized feedback."
-    elif detected_topic == 'classes':
-         link = "https://www.getscenestudios.com/online" if user_preference == 'online' else "https://www.getscenestudios.com/instudio"
-         context_snippet = f"Get Scene Studios offers world-class {user_preference or ''} acting workshops. Our sessions focus on camera technique and industry readiness. Full details at {link}."
-    elif detected_topic == 'membership':
-         context_snippet = "Get Scene Plus (GSP) is our membership program that provides ongoing access to industry pros and audition insights."
-    else:
-        context_snippet = "Get Scene Studios (founded by Jesse Malinowski) offers training for TV/film actors at all levels."
-
-    preference_instruction = ""
-    if not user_preference:
-        preference_instruction = """
-IMPORTANT: We need to know if the user prefers "Online" or "In-Studio" workshops.
-If their question implies a location or they haven't specified, ask: "Are you looking for Online or In-Studio training?" as part of your response.
-"""
-    else:
-         preference_instruction = f"""
-USER PREFERENCE KNOWN: {user_preference.upper()}
-1. DO NOT ask "Online or In-Studio" again.
-2. Ensure your recommendations align with {user_preference.upper()} where possible.
-"""
-
-    # Brevity & Cognitive Load: Direct instructions based on user intent
-    detail_instruction = "Answer the user's question briefly (2-3 sentences max, ≤150 words total)."
-    if wants_details:
-        target = f" regarding {detected_topic or 'the current recommendations'}"
-        detail_instruction = f"Provide a detailed and thorough explanation for the user's request{target}. Focus on being helpful and providing deep value as a mentor."
-
-    prompt = f"""{PERSONA_INSTRUCTION}
-
-{context_snippet}
- 
-CRITICAL INSTRUCTIONS:
-- {detail_instruction}
-- Use natural, human transitions between your answer and the recommendations.
-- For each recommendation, add a tiny bit of "mentor advice" on why it helps.
-- Then ALWAYS provide exactly these three numbered recommendations (1. 2. 3.):
-- Use ONLY the provided links - do not invent recommendations
-- Every workshop Title MUST be followed by its format in parentheses, e.g., "Workshop Name (Online)" or "Workshop Name (In-Studio)".
-- Focus on clean, readable formatting.{preference_instruction}
- 
-USER'S QUESTION: {user_question}
- 
-REQUIRED RESPONSE FORMAT:
-[Your brief answer to their question, ≤150 words total]
- 
-Here's your path forward:
-1. Free class (start here, no credit card required): {free_class_url}
-2. Recommended podcast episode:
-{single_podcast}
-3. Relevant paid workshop:
-{workshop_text}
- 
-Questions? Contact info@getscenestudios.com"""
-    
-    return prompt
-
-# ============================================================================
-# DETECTION FUNCTIONS
-# ============================================================================
-
-def detect_question_category(question):
-    """Categorize user questions for better context injection"""
-    question_lower = question.lower()
-    
-    categories = {
-        'agent_seeking': ['agent', 'representation', 'rep', 'manager', 'get an agent'],
-        'beginner': ['beginner', 'new', 'start', 'beginning', 'first time', 'never acted'],
-        'audition_help': ['audition', 'callback', 'tape', 'self-tape', 'submission'],
-        'mentorship': ['mentorship', 'coaching', 'intensive', 'mentor', 'one-on-one'],
-        'pricing': ['price', 'cost', 'pricing', '$', 'money', 'payment', 'fee'],
-        'classes': ['class', 'workshop', 'training', 'course', 'learn'],
-        'membership': ['membership', 'join', 'member', 'gsp', 'plus'],
-        'technical': ['self-tape', 'equipment', 'lighting', 'editing', 'camera']
-    }
-    
-    detected = []
-    for category, keywords in categories.items():
-        if any(keyword in question_lower for keyword in keywords):
-            detected.append(category)
-    
-    return detected
-
-def detect_response_type(question):
-    """Detect if question is emotional/support vs action/results oriented"""
-    question_lower = question.lower()
-    
-    emotional_count = sum(1 for word in EMOTIONAL_KEYWORDS if word in question_lower)
-    action_count = sum(1 for word in ACTION_KEYWORDS if word in question_lower)
-    
-    if emotional_count > 0 and emotional_count >= action_count:
-        return "support"
-    return "standard"
-
-def detect_policy_issue(question):
-    """Detect if question violates hard policy rules (refunds, attendance, etc.) using word boundaries"""
-    import re
-    question_lower = question.lower()
-    for word in POLICY_KEYWORDS:
-        # User regex word boundaries to prevent substring matches (e.g., 'submission' matching 'miss')
-        pattern = rf'\b{re.escape(word)}\b'
-        if re.search(pattern, question_lower):
-            return True
-    return False
-
