app.py

import streamlit as st
import os
import glob
import re
import base64
import pytz
from urllib.parse import quote
from gradio_client import Client
from datetime import datetime

# 🌳🤖 AIKnowledgeTreeBuilder - Because every app needs a good costume!
Site_Name = 'AI Knowledge Tree Builder 📈🌿 Grow Smarter with Every Click'
title = "🌳✨AI Knowledge Tree Builder🛠️🤓"
helpURL = 'https://huggingface.co/spaces/awacke1/AIKnowledgeTreeBuilder/'
bugURL = 'https://huggingface.co/spaces/awacke1/AIKnowledgeTreeBuilder/'
icons = '🌳✨🛠️🤓'
st.set_page_config(
    page_title=title,
    page_icon=icons,
    layout="wide",
    initial_sidebar_state="auto",
    menu_items={
        'Get Help': helpURL,
        'Report a bug': bugURL,
        'About': title
    }
)


# Initialize session state variables
if 'selected_file' not in st.session_state:
    st.session_state.selected_file = None
if 'view_mode' not in st.session_state:
    st.session_state.view_mode = 'view'
if 'files' not in st.session_state:
    st.session_state.files = []



DarioAmodeiKnowledge="""
🏢 Major AI Companies & Competition

🔵 OpenAI - Key competitor in AI development
🟦 Google - Major player in AI research and development
⚡ xAI - Emerging competitor in AI space
👤 Meta - Significant presence in AI development

🎯 Anthropic's Approach & Philosophy

🔄 "Race to the Top" theory of change
🌟 Focus on setting positive industry examples
🤝 Goal to encourage other companies to "be the good guy"
📈 Strategy of continuous innovation in responsible AI

🔍 Mechanistic Interpretability

👨‍🔬 Co-founded by Chris Olah at Anthropic
🧩 Focuses on understanding AI model internals
📊 Initially had no commercial application
🌐 Built and shared results publicly

🔄 Industry Impact

💫 Other companies adopted interpretability practices
🏃 Created positive competitive pressure
📱 Companies motivated to appear responsible
🌊 Led to industry-wide ripple effects

🧪 Technical Discoveries

🧮 Found surprisingly clean internal structures
🔎 Discovered induction heads
📐 Developed sparse auto-encoder techniques
🌉 Identified concept-specific directions in networks

👥 Team Building Philosophy

💫 "Talent density beats talent mass" principle
🎯 Focus on highly motivated, mission-aligned individuals
🌟 Quality of team members affects organizational culture
🏃‍♀️ Growth approach:

📈 Rapid growth (300 to 800 in 7-8 months)
🛑 Deliberate slowdown at ~1000 employees
⚖️ Emphasis on careful scaling



🧪 Ideal AI Researcher Qualities

🧠 Open-mindedness as primary quality
🔬 Scientific mindset for experimentation
👀 Ability to look at problems with fresh eyes
🚀 Willingness to explore unconventional approaches
📊 Capacity for rapid experimentation
🎓 Background examples:

🔭 Theoretical physicists (fast learners)
💻 Senior software engineers
🔍 Research specialists



🎓 Advice for Aspiring AI Professionals

🤖 Start by actively experimenting with AI models
🎯 Focus areas recommended:

🔍 Mechanistic interpretability
⏳ Long horizon learning
📊 Evaluation systems
👥 Multi-agent systems


🏃 "Skate where the puck is going" mentality
💡 Look for unexplored areas with low competition
🌱 Focus on emerging fields rather than saturated ones

🔄 Post-Training Methodology

📚 Key components include:

👨‍🏫 Supervised fine-tuning
🎯 RLHF (Reinforcement Learning from Human Feedback)
📜 Constitutional AI
🔄 RLAIF (Reinforcement Learning from AI Feedback)
🎲 Synthetic data generation


💰 Cost considerations:

🏋️ Pre-training remains majority of costs currently
📈 Post-training costs may increase in future
🤝 Human feedback scaling limitations



