antvis / GPT-Vis
š¤ GPT Vision, Visualization for AI Friendly! AntV's entry for AI, and 100% generated by AI.
AI Architecture Analysis
This repository is indexed by RepoMind. By analyzing antvis/GPT-Vis in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.
Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.
Repository Overview (README excerpt)
Crawler viewEnglish | ē®ä½äøę GPT-Vis, Visualization for AI Friendly! AI-Native Visualization Components for the LLM Era. Framework-agnostic visualization library designed for AI-powered applications. š Documentation ⢠š¤ Chart Skill ⢠š§ Knowledge Base ⢠š® Try Demo ⢠š MCP Server > **š¢ Version 1.0 Preview**: Reimagined architecture optimized for AI. Stable release expected **March 21, 2026**. ⨠Features ⢠**š Framework Agnostic**: Works with vanilla JavaScript, React, Vue, Angular, or any framework ⢠**āļø Natural Syntax**: Simple, markdown-like syntax that LLMs can generate effortlessly ⢠**š Streaming Support**: Built-in support for streaming output from AI models ⢠**š”ļø Fault Tolerant**: Gracefully handles incomplete or malformed data ⢠**š 20+ Chart Types**: Statistical, relationship, and advanced visualization charts ⢠**š§ Intelligent Defaults**: Automatic data detection, smart color schemes, adaptive layouts š Quick Start Installation Basic Usage Streaming Support š Syntax Guide Basic Structure Examples **Simple chart:** **With style:** **Hierarchical data:** š§ Framework Integration Vanilla JavaScript React Vue š§ Knowledge Base GPT-Vis includes a comprehensive knowledge base to help LLMs understand when to use each chart type and how to structure data. Evaluated on 200+ scenarios with 90%+ accuracy. š¤ Contributing > **ā ļø AI-Generated Code Policy**: This project only merges AI-generated code. To contribute: ⢠Submit an Issue describing the problem or feature ⢠Tag @copilot to generate the implementation ⢠Submit PR with AI-generated code š License MIT Ā© AntV