#!/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 # Page Configuration st.set_page_config( page_title="AI Knowledge Tree Builder ๐Ÿ“ˆ๐ŸŒฟ", page_icon="๐ŸŒณโœจ", layout="wide", initial_sidebar_state="auto", ) # Predefined Knowledge Trees trees = { "ML Engineering": """ 0. ML Engineering ๐ŸŒ 1. Data Preparation - Load Data ๐Ÿ“Š - Preprocess Data ๐Ÿ› ๏ธ 2. Model Building - Train Model ๐Ÿค– - Evaluate Model ๐Ÿ“ˆ 3. Deployment - Deploy Model ๐Ÿš€ """, "Health": """ 0. Health and Wellness ๐ŸŒฟ 1. Physical Health - Exercise ๐Ÿ‹๏ธ - Nutrition ๐ŸŽ 2. Mental Health - Meditation ๐Ÿง˜ - Therapy ๐Ÿ›‹๏ธ """, } # Project Seeds project_seeds = { "Code Project": """ 0. Code Project ๐Ÿ“‚ 1. app.py ๐Ÿ 2. requirements.txt ๐Ÿ“ฆ 3. README.md ๐Ÿ“„ """, "Papers Project": """ 0. Papers Project ๐Ÿ“š 1. markdown ๐Ÿ“ 2. mermaid ๐Ÿ–ผ๏ธ 3. huggingface.co ๐Ÿค— """, "AI Project": """ 0. AI Project ๐Ÿค– 1. Streamlit Torch Transformers - Streamlit ๐ŸŒ - Torch ๐Ÿ”ฅ - Transformers ๐Ÿค– 2. DistillKit MergeKit Spectrum - DistillKit ๐Ÿงช - MergeKit ๐Ÿ”„ - Spectrum ๐Ÿ“Š 3. Transformers Diffusers Datasets - Transformers ๐Ÿค– - Diffusers ๐ŸŽจ - Datasets ๐Ÿ“Š """, } # Utility Functions def sanitize_label(label): """Remove invalid characters for Mermaid labels.""" 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"""
{mermaid_code}
""" 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} ๐ŸŒฑ") 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'Download {file_path}' # Search Agents (Highest resolution social network default: X) search_urls = { "๐Ÿ“š๐Ÿ“–ArXiv": lambda k: f"/?q={quote(k)}", "๐Ÿ”ฎGoogle": lambda k: f"https://www.google.com/search?q={quote(k)}", "๐Ÿ“บYoutube": lambda k: f"https://www.youtube.com/results?search_query={quote(k)}", "๐Ÿ”ญBing": lambda k: f"https://www.bing.com/search?q={quote(k)}", "๐Ÿ’กTruth": lambda k: f"https://truthsocial.com/search?q={quote(k)}", "๐Ÿ“ฑX": lambda k: f"https://twitter.com/search?q={quote(k)}", } # Main App st.title("๐ŸŒณ AI Knowledge Tree Builder ๐ŸŒฑ") # Select Project Type project_type = st.selectbox("Select Project Type", ["Code Project", "Papers Project", "AI Project"]) if 'current_tree' not in st.session_state: st.session_state['current_tree'] = trees.get("ML Engineering", project_seeds[project_type]) # 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 ๐ŸŒฑ") and new_node and parent_node: st.session_state['current_tree'] = grow_tree(st.session_state['current_tree'], new_node, parent_node) with open("current_tree.md", "w") as f: f.write(st.session_state['current_tree']) st.success(f"Added '{new_node}' under '{parent_node}'!") # 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: Minimal ML Model Building if project_type == "AI Project": st.subheader("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)