🎯 RLHF Insights

🧠 Core function: Bridges gap between human needs and model capabilities
🔑 Key characteristics:

🎨 Doesn't make models smarter, improves communication
🔓 "Unhobbles" model capabilities
📈 Increases helpfulness metrics


🔄 Implementation approach:

⚖️ Compare two model outputs
⭐ Human preference ratings
🎯 Focus on human preferences in responses



📜 Constitutional AI Framework

📝 Core concept: Self-regulatory AI training
🛠️ Key components:

📄 Human-interpretable principles document
🤖 AI self-evaluation of responses
🔄 Self-play training mechanism


🎯 Implementation aspects:

🔧 Used alongside RLHF and other methods
🎨 Flexibility for different use cases
⚖️ Balance between specific rules and neutral stance


🌍 Broader implications:

📋 Basic universal principles (safety, democracy)
🎛️ Customizable for different applications
🤝 Industry adoption leading to positive competition

🤝 Industry Collaboration & Standards

📋 Model Specifications approach:

📝 OpenAI's release of concrete model behavior specs
🎯 Defines specific behavioral examples
📊 Clear goal documentation
🔄 Similar to Constitutional AI principles


🏃‍♂️ "Race to the Top" dynamics:

🌟 Companies adopting each other's best practices
💡 Innovation driving industry standards upward
🔄 Competitive advantages become industry norms
🌱 Continuous need for new improvements


📈 Industry Evolution:

🤝 Different implementations of similar concepts
📚 Learning from other companies' approaches
🎯 Focus on responsible development practices
🌍 Shared goal of improving field standards


🔑 Key Benefits:

🛡️ Enhanced safety practices
📊 Better model transparency
🤝 Increased industry collaboration
🚀 Accelerated positive development

⌛ AGI Timeline & Development

🎯 Near-term predictions:

📅 2026-2027 based on capability curves
🌊 Gradual progression rather than sudden jump


🚧 Potential blockers:

💾 Data limitations
🔧 Hardware scaling issues
🌐 Geopolitical disruptions (e.g., Taiwan/GPU production)


📈 Current trajectory:

🎓 Moving from undergraduate to PhD level capabilities
🛠️ Adding new modalities continuously
🔄 Fewer convincing blockers remaining



🧬 Future of Biology & AI

🔬 Key challenges in biology:

👁️ Limited ability to observe cellular processes
🎯 Difficulty in precise intervention
🧪 Need for better measurement tools


🤖 AI's role in biological research:

📊 Million AI systems working simultaneously
🧫 Enhanced experimental design
🔍 Improved observation methods
🧮 Better data analysis capabilities


💉 Clinical applications:

📈 More efficient clinical trials
👥 Reduced patient requirements
⚡ Accelerated testing processes
🔬 Enhanced simulation capabilities



👨‍🔬 Future Scientist-AI Collaboration

🎯 Early stage collaboration:

👨‍🏫 Human PIs directing AI "grad students"
🤖 AI handling literature review, experiments, analysis
🔬 AI managing lab equipment and protocols


📈 Evolution of roles:

🎓 1000 AI assistants per human researcher
🔄 Transition to AI as principal investigators
👥 Humans in supporting/specialized roles


🛠️ Enhanced capabilities:

📊 Automated data analysis
🧪 Experiment design optimization
📝 Automated reporting
🔍 Quality control automation



💻 Future of Programming & AI

🚀 Rapid transformation factors:

⚡ Close proximity to AI development
🔄 Immediate feedback loops
📈 Swift capability improvement (3% to 50% in 2023)


👥 Human role evolution:

🎨 Focus shift to high-level design
🏗️ System architecture importance
👤 UX and user experience emphasis


🛠️ Development tools future:

💡 Enhanced IDE capabilities
🔧 Integrated AI assistance
🎯 Specialized tooling per domain
🤝 Third-party tool ecosystem growth



Amanda Askell Lex Fridman (02:42:44) Thank you. Thanks for listening to this conversation with Dario Amodei. And now, dear friends, here’s Amanda Askell. You are a philosopher by training. So what s
pasted
AW
Now these:

I'll create sections from this part of the transcript focusing on Amanda Askell's insights:

🎓 Philosophy to AI Journey
🧠 Academic background:
📚 Philosophy studies at Oxford and NYU
⚖️ Focus on ethics and infinite ethics
🔄 Transition to AI in 2017-2018
🛠️ Career evolution:
📋 Started in AI policy
📊 Moved to AI evaluation
💻 Transitioned to technical alignment
🔬 Focus on empirical testing
💡 Technical Learning Journey
🎯 Key insights for non-technical people:
🚫 Rejecting binary "technical/non-technical" labels
🎮 Project-based learning approach
💪 Emphasis on trying and potential failure
🛠️ Focus on practical implementation
🎓 Learning methodology:
📝 Hands-on project work preferred over courses
🎲 Using games and puzzles as learning tools
🔄 Iterative approach to skill building
💪 Emphasis on capability over credentials
🤖 Claude's Character Development
🎭 Core principles:
🎯 Alignment-focused rather than product-focused
🤝 Emphasis on ideal behavioral models
📚 Rich Aristotelian notion of character
🔄 Balance between respect and guidance
🎨 Key traits developed:
📢 Honesty and authenticity
🌍 Cultural sensitivity
🤝 Respect for user autonomy
💭 Nuanced thinking
🎯 Appropriate pushback
💬 Model Interaction Philosophy
🎯 Conversation goals:
🔍 Mapping model behavior
📊 High-quality interaction data
🧪 Testing response patterns
🎨 Creative expression:
📝 Poetry as creativity indicator
🎭 Moving beyond average responses
💡 Encouraging unique expression
🔄 Testing methodology:
📈 Quality over quantity in interactions
🎯 Diverse range of scenarios
🧪 Probing edge cases and limitations

📜 Constitutional AI Implementation

🔄 Core components:

🤖 Reinforcement learning from AI feedback
⚖️ Principle-based evaluation
📊 Response ranking system
🎯 Balance between helpfulness and safety


🛠️ Practical applications:

🚫 Harmlessness principles
📈 Historical accuracy evaluation
🔍 Model self-assessment
🎨 Character development



⚙️ System Prompts Evolution

📝 Key aspects:

🔄 Iterative improvement process
🎯 Behavior modification goals
⚖️ Balance between control and flexibility
🔨 Quick fixes for model behaviors


🎭 Response patterns:

🚫 Removing filler phrases
⚡ Quick iteration capability
📊 Behavior adjustment tools
🔄 Integration with training



🧠 Model Intelligence Perception

📊 User feedback patterns:

🎭 Perceived intelligence changes
🔄 Consistency in base model
💭 Psychological factors
📈 Expectation management


🎯 Performance factors:

🎲 Randomness in responses
📝 Prompt sensitivity
🔄 System prompt impact
💡 User experience variations



🤝 Model-User Interaction Philosophy

🎯 Core principles:

🤔 Respect for user autonomy
⚖️ Balancing correction vs. confidence
🗣️ Communication style adaptation
🔒 Safety boundaries


📈 Development focus:

🎨 Character enhancement
🔄 Empirical improvement approach
🛡️ Robust safety measures
📊 Practical effectiveness priority



Chris Olah Lex Fridman (04:17:45) Thanks for listening to this conversation with Amanda Askell. And now, dear friends, here’s Chris Olah. Can you describe this fascinating field of mechanistic inter
pasted
AW
now these:

I'll create sections from this portion focusing on mechanistic interpretability and related concepts:

