Hugging Face's logo

Spaces:
tomvaillant
/
graphics-llm
Running

App Files Community
1
graphics-llm / README.md
Tom
Add Datawrapper chart generation mode with clean iframe display
2a10e9c
preview code
|
raw
history blame contribute delete
1.6 kB

A newer version of the Gradio SDK is available: 6.1.0

Upgrade
metadata
title: Viz LLM
emoji: 📊
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.49.1
app_file: app.py
pinned: false
short_description: AI assistant for visualization guidance and chart generation
license: mit

📊 Viz LLM

AI-powered data visualization assistant with two modes:

  • 💡 Ideation Mode: Get design recommendations based on research and best practices
  • 📊 Chart Generation Mode: Upload CSV data and automatically generate publication-ready charts

Features

Ideation Mode:

  • Research-backed visualization guidance
  • Chart type recommendations
  • Design best practices and accessibility advice
  • Powