README.md

---
title: TransformersDiffusersNDatasets
emoji: 🏢
colorFrom: gray
colorTo: green
sdk: streamlit
sdk_version: 1.43.0
app_file: app.py
pinned: false
license: mit
short_description: 🌳 AI Knowledge Tree Builder 📈🌿
---

# 🌳 AI Knowledge Tree Builder 📈🌿

## 🌟 Overview
The **AI Knowledge Tree Builder** is a Streamlit app designed to cultivate and visualize hierarchical knowledge structures. It supports growing trees with new nodes, linking them to real-time social networks or search engines, and building AI models from CSV uploads—all visualized with Mermaid graphs and tied to cutting-edge research.

## 🚀 Features
- 🌱 **Tree Growth**: Add nodes (e.g., "Feature Engineering" under "ML Engineering") to extend trees dynamically.
  - **How-to**: Enter a new node name and parent node, click "Grow Tree" → Tree updates instantly!
- 🖼️ **Mermaid Visualizations**: Render trees as clickable graphs with sanitized text (no invalid characters like parentheses).
  - **Tip**: Click nodes to explore via your chosen search agent (e.g., X for current events).
- 📱 **Node Linking**: Connect nodes to high-resolution social networks (default: X) or choose from six agents: ArXiv, Google, YouTube, Bing, TruthSocial, X.
  - **Tweet**: "Stay current with AI Knowledge Tree Builder! 🌳 Nodes link to X by default for real-time insights. #KnowledgeGraph #AI"
- 🌳 **Base Trees**: Start with "Health" or "ML Engineering" (default) as foundational knowledge structures.
- 🌱 **Project Seeds**: Choose your project type to seed the tree:
  - **Code Project**: Root nodes: `app.py`, `requirements.txt`, `README.md`.
  - **Papers Project**: Root nodes: `markdown`, `mermaid`, `huggingface.co`.
  - **AI Project**: Three variations:
    1. **Streamlit, Torch, Transformers**: Upload a CSV, train a minimal ML model, and demo it.
       - **How-to**: Upload CSV → Select features & target → Train → Download `app.py`, `requirements.txt`, `README.md`.
       - **Tweet**: "Build an AI model in minutes! 🌳 Upload a CSV, train with Torch, and deploy with Streamlit. #MachineLearning #AI"
    2. **DistillKit, MergeKit, Spectrum**: Seeds for distillation model building.
    3. **Transformers, Diffusers, Datasets**: Seeds for advanced AI projects.
- 📚 **Research Links**: Root node ties to [Hugging Face Profile](https://huggingface.co/awacke1), [TeachingCV](https://huggingface.co/spaces/awacke1/TeachingCV), [DeepResearchEvaluator](https://huggingface.co/spaces/awacke1/DeepResearchEvaluator).
- 📁 **Export**: Save trees as Markdown with outlines and Mermaid code.
  - **Tweet**: "Export your knowledge tree as Markdown! 🌳 Outline + Mermaid graph ready for Git or docs. #AI #Visualization"

## 📋 Structure
- **Base Trees**:
  - **ML Engineering (Default)** 🌐
    - Data Preparation → Load Data 📊, Preprocess Data 🛠️
    - Model Building → Train Model 🤖, Evaluate Model 📈
    - Deployment → Deploy Model 🚀
  - **Health** 🌿
    - Physical Health → Exercise 🏋️, Nutrition 🍎
    - Mental Health → Meditation 🧘, Therapy 🛋️
- **Project Seeds**:
  - Code Project: `app.py` 🐍 → `requirements.txt` 📦 → `README.md` 📄
  - Papers Project: `markdown` 📝 → `mermaid` 🖼️ → `huggingface.co` 🤗
  - AI Project: 
    - Streamlit 🌐 → Torch 🔥 → Transformers 🤖
    - DistillKit 🧪 → MergeKit 🔄 → Spectrum 📊
    - Transformers 🤖 → Diffusers 🎨 → Datasets 📊

## 🎉 Announcement Tweet
🚀 Meet the **AI Knowledge Tree Builder**! 🌳 Grow trees 🌱, link nodes to X 📱 for current events, build AI models from CSVs 🤖, and visualize with Mermaid 🖼️. Start with ML Engineering or Health, export to Markdown, and dive into research! Try it: [link] #AI #MachineLearning #KnowledgeGraph

## 🛠️ How to Run
1. Clone the repo: `git clone [repo-link]`
2. Install dependencies: `pip install -r requirements.txt`
3. Launch the app: `streamlit run app.py`
4. Select a project type, grow your tree, and explore!