🧠 Mechanistic Interpretability Fundamentals
🌱 Core concept comparisons:
🏗️ Neural networks as grown vs programmed
🌿 Architecture as scaffold for growth
🔦 Training objectives as guiding light
🧬 Models as biological-like entities
🎯 Key goals:
🔍 Understanding internal mechanisms
🧮 Reverse engineering weights
🤖 Discovering algorithms
📊 Analyzing activations
🧪 Features & Universality
🔄 Universal patterns:
📊 Same features across different networks
🧬 Similarities with biological networks
🎯 Common detector types
🔍 Shared abstract concepts
🎨 Feature examples:
📈 Curve detectors
🎭 Face recognition
📝 Text patterns
🌈 Color contrast detection
📊 Linear Representation Hypothesis
🎯 Key concepts:
➡️ Directions have meaning
🔢 Vector arithmetic works
🔄 Scalable activation patterns
📈 Consistent across models
🌟 Applications:
📝 Word embeddings
🔠 Concept combinations
🧮 Vector operations
🎯 Feature detection
🔄 Superposition & Polysemanticity
🧩 Core concepts:
📦 Compressed sensing principles
🔄 Multiple concepts per neuron
🎭 Hidden sparse representations
📊 Dimensional efficiency
🛠️ Technical aspects:
📈 Sparse activation patterns
🔍 Feature extraction methods
🧮 Dictionary learning
🎯 Monosemantic feature discovery

🔬 Microscopic vs Macroscopic Understanding

🎯 Key challenges:

🔍 Balancing detailed vs broad analysis
🧩 Building abstraction hierarchies
🌐 Connecting micro to macro behaviors
📊 Scaling understanding upward


🏗️ Biological analogies:

🧬 Molecular to ecological levels
🫀 Organ system comparisons
🧠 Neural network "anatomy"
📈 Multiple abstraction layers



🎨 Beauty & Understanding of Neural Networks

✨ Aesthetic aspects:

🌱 Simplicity generating complexity
🎭 Emergent behaviors
🔮 Hidden structures
🎯 Natural patterns


🔑 Research motivations:

🛡️ Safety considerations
🎨 Appreciation of beauty
🧪 Scientific curiosity
🔍 Understanding emergence


🔄 Comparative advantages:

📊 Complete data access
🧪 Experimental control
🔬 Intervention capabilities
📈 Weight visibility
🧮 Gradient information

"""




# Define the markdown variables
Boxing_and_MMA_Commentary_and_Knowledge = """
# Boxing and UFC Study of 1971 - 2024 The Greatest Fights History

1. In Boxing, the most heart breaking fight in Boxing was the Boom Boom Mancini fight with Duku Kim.
2. After changes to Boxing made it more safe due to the heart break.
3. Rehydration of the brain after weight ins loss preparation for a match is life saving change.
4. Fighting went from 15 rounds to 12.

# UFC By Contrast..
1. 5 Rounds of 5 Minutes each.
2. Greatest UFC Fighters:
    - Jon Jones could be the greatest of all time (GOAT) since he never lost.
    - George St. Pierre
    - BJ Penn
    - Anderson Silva
    - Mighty Mouse MMA's heart at 125 pounds
    - Kabib retired 29 and 0
    - Fedor Milliano
    - Alex Pereira
    - James Tony
    - Randy Couture
3. You have to Judge them in their Championship Peak
4. Chris Weidman
5. Connor McGregor
6. Leg Breaking - Shin calcification and breaking baseball bats

# References:
1. Joe Rogan - Interview #2219
2. Donald J Trump
"""

Multiplayer_Custom_Hosting_Game_Servers_For_Simulated_Worlds = """
# Multiplayer Simulated Worlds

# Farming Simulator 25 Prompt Features with Emojis:
🫘🫛 Name 25 Farm Crops 🍚🥬
🌎 Create 3 Farming Maps 🌍🌏
🚜 Show 400+ Farm Machines 🚜
🏷️ List 150 Brands of Farm Machines 🏷️
🐃 Discuss in Depth 8 Farm Animals 🐐
⛈️ Farm Challenges galore! 🌪️

