app.py

#!/usr/bin/env python3
import os
import re
import streamlit as st
import streamlit.components.v1 as components
from urllib.parse import quote
import pandas as pd
import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, TensorDataset
import base64
import glob
import time
from transformers import AutoModelForCausalLM, AutoTokenizer
from mergekit.config import MergeConfiguration
from mergekit.merge import Mergekit
from spectrum import SpectrumAnalyzer
import yaml
from dataclasses import dataclass
from typing import Optional, List
import logging

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# Page Configuration
st.set_page_config(
    page_title="AI Knowledge Tree Builder 📈🌿",
    page_icon="🌳✨",
    layout="wide",
    initial_sidebar_state="auto",
)

# Predefined Knowledge Trees
trees = {
    "ML Engineering": """
0. ML Engineering 🌐
1. Data Preparation
- Load Data 📊
- Preprocess Data 🛠️
2. Model Building
- Train Model 🤖
- Evaluate Model 📈
3. Deployment
- Deploy Model 🚀
    """,
    "Health": """
0. Health and Wellness 🌿
1. Physical Health
- Exercise 🏋️
- Nutrition 🍎
2. Mental Health
- Meditation 🧘
- Therapy 🛋️
    """,
}

# Project Seeds
project_seeds = {
    "Code Project": """
0. Code Project 📂
1. app.py 🐍
2. requirements.txt 📦
3. README.md 📄
    """,
    "Papers Project": """
0. Papers Project 📚
1. markdown 📝
2. mermaid 🖼️
3. huggingface.co 🤗
    """,
    "AI Project": """
0. AI Project 🤖
1. Streamlit Torch Transformers
- Streamlit 🌐
- Torch 🔥
- Transformers 🤖
2. MergeKit Spectrum
- MergeKit 🔄
- Spectrum 📊
3. Transformers Diffusers Datasets
- Transformers 🤖
- Diffusers 🎨
- Datasets 📊
    """,
}

# Meta class for model configuration
class ModelMeta(type):
    def __new__(cls, name, bases, attrs):
        attrs['registry'] = {}
        return super().__new__(cls, name, bases, attrs)

# Base Model Configuration Class
@dataclass
class ModelConfig(metaclass=ModelMeta):
    name: str
    base_model: str
    size: str
    domain: Optional[str] = None
    
    def __init_subclass__(cls):
        ModelConfig.registry[cls.__name__] = cls

    @property
    def model_path(self):
        return f"models/{self.name}"

# Decorator for pipeline stages
def pipeline_stage(func):
    def wrapper(*args, **kwargs):
        st.spinner(f"Running {func.__name__}...")
        result = func(*args, **kwargs)
        st.success(f"Completed {func.__name__}!")
        return result
    return wrapper

# Model Builder Class
class ModelBuilder:
    def __init__(self):
        self.config = None
        self.model = None
        self.tokenizer = None

    @pipeline_stage
    def load_base_model(self, model_name: str):
        """Load base model from Hugging Face"""
        self.model = AutoModelForCausalLM.from_pretrained(model_name)
        self.tokenizer = AutoTokenizer.from_pretrained(model_name)
        return self

    @pipeline_stage
    def apply_merge(self, models_to_merge: List[str], output_dir: str):
        """Apply Mergekit for model merging"""
        merge_config = MergeConfiguration(
            models=models_to_merge,
            merge_method="linear",
            output_dir=output_dir
        )
        merger = Mergekit(merge_config)
        merger.run()
        self.model = AutoModelForCausalLM.from_pretrained(output_dir)
        return self

    @pipeline_stage
    def apply_spectrum(self, domain_data: str):
        """Apply Spectrum for domain specialization"""
        analyzer = SpectrumAnalyzer(self.model)
        analyzer.fit(domain_data)
        self.model = analyzer.specialized_model
        return self

    def save_model(self, path: str):
        """Save the final model"""
        self.model.save_pretrained(path)
        self.tokenizer.save_pretrained(path)