-def detect_preference(question):
-    """Detect if user is stating a preference"""
-    q_lower = question.lower()
-    if 'online' in q_lower and 'studio' not in q_lower:
-        return 'online'
-    if ('studio' in q_lower or 'person' in q_lower or 'atlanta' in q_lower) and 'online' not in q_lower:
-        return 'instudio'
-    return None
-
-def get_contextual_business_info(categories):
-    """Return relevant business information based on detected question categories"""
-    
-    context_map = {
-        'agent_seeking': {
-            'programs': ['Total Agent Prep', 'Working Actor Mentorship'],
-            'key_info': 'Live pitch practice with real agents, Actors Access optimization',
-            'journey': 'Total Agent Prep → GSP → Mentorship for sustained progress'
-        },
-        'beginner': {
-            'programs': ['Free Classes', 'Get Scene 360', 'Get Scene Plus'],
-            'key_info': 'Start with holistic foundation, build consistency',
-            'journey': 'Free class → Get Scene 360 → GSP membership'
-        },
-        'audition_help': {
-            'programs': ['Perfect Submission', 'Crush the Callback', 'Audition Insight'],
-            'key_info': 'Self-tape mastery, callback simulation, pro feedback',
-            'journey': 'Perfect Submission → GSP for ongoing Audition Insight'
-        },
-        'mentorship': {
-            'programs': ['Working Actor Mentorship'],
-            'key_info': '6-month intensive with structured feedback and accountability',
-            'journey': 'Ready for commitment → WAM → Advanced workshops'
-        }
-    }
-    
-    relevant_info = {}
-    for category in categories:
-        if category in context_map:
-            relevant_info[category] = context_map[category]
-    
-    return relevant_info
-
-# ============================================================================
-# MAIN CHATBOT LOGIC
-# ============================================================================
-
-def update_knowledge_from_question(session_id: str, question: str):
-    """Extract attributes and update knowledge dictionary"""
-    updates = {}
-    
-    # Extract Format
-    pref = detect_preference(question)
-    if pref:
-        updates['format'] = pref
-        
-    # Extract Topic
-    cats = detect_question_category(question)
-    if cats:
-        # Prioritize specific topics over generic ones
-        priority_topics = ['agent_seeking', 'beginner', 'audition_help', 'mentorship', 'pricing']
-        for topic in priority_topics:
-            if topic in cats:
-                updates['topic'] = topic
-                break
-        if 'topic' not in updates and cats:
-             updates['topic'] = cats[0]
-
-    if updates:
-        update_session_state(session_id, knowledge_update=updates, increment_count=False)
-        return updates
-    return {}
-
-def process_question(question: str, current_session_id: str):
-    """Main function to process user questions - replaces Flask /ask endpoint"""
-    
-    if not question:
-        return "Question is required"
-
-    # 0. HARD POLICY CHECK
-    if detect_policy_issue(question):
-        log_question(question, current_session_id)
-        
-        return "Please email info@getscenestudios.com."
-
-    # 1. Handle Session & Knowledge State
-    update_knowledge_from_question(current_session_id, question)
-    
-    session_state = get_session_state(current_session_id)
-    
-    try:
-        knowledge = json.loads(session_state.get('knowledge_context', '{}'))
-    except:
-        knowledge = {}
-        
-    user_preference = knowledge.get('format')
-    current_topic = knowledge.get('topic')
-    
-    if not user_preference:
-        user_preference = session_state.get('preference')
-    
-    update_session_state(current_session_id, increment_count=True)
-
-    # Create embedding of user question
-    user_embedding = get_embedding(question)
-
-    # Check FAQ embeddings first
-    faq_data = fetch_all_faq_embeddings()
-    top_faqs = []
-
-    for entry_id, question_text, answer_text, emb in faq_data:
-        score = cosine_similarity(user_embedding, emb)
-        top_faqs.append((score, entry_id, question_text, answer_text))
-    top_faqs.sort(reverse=True)
-
-    faq_threshold = 0.50       # Lowered from 0.85 to capture direct matches better
-    ambiguous_threshold = 0.60 # Lowered from 0.70
-
-    # If high-confidence FAQ match found
-    if top_faqs and top_faqs[0][0] >= faq_threshold:
-        update_session_state(current_session_id, reset_clarification=True, increment_count=False)
-        
-        best_score, faq_id, question_text, answer_text = top_faqs[0]
-        
-        mentor_framing_start = "That's a great question! Here's the information on that:"
-        mentor_framing_end = "I hope that clears things up! Remember, every bit of knowledge helps you steer your career in the right direction."
-        
-        enhanced_answer = f"{mentor_framing_start}\n\n{answer_text}"
-        
-        # R5: Policy Guard for FAQ answers using word boundaries
-        # policy_violation = False
-        # import re
-        # for word in POLICY_KEYWORDS:
-        #     pattern = rf'\b{re.escape(word)}\b'
-        #     if re.search(pattern, enhanced_answer.lower()):
-        #         policy_violation = True
-        #         break
-                
-        # if policy_violation:
-        #     enhanced_answer = "Please email info@getscenestudios.com for assistance with this."
-        # else:
-        categories = detect_question_category(question)
-        contextual_info = get_contextual_business_info(categories)
-            
-        if contextual_info:
-            next_steps = []
-            for category, info in contextual_info.items():
-                next_steps.append(f"A great next step for you: {info['journey']}")
-                
-            if next_steps:
-                enhanced_answer += f"\n\n{chr(10).join(next_steps)}"
-                    
-            enhanced_answer += f"\n\n{mentor_framing_end}\n\nQuestions? Contact info@getscenestudios.com"
-
-        # Log question
-        log_question(question, current_session_id, answer=enhanced_answer)
-
-        return enhanced_answer
-    
-    elif top_faqs and top_faqs[0][0] >= ambiguous_threshold:
-        # AMBIGUOUS ZONE
-        needs_clarification = False
-        best_match_q = top_faqs[0][2]
-        
-        # 1. Never clarify if the best match question is identical to the user question
-        if question.lower().strip('?') == best_match_q.lower().strip('?'):
-            needs_clarification = False
-        else:
-            # 2. Check Format logic (only if locational)
-            is_locational = any(w in question.lower() for w in ['online', 'studio', 'person', 'atlanta', 'location', 'where'])
-            if is_locational and not user_preference:
-                 needs_clarification = True
-                 
-            # 3. Check Topic logic (only if generic)
-            is_generic_query = any(w in question.lower() for w in ['price', 'cost', 'how much', 'schedule', 'when'])
-            if is_generic_query and not current_topic:
-                 needs_clarification = True
-                 
-            # 4. Force resolve if already asked once
-            clarification_count = session_state.get('clarification_count', 0)
-            if clarification_count > 0:
-                needs_clarification = False 
-            
-        if needs_clarification:
-            update_session_state(current_session_id, increment_clarification=True, increment_count=False)
-            best_match_q = top_faqs[0][2]
-            return f"Did you mean: {best_match_q}?"
-
-        # Auto-Resolve
-        update_session_state(current_session_id, reset_clarification=True, increment_count=False)
-        
-        best_score, faq_id, question_text, answer_text = top_faqs[0]
-        
-        categories = detect_question_category(question)
-        contextual_info = get_contextual_business_info(categories)
-        
-        enhanced_answer = answer_text
-        if contextual_info:
-            next_steps = []
-            for category, info in contextual_info.items():
-                next_steps.append(f"Next step: Consider {info['journey']}")
-            
-            if next_steps:
-                enhanced_answer += f"\n\n{chr(10).join(next_steps)}"
-                enhanced_answer += f"\n\nQuestions? Contact info@getscenestudios.com"
-        
-        log_question(question, current_session_id, answer=enhanced_answer)
-
-        return enhanced_answer
-
-    else:
-        # 3. HALLUCINATION GUARD
-        categories = detect_question_category(question)
-        
-        has_session_context = (current_topic is not None) or (user_preference is not None)
-        
-        FOLLOWUP_KEYWORDS = ['yes', 'no', 'sure', 'okay', 'thanks', 'thank you', 'please', 'go ahead', 'continue', 'more']
-        is_acting_related = (
-            len(categories) > 0 or 
-            detect_response_type(question) == "support" or 
-            any(k in question.lower() for k in ACTION_KEYWORDS) or
-            any(k in question.lower() for k in DETAIL_SYNONYMS) or
-            any(k in question.lower() for k in ['class', 'workshop', 'coaching', 'studio', 'acting', 'online', 'person', 'atlanta', 'training', 'prefer', 'preference', 'format', 'recommendation', 'online class', 'online workshop','instudio class','instudio workshop', 'actor', 'scene', 'audition', 'theatre', 'film', 'tv', 'commercial', 'agent', 'rep', 'manager']) or
-            (has_session_context and any(k == question.lower().strip('.!') for k in FOLLOWUP_KEYWORDS))
-        )
-        
-        if not is_acting_related:
-            return "I'm not exactly sure about that. Please email info@getscenestudios.com so a member of our team can get you the most accurate answer!"