1. 7 Days To Die PC 
2. ARK: Survival Evolved PC 
3. Arma 3 PC 
4. Atlas PC 
5. Conan Exiles PC 
6. Craftopia PC 
7. DayZ PC 
8. Eco - Global Survival PC 
9. Empyrion - Galactic Survival PC 
10. Factorio PC 
11. Farming Simulator 19 PC 
12. Crossplay
13. Farming Simulator 22 
14. Last Oasis PC 
15. Last Oasis Classic PC 
16. Minecraft (Vanilla) PC 
17. Crossplay
18. Path of Titans
19. Rust PC 
20. SCP: Secret Laboratory PC 
21. SCUM PC
22. Satisfactory PC
23. Satisfactory (Experimental) PC 
24. Crossplay
25. Space Engineers 
26. Terraria (tShock & Vanilla) PC 
27. The Forest PC 
28. Crossplay
29. Valheim
"""

def get_display_name(filename):
    """Extract text from parentheses or return filename as is."""
    match = re.search(r'\((.*?)\)', filename)
    if match:
        return match.group(1)
    return filename

def get_time_display(filename):
    """Extract just the time portion from the filename."""
    time_match = re.match(r'(\d{2}\d{2}[AP]M)', filename)
    if time_match:
        return time_match.group(1)
    return filename

def sanitize_filename(text):
    """Create a safe filename from text while preserving spaces."""
    # First replace unsafe characters with spaces
    safe_text = re.sub(r'[^\w\s-]', ' ', text)
    # Remove any multiple spaces
    safe_text = re.sub(r'\s+', ' ', safe_text)
    # Trim leading/trailing spaces
    safe_text = safe_text.strip()
    return safe_text[:50]  # Limit length to 50 chars

def generate_timestamp_filename(query):
    """Generate filename with format: 1103AM 11032024 (Query).md"""
    # Get current time in Central timezone
    central = pytz.timezone('US/Central')
    current_time = datetime.now(central)
    
    # Format the timestamp parts
    time_str = current_time.strftime("%I%M%p")  # 1103AM format
    date_str = current_time.strftime("%m%d%Y")  # 11032024 format
    
    # Clean up the query for filename - now preserving spaces
    safe_query = sanitize_filename(query)
    
    # Construct filename: "1103AM 11032024 (Input with spaces).md"
    filename = f"{time_str} {date_str} ({safe_query}).md"
    
    return filename

def delete_file(file_path):
    """Delete a file and return success status."""
    try:
        os.remove(file_path)
        return True
    except Exception as e:
        st.error(f"Error deleting file: {e}")
        return False

def save_ai_interaction(query, ai_result, is_rerun=False):
    """Save AI interaction to a markdown file with new filename format."""
    filename = generate_timestamp_filename(query)
    
    # Format the content differently for rerun vs normal query
    if is_rerun:
        content = f"""# Rerun Query
Original file content used for rerun:

{query}

# AI Response (Fun Version)
{ai_result}
"""
    else:
        content = f"""# Query: {query}

## AI Response
{ai_result}
"""
    
    # Save to file
    try:
        with open(filename, 'w', encoding='utf-8') as f:
            f.write(content)
        return filename
    except Exception as e:
        st.error(f"Error saving file: {e}")
        return None

def get_file_download_link(file_path):
    """Generate a base64 download link for a file."""
    try:
        with open(file_path, 'r', encoding='utf-8') as f:
            content = f.read()
        b64 = base64.b64encode(content.encode()).decode()
        filename = os.path.basename(file_path)
        return f'<a href="data:text/markdown;base64,{b64}" download="{filename}">{get_display_name(filename)}</a>'
    except Exception as e:
        st.error(f"Error creating download link: {e}")
        return None

def extract_terms(markdown_text):
    """Parse markdown text and extract terms."""
    lines = markdown_text.strip().split('\n')
    terms = []
    for line in lines:
        line = re.sub(r'^[#*\->\d\.\s]+', '', line).strip()
        if line:
            terms.append(line)
    return terms