# Utility Functions
def sanitize_label(label):
    """Remove invalid characters for Mermaid labels."""
    return re.sub(r'[^\w\s-]', '', label).replace(' ', '_')

def sanitize_filename(label):
    """Make a valid filename from a label."""
    return re.sub(r'[^\w\s-]', '', label).replace(' ', '_')

def parse_outline_to_mermaid(outline_text, search_agent):
    """Convert tree outline to Mermaid syntax with clickable nodes."""
    lines = outline_text.strip().split('\n')
    nodes, edges, clicks, stack = [], [], [], []
    for line in lines:
        indent = len(line) - len(line.lstrip())
        level = indent // 4
        label = re.sub(r'^[#*\->\d\.\s]+', '', line.strip())
        if label:
            node_id = f"N{len(nodes)}"
            sanitized_label = sanitize_label(label)
            nodes.append(f'{node_id}["{label}"]')
            search_url = search_urls[search_agent](label)
            clicks.append(f'click {node_id} "{search_url}" _blank')
            if stack:
                parent_level = stack[-1][0]
                if level > parent_level:
                    edges.append(f"{stack[-1][1]} --> {node_id}")
                    stack.append((level, node_id))
                else:
                    while stack and stack[-1][0] >= level:
                        stack.pop()
                    if stack:
                        edges.append(f"{stack[-1][1]} --> {node_id}")
                    stack.append((level, node_id))
            else:
                stack.append((level, node_id))
    return "%%{init: {'themeVariables': {'fontSize': '18px'}}}%%\nflowchart LR\n" + "\n".join(nodes + edges + clicks)

def generate_mermaid_html(mermaid_code):
    """Generate HTML to display Mermaid diagram."""
    return f"""
    <html><head><script src="https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.min.js"></script>
    <style>.centered-mermaid{{display:flex;justify-content:center;margin:20px auto;}}</style></head>
    <body><div class="mermaid centered-mermaid">{mermaid_code}</div>
    <script>mermaid.initialize({{startOnLoad:true}});</script></body></html>
    """

def grow_tree(base_tree, new_node_name, parent_node):
    """Add a new node to the tree under a specified parent."""
    lines = base_tree.strip().split('\n')
    new_lines = []
    added = False
    for line in lines:
        new_lines.append(line)
        if parent_node in line and not added:
            indent = len(line) - len(line.lstrip())
            new_lines.append(f"{' ' * (indent + 4)}- {new_node_name} 🌱")
            added = True
    return "\n".join(new_lines)

def get_download_link(file_path, mime_type="text/plain"):
    """Generate a download link for a file."""
    with open(file_path, 'rb') as f:
        data = f.read()
    b64 = base64.b64encode(data).decode()
    return f'<a href="data:{mime_type};base64,{b64}" download="{file_path}">Download {file_path}</a>'

def save_tree_to_file(tree_text, parent_node, new_node):
    """Save tree to a markdown file with name based on nodes."""
    root_node = tree_text.strip().split('\n')[0].split('.')[1].strip() if tree_text.strip() else "Knowledge_Tree"
    filename = f"{sanitize_filename(root_node)}_{sanitize_filename(parent_node)}_{sanitize_filename(new_node)}_{int(time.time())}.md"
    
    mermaid_code = parse_outline_to_mermaid(tree_text, "🔮Google")  # Default search engine for saved trees
    export_md = f"# Knowledge Tree: {root_node}\n\n## Outline\n{tree_text}\n\n## Mermaid Diagram\n```mermaid\n{mermaid_code}\n```"
    
    with open(filename, "w") as f:
        f.write(export_md)
    return filename

def load_trees_from_files():
    """Load all saved tree markdown files."""
    tree_files = glob.glob("*.md")
    trees_dict = {}
    
    for file in tree_files:
        if file != "README.md" and file != "knowledge_tree.md":  # Skip project README and temp export
            try:
                with open(file, 'r') as f:
                    content = f.read()
                    # Extract the tree name from the first line
                    match = re.search(r'# Knowledge Tree: (.*)', content)
                    if match:
                        tree_name = match.group(1)
                    else:
                        tree_name = os.path.splitext(file)[0]
                    
