antvis/GPT-Vis

🤖 GPT Vision, Visualization for AI Friendly! AntV's entry for AI.

What it solves

GPT-Vis solves the challenge of displaying data visualizations directly from AI-generated content. It provides a bridge between Large Language Models (LLMs) and visual interfaces, allowing AI to output charts that render immediately without requiring complex manual coding or data formatting.

How it works

It uses a simple, markdown-like syntax (DSL) that LLMs can easily generate. You can pass this syntax or standard JSON objects to the library, which then handles the rendering. It supports streaming, meaning charts can appear and update in real-time as the AI generates the data. It is framework-agnostic, working with vanilla JavaScript, React, Vue, and others.

Who it’s for

It is for developers building AI-powered applications, chatbots, or data dashboards who want to integrate interactive visualizations that AI models can create on the fly.

Highlights

  • Framework-agnostic: Works with any JavaScript framework or vanilla JS.
  • Streaming support: Renders charts incrementally as the AI generates tokens.
  • 26 chart types: Includes statistical, relationship, and text-based visualizations.
  • Fault-tolerant: Gracefully handles incomplete or malformed AI-generated data.
  • Reusable themes: Consistent styling across all chart types, customizable via a Theme Studio.
  • Shadcn/ui integration: Provides copy-pasteable React components for easy project integration.

Related

  • Dispatch
    Flint Visualization Language – Microsoft’s AI‑Focused Chart DSL

    Flint is Microsoft’s new JSON‑based visualization DSL designed to let LLM agents generate charts across multiple back‑ends, but the HN community questions its necessity and token efficiency compared to existing libraries.

  • Project
    openflowkit/openflowkit

    An open-source architecture diagramming tool that allows users and AI agents to create, edit, and synchronize diagrams with codebases via a shared DSL.

  • Project
    microsoft/SwiftStreamingMarkdown

    An iOS and macOS Markdown renderer optimized for LLM streaming, providing smooth transitions, LaTeX support, and inline citation UI.

  • Project
    Simon-He95/markstream-vue

    A family of streaming Markdown renderers for AI chat and LLM token streams, providing stable partial states and smooth rendering across multiple JS frameworks.

  • Project
    antvis/chart-visualization-skills

    A suite of AI-powered skills and a context retrieval service that enables AI agents to generate professional data visualizations, infographics, and narrative reports using the AntV ecosystem.