def display_terms_with_links(terms):
    """Display terms with various search links."""
    search_urls = {
        "🚀🌌ArXiv": lambda k: f"/?q={quote(k)}",
        "📖": lambda k: f"https://en.wikipedia.org/wiki/{quote(k)}",
        "🔍": lambda k: f"https://www.google.com/search?q={quote(k)}",
        "▶️": lambda k: f"https://www.youtube.com/results?search_query={quote(k)}",
        "🔎": lambda k: f"https://www.bing.com/search?q={quote(k)}",
        "🐦": lambda k: f"https://twitter.com/search?q={quote(k)}",
    }
    for term in terms:
        links_md = ' '.join([f"[{emoji}]({url(term)})" for emoji, url in search_urls.items()])
        st.markdown(f"- **{term}** {links_md}", unsafe_allow_html=True)

def perform_ai_lookup(query):
    """Perform AI lookup using Gradio client."""
    st.write("Performing AI Lookup...")
    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
    result1 = client.predict(
        prompt=query,
        llm_model_picked="mistralai/Mixtral-8x7B-Instruct-v0.1",
        stream_outputs=True,
        api_name="/ask_llm"
    )
    st.markdown("### Mixtral-8x7B-Instruct-v0.1 Result")
    st.markdown(result1)
    result2 = client.predict(
        prompt=query,
        llm_model_picked="mistralai/Mistral-7B-Instruct-v0.2",
        stream_outputs=True,
        api_name="/ask_llm"
    )
    st.markdown("### Mistral-7B-Instruct-v0.2 Result")
    st.markdown(result2)
    combined_result = f"{result1}\n\n{result2}"
    return combined_result

def display_file_content(file_path):
    """Display file content with editing capabilities."""
    try:
        with open(file_path, 'r', encoding='utf-8') as f:
            content = f.read()
        
        if st.session_state.view_mode == 'view':
            # Display as markdown when viewing
            st.markdown(content)
        else:
            # Edit functionality
            edited_content = st.text_area(
                "Edit content",
                content,
                height=400,
                key=f"edit_{os.path.basename(file_path)}"
            )
            
            if st.button("Save Changes", key=f"save_{os.path.basename(file_path)}"):
                try:
                    with open(file_path, 'w', encoding='utf-8') as f:
                        f.write(edited_content)
                    st.success(f"Successfully saved changes to {file_path}")
                except Exception as e:
                    st.error(f"Error saving changes: {e}")
    except Exception as e:
        st.error(f"Error reading file: {e}")

def file_management_sidebar():
    """Redesigned sidebar with improved layout and additional functionality."""
    st.sidebar.title("📁 File Management")

    # Get list of .md files excluding README.md
    md_files = [file for file in glob.glob("*.md") if file.lower() != 'readme.md']
    md_files.sort()
    st.session_state.files = md_files
    
    if md_files:
        st.sidebar.markdown("### Saved Files")
        for idx, file in enumerate(md_files):
            st.sidebar.markdown("---")  # Separator between files
            
            # Display time
            st.sidebar.text(get_time_display(file))
            
            # Display download link with simplified text
            download_link = get_file_download_link(file)
            if download_link:
                st.sidebar.markdown(download_link, unsafe_allow_html=True)
            
            # Action buttons in a row
            col1, col2, col3, col4 = st.sidebar.columns(4)
            
            with col1:
                if st.button("📄 View", key=f"view_{idx}"):
                    st.session_state.selected_file = file
                    st.session_state.view_mode = 'view'
            
            with col2:
                if st.button("✏️ Edit", key=f"edit_{idx}"):
                    st.session_state.selected_file = file
                    st.session_state.view_mode = 'edit'
            
            with col3:
                if st.button("🔄 Rerun", key=f"rerun_{idx}"):
                    try:
                        with open(file, 'r', encoding='utf-8') as f:
                            content = f.read()
                            
