---
title: Chart GPT
emoji: 👀
colorFrom: pink
colorTo: indigo
sdk: gradio
sdk_version: 5.33.0
app_file: app.py
pinned: false
license: apache-2.0
tags:
  - mcp-server-track
short_description: Chart GPT' AI-Powered Multi Diagram Generator
models:
 - VIDraft/Gemma-3-R1984-27B
 - VIDraft/Gemma-3-R1984-12B
 - VIDraft/Gemma-3-R1984-4B 
---

ChartGPT : AI-Powered Multi Diagram Generator
VIDEO Link: https://www.youtube.com/watch?v=erof86WoNMY

<div align="center">
  <h3>🎨 AI Service that Generates Professional Diagrams from Natural Language</h3>
  <p>Based LLM 'Gemma-3-R1984-27B' Model. Powered by VIDraft⚡</p>
  <p><em>Ranked 2nd on Google DeepMind' FACTS Grounding Leaderboard</em></p>
</div>

Service Link:  https://huggingface.co/spaces/openfree/Chart-GPT

📌 Overview
ChartGPT is an AI-based service that automatically generates professional diagrams from Korean and English prompts. Without needing to learn complex diagramming tools, simply describe what you want and AI will automatically generate structured diagrams.

🚀 Core Technology
Based LLM: Gemma-3-R1984-27B

Achieved 2nd place on Google DeepMind FACTS Grounding Leaderboard
State-of-the-art language model with exceptional factuality and accuracy
Outstanding performance in both Korean and English
Optimized for complex structuring tasks

MCP (Model Context Protocol) Support

Standardized AI Integration: Full support for Anthropic's MCP protocol
Integration with Various AI Tools: Seamless integration with major AI services like Claude and ChatGPT
Extensible Architecture: Operates as an MCP server for easy connection with other applications

✨ Key Features
1. Support for 5 Diagram Types

🗺️ Concept Map: Visualize relationships between topics and related concepts
📊 Synoptic Chart: Display the overall structure of processes or systems at a glance
☀️ Radial Diagram: Express structures expanding radially from a central concept
🔄 Process Flow: Represent workflows or decision-making processes sequentially
📋 WBS Diagram: Display projects broken down hierarchically

2. AI-Based Automatic Generation

Generate diagrams from natural language prompts
Support for both Korean and English
Automatic structured JSON generation

3. Brave Search Integration

Reflect latest information through real-time web search
Generate more accurate and richer content
Optional activation

4. Flexible Output Formats

PNG format (high-quality images)
SVG format (vector graphics, infinitely scalable)

🔌 MCP (Model Context Protocol) Utilization
ChartGPT supports MCP for integration with various AI applications:
MCP Use Cases

AI Agent Integration: AIs like Claude and GPT can directly request diagram generation
Workflow Automation: Automatically insert diagrams during document creation
Multimodal AI Pipeline: Automate text analysis → diagram generation

📖 How to Use
Using the AI Assistant Tab

Enter Prompt

Describe the diagram you want in natural language
Example: "Create a flowchart showing the machine learning process"


Select Diagram Type

Choose the appropriate diagram type from the dropdown


Use Brave Search (Optional)

Activate checkbox when latest information is needed
Web search results will be reflected in diagram generation


Click Generate Button

AI automatically generates JSON structure
Diagram image automatically rendered



Direct JSON Input
Fine-tune by directly editing JSON in each diagram type tab
🎯 Use Cases
Business

Project planning (WBS)
Business process documentation (Process Flow)
Organizational chart creation (Radial Diagram)

Education

Learning content organization (Concept Map)
Course explanatory materials (Synoptic Chart)
Research topic structuring (Concept Map)

Technical Documentation

System architecture diagramming
API flow explanation
Data processing pipeline visualization

🔧 Advanced Configuration
Customizing JSON Structure
Each diagram type has its unique JSON structure:
Concept Map Example:

json{
  "central_node": "Artificial Intelligence",
  "nodes": [
    {
      "id": "ml",
      "label": "Machine Learning",
      "relationship": "includes",
      "subnodes": []
    }
  ]
}

Prompt Writing Tips

Be Specific: "AI classification system" → "AI classification system including deep learning, machine learning, and natural language processing"
Specify Relationships: "A is part of B", "X leads to Y", etc.
Describe Hierarchical Structure: "A at the top level, with B and C below", etc.

💡 Model Performance
Gemma-3-R1984-27B Features

High Factuality: 2nd place on Google DeepMind FACTS Leaderboard
Structuring Ability: Accurately understands complex relationships and hierarchical structures
Multilingual Support: Ensures equal quality in both Korean and English
Context Understanding: Accurately grasps prompt intent

🛠️ Tech Stack

Frontend: Gradio (with built-in MCP server)
AI Model: Gemma-3-R1984-27B (2nd on FACTS Grounding Leaderboard)
Diagram Engine: Graphviz
Search Engine: Brave Search API
Protocol: MCP (Model Context Protocol)
Language: Python


<div align="center">
  <p>Made with ❤️ by VIDraft Team</p>
  <p><strong>Powered by VIDraft⚡</strong></p>
  <p><em>MCP-enabled for seamless AI integration</em></p>
</div>