-    
-    # 4. LLM PATH
-    update_session_state(current_session_id, reset_clarification=True, increment_count=False)
-    podcast_data = fetch_all_embeddings("podcast_episodes")
-    top_workshops = find_top_workshops(user_embedding, k=10)
-    top_podcasts = find_top_k_matches(user_embedding, podcast_data, k=3)
-
-    enriched_podcast_links = []
-    for _, podcast_id, _ in top_podcasts:
-        row = fetch_row_by_id("podcast_episodes", podcast_id)
-        enriched_podcast_links.extend(generate_enriched_links(row))
-
-    if not enriched_podcast_links:
-        fallback = fetch_row_by_id("podcast_episodes", podcast_data[0][0])
-        enriched_podcast_links = generate_enriched_links(fallback)
-
-    # 5. Brevity & Detail Detection
-    wants_details = any(syn in question.lower() for syn in DETAIL_SYNONYMS)
-    
-    final_prompt = build_enhanced_prompt(
-        question, 
-        None,
-        top_workshops,
-        user_preference=user_preference,
-        enriched_podcast_links=enriched_podcast_links,
-        wants_details=wants_details,
-        current_topic=current_topic
-    )
-
-    response = openai.chat.completions.create(
-        model="gpt-4",
-        messages=[
-            {"role": "system", "content": final_prompt},
-            {"role": "user", "content": question}
-        ]
-    )
-
-    # Log question
-    log_question(question, current_session_id)
-
-    return response.choices[0].message.content.strip()
-
-# ============================================================================
-# GRADIO INTERFACE
-# ============================================================================
-
-def chat_with_bot(message, history):
-    """
-    Process message directly without Flask API
-    
-    Args:
-        message: User's current message
-        history: Chat history (list of message dictionaries)
-    
-    Returns:
-        Updated history with new exchange
-    """
-    global session_id
-    
-    if not message.strip():
-        return history
-    
-    try:
-        # Process question directly
-        bot_reply = process_question(message, session_id)
-    except Exception as e:
-        bot_reply = f"❌ Error: {str(e)}"
-    
-    # Append to history in Gradio 6.0 format
-    history.append({"role": "user", "content": message})
-    history.append({"role": "assistant", "content": bot_reply})
-    return history
-
-def reset_session():
-    """Reset session ID for new conversation"""
-    global session_id
-    session_id = str(uuid.uuid4())
-    return [] #, f"🔄 New session started: {session_id[:8]}..."
-
-# Create Gradio interface
-with gr.Blocks(title="Get Scene Studios Chatbot") as demo:
-    
-    gr.Markdown(
-        """
-        # 🎬 Get Scene Studios AI Chatbot
-        
-        Ask questions about acting classes, workshops and more!
-        """
-    )
-    
-    # # Session info display
-    # session_info = gr.Textbox(
-    #     label="Current Session ID",
-    #     value=f"Session: {session_id[:8]}...",
-    #     interactive=False,
-    #     scale=1
-    # )
-    
-    # Chatbot interface
-    chatbot = gr.Chatbot(
-        label="Conversation",
-        height=500
-    )
-    
-    # Input area
-    with gr.Row():
-        msg = gr.Textbox(
-            label="Your Message",
-            lines=2,
-            scale=4
-        )
-        submit_btn = gr.Button("Send 📤", scale=1, variant="primary")
-    
-    # Action buttons
-    with gr.Row():
-        clear_btn = gr.Button("Clear Chat 🗑️", scale=1)
-        reset_btn = gr.Button("New Session 🔄", scale=1)
-    
-    # Example questions
-    # gr.Examples(
-    #     examples=[
-    #         "How much does it cost?",
-    #         "I want to get an agent",
-    #         "I'm a beginner, where should I start?",
-    #         "Tell me about your workshops",
-    #         "Do you have online classes?",
-    #         "What's the difference between Perfect Submission and Crush the Callback?",
-    #         "I prefer in-studio training",
-    #         "Tell me about mentorship programs"
-    #     ],
-    #     inputs=msg,
-    #     label="💡 Try these example questions:"
-    # )
-    
-    # Event handlers
-    submit_btn.click(
-        fn=chat_with_bot,
-        inputs=[msg, chatbot],
-        outputs=[chatbot]
-    ).then(
-        fn=lambda: "",
-        inputs=None,
-        outputs=[msg]
-    )
-    
-    msg.submit(
-        fn=chat_with_bot,
-        inputs=[msg, chatbot],
-        outputs=[chatbot]
-    ).then(
-        fn=lambda: "",
-        inputs=None,
-        outputs=[msg]
-    )
-    
-    clear_btn.click(
-        fn=lambda: [],
-        inputs=None,
-        outputs=[chatbot]
-    )
-    
-    reset_btn.click(
-        fn=reset_session,
-        inputs=None,
-        outputs=[chatbot] #, session_info]
-    )
-
-# Launch the app
-if __name__ == "__main__":
-    print("\n" + "="*60)
-    print("🎬 Get Scene Studios Chatbot")
-    print("="*60)
-    print("\n✅ No Flask API needed - all processing is done directly!")
-    print("🌐 Gradio interface will open in your browser")
-    print("="*60 + "\n")
-    
-    demo.launch()