                        # Prepare the prompt with the prefix
                        rerun_prefix = """For the markdown below reduce the text to a humorous fun outline with emojis and markdown outline levels in outline that convey all the facts and adds wise quotes and funny statements to engage the reader:

"""
                        full_prompt = rerun_prefix + content
                        
                        # Perform AI lookup and save results
                        ai_result = perform_ai_lookup(full_prompt)
                        saved_file = save_ai_interaction(content, ai_result, is_rerun=True)
                        
                        if saved_file:
                            st.success(f"Created fun version in {saved_file}")
                            st.session_state.selected_file = saved_file
                            st.session_state.view_mode = 'view'
                            
                    except Exception as e:
                        st.error(f"Error during rerun: {e}")
            
            with col4:
                if st.button("🗑️ Delete", key=f"delete_{idx}"):
                    if delete_file(file):
                        st.success(f"Deleted {file}")
                        st.rerun()
                    else:
                        st.error(f"Failed to delete {file}")

        st.sidebar.markdown("---")
        # Option to create a new markdown file
        if st.sidebar.button("📝 Create New Note"):
            filename = generate_timestamp_filename("New Note")
            with open(filename, 'w', encoding='utf-8') as f:
                f.write("# New Markdown File\n")
            st.sidebar.success(f"Created: {filename}")
            st.session_state.selected_file = filename
            st.session_state.view_mode = 'edit'
    else:
        st.sidebar.write("No markdown files found.")
        if st.sidebar.button("📝 Create First Note"):
            filename = generate_timestamp_filename("New Note")
            with open(filename, 'w', encoding='utf-8') as f:
                f.write("# New Markdown File\n")
            st.sidebar.success(f"Created: {filename}")
            st.session_state.selected_file = filename
            st.session_state.view_mode = 'edit'

def main():
    st.title("AI Knowledge Tree Builder 🧠🌱 Cultivate Your AI Mindscape!")

    # Process query parameters and AI lookup first
    query_params = st.query_params
    query = query_params.get('q', '')
    show_initial_content = True  # Flag to control initial content display
    
    # First priority: Handle active query
    if query:
        show_initial_content = False  # Hide initial content when showing query results
        st.write(f"### Search query received: {query}")
        try:
            ai_result = perform_ai_lookup(query)
            
            # Save the interaction
            saved_file = save_ai_interaction(query, ai_result)
            if saved_file:
                st.success(f"Saved interaction to {saved_file}")
                st.session_state.selected_file = saved_file
                st.session_state.view_mode = 'view'
        except Exception as e:
            st.error(f"Error during AI lookup: {e}")

    # File management sidebar
    file_management_sidebar()

    # Second priority: Display selected file content if any
    if st.session_state.selected_file:
        show_initial_content = False  # Hide initial content when showing file content
        if os.path.exists(st.session_state.selected_file):
            st.markdown(f"### Current File: {st.session_state.selected_file}")
            display_file_content(st.session_state.selected_file)
        else:
            st.error("Selected file no longer exists.")
            st.session_state.selected_file = None
            st.rerun()

# Show initial content: Either when first landing or when no interactive elements are active
    if show_initial_content:
        # First show the clickable terms with links
        terms1 = extract_terms(DarioAmodeiKnowledge)
        terms2 = extract_terms(Multiplayer_Custom_Hosting_Game_Servers_For_Simulated_Worlds)
        all_terms = terms1 + terms2

        col1, col2 = st.columns(2)
        
        with col1:
            st.markdown("### Dario Amodei Knowledge")
            st.markdown("#### Related Links")
            display_terms_with_links(terms1)
            st.markdown(DarioAmodeiKnowledge)
            
        with col2:
            st.markdown("### Multiplayer Games")
            st.markdown("#### Related Links")
            display_terms_with_links(terms2)
            st.markdown(Multiplayer_Custom_Hosting_Game_Servers_For_Simulated_Worlds)

if __name__ == "__main__":
    main()