                    # Extract the outline section
                    outline_match = re.search(r'## Outline\n(.*?)(?=\n## |$)', content, re.DOTALL)
                    if outline_match:
                        tree_outline = outline_match.group(1).strip()
                        trees_dict[f"{tree_name} ({file})"] = tree_outline
            except Exception as e:
                print(f"Error loading {file}: {e}")
    
    return trees_dict

# Search Agents (Highest resolution social network default: X)
search_urls = {
    "📚📖ArXiv": lambda k: f"/?q={quote(k)}",
    "🔮Google": lambda k: f"https://www.google.com/search?q={quote(k)}",
    "📺Youtube": lambda k: f"https://www.youtube.com/results?search_query={quote(k)}",
    "🔭Bing": lambda k: f"https://www.bing.com/search?q={quote(k)}",
    "💡Truth": lambda k: f"https://truthsocial.com/search?q={quote(k)}",
    "📱X": lambda k: f"https://twitter.com/search?q={quote(k)}",
}

# Main App
st.title("🌳 AI Knowledge Tree Builder 🌱")

# Sidebar with saved trees
st.sidebar.title("Saved Trees")
saved_trees = load_trees_from_files()
selected_saved_tree = st.sidebar.selectbox("Select a saved tree", ["None"] + list(saved_trees.keys()))

# Select Project Type
project_type = st.selectbox("Select Project Type", ["Code Project", "Papers Project", "AI Project"])

# Initialize or load tree
if 'current_tree' not in st.session_state:
    if selected_saved_tree != "None" and selected_saved_tree in saved_trees:
        st.session_state['current_tree'] = saved_trees[selected_saved_tree]
    else:
        st.session_state['current_tree'] = trees.get("ML Engineering", project_seeds[project_type])
elif selected_saved_tree != "None" and selected_saved_tree in saved_trees:
    st.session_state['current_tree'] = saved_trees[selected_saved_tree]

# Select Search Agent for Node Links
search_agent = st.selectbox("Select Search Agent for Node Links", list(search_urls.keys()), index=5)  # Default to X

# Tree Growth
new_node = st.text_input("Add New Node")
parent_node = st.text_input("Parent Node")
if st.button("Grow Tree 🌱") and new_node and parent_node:
    st.session_state['current_tree'] = grow_tree(st.session_state['current_tree'], new_node, parent_node)
    
    # Save to a new file with the node names
    saved_file = save_tree_to_file(st.session_state['current_tree'], parent_node, new_node)
    st.success(f"Added '{new_node}' under '{parent_node}' and saved to {saved_file}!")
    
    # Also update the temporary current_tree.md for compatibility
    with open("current_tree.md", "w") as f:
        f.write(st.session_state['current_tree'])

# Display Mermaid Diagram
st.markdown("### Knowledge Tree Visualization")
mermaid_code = parse_outline_to_mermaid(st.session_state['current_tree'], search_agent)
components.html(generate_mermaid_html(mermaid_code), height=600)

# Export Tree
if st.button("Export Tree as Markdown"):
    export_md = f"# Knowledge Tree\n\n## Outline\n{st.session_state['current_tree']}\n\n## Mermaid Diagram\n```mermaid\n{mermaid_code}\n```"
    with open("knowledge_tree.md", "w") as f:
        f.write(export_md)
    st.markdown(get_download_link("knowledge_tree.md", "text/markdown"), unsafe_allow_html=True)

# AI Project: Model Building Options
if project_type == "AI Project":
    st.subheader("AI Model Building Options")
    model_option = st.radio("Choose Model Building Method", ["Minimal ML Model from CSV", "Advanced Model Pipeline"])

    if model_option == "Minimal ML Model from CSV":
        st.write("### Build Minimal ML Model from CSV")
        uploaded_file = st.file_uploader("Upload CSV", type="csv")
        if uploaded_file:
            df = pd.read_csv(uploaded_file)
            st.write("Columns:", df.columns.tolist())
            feature_cols = st.multiselect("Select feature columns", df.columns)
            target_col = st.selectbox("Select target column", df.columns)
            if st.button("Train Model"):
                X = df[feature_cols].values
                y = df[target_col].values
                X_tensor = torch.tensor(X, dtype=torch.float32)
                y_tensor = torch.tensor(y, dtype=torch.float32).view(-1, 1)
                dataset = TensorDataset(X_tensor, y_tensor)
                loader = DataLoader(dataset, batch_size=32, shuffle=True)
                model = nn.Linear(X.shape[1], 1)
                criterion = nn.MSELoss()
                optimizer = optim.Adam(model.parameters(), lr=0.01)
                for epoch in range(10):
                    for batch_X, batch_y in loader:
                        optimizer.zero_grad()
                        outputs = model(batch_X)
                        loss = criterion(outputs, batch_y)
                        loss.backward()
                        optimizer.step()
                torch.save(model.state_dict(), "model.pth")
                app_code = f"""
import streamlit as st
import torch
import torch.nn as nn

model = nn.Linear({len(feature_cols)}, 1)
model.load_state_dict(torch.load("model.pth"))
model.eval()

st.title("ML Model Demo")
inputs = []
for col in {feature_cols}:
    inputs.append(st.number_input(col))
if st.button("Predict"):
    input_tensor = torch.tensor([inputs], dtype=torch.float32)
    prediction = model(input_tensor).item()
    st.write(f"Predicted {target_col}: {{prediction}}")
"""
                with open("app.py", "w") as f:
                    f.write(app_code)
                reqs = "streamlit\ntorch\npandas\n"
                with open("requirements.txt", "w") as f:
                    f.write(reqs)
                readme = """
# ML Model Demo

## How to run
1. Install requirements: `pip install -r requirements.txt`
2. Run the app: `streamlit run app.py`
3. Input feature values and click "Predict".
"""
                with open("README.md", "w") as f:
                    f.write(readme)
                st.markdown(get_download_link("model.pth", "application/octet-stream"), unsafe_allow_html=True)
                st.markdown(get_download_link("app.py", "text/plain"), unsafe_allow_html=True)
                st.markdown(get_download_link("requirements.txt", "text/plain"), unsafe_allow_html=True)
                st.markdown(get_download_link("README.md", "text/markdown"), unsafe_allow_html=True)

    elif model_option == "Advanced Model Pipeline":
        st.write("### Advanced Model Building Pipeline")
        
        # Model Configuration
        with st.expander("Model Configuration", expanded=True):
            base_model = st.selectbox(
                "Select Base Model",
                ["mistral-7b", "llama-2-7b", "gpt2-medium"]
            )
            model_name = st.text_input("Model Name", "custom-model")
            domain = st.text_input("Target Domain", "general")
            use_merging = st.checkbox("Apply Model Merging", False)
            use_spectrum = st.checkbox("Apply Spectrum Specialization", True)

        # Build Model
        if st.button("Build Advanced Model"):
            config = ModelConfig(
                name=model_name,
                base_model=base_model,
                size="7B",
                domain=domain
            )
            builder = ModelBuilder()
            
            with st.status("Building advanced model...", expanded=True) as status:
                builder.load_base_model(config.base_model)
                
                if use_merging:
                    models_to_merge = st.multiselect(
                        "Select Models to Merge",
                        ["mistral-7b", "llama-2-7b", "gpt2-medium"]
                    )
                    builder.apply_merge(models_to_merge, f"merged_{config.name}")
                
                if use_spectrum:
                    domain_data = st.text_area("Enter domain-specific data", "Sample domain data")
                    builder.apply_spectrum(domain_data)
                
                builder.save_model(config.model_path)
                status.update(label="Advanced model built successfully!", state="complete")
            
            # Generate deployment files
            app_code = f"""
import streamlit as st
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("{config.model_path}")
tokenizer = AutoTokenizer.from_pretrained("{config.model_path}")

st.title("Advanced Model Demo")
input_text = st.text_area("Enter text")
if st.button("Generate"):
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs)
    st.write(tokenizer.decode(outputs[0], skip_special_tokens=True))
"""
            with open("advanced_app.py", "w") as f:
                f.write(app_code)
            reqs = "streamlit\ntorch\ntransformers\nmergekit\nspectrum\n"
            with open("advanced_requirements.txt", "w") as f:
                f.write(reqs)
            readme = f"""
# Advanced Model Demo

## How to run
1. Install requirements: `pip install -r advanced_requirements.txt`
2. Run the app: `streamlit run advanced_app.py`
3. Input text and click "Generate".
"""
            with open("advanced_README.md", "w") as f:
                f.write(readme)
            
            st.markdown(get_download_link("advanced_app.py", "text/plain"), unsafe_allow_html=True)
            st.markdown(get_download_link("advanced_requirements.txt", "text/plain"), unsafe_allow_html=True)
            st.markdown(get_download_link("advanced_README.md", "text/markdown"), unsafe_allow_html=True)
            st.write(f"Model saved at: {config.model_path}")

if __name__ == "__main__":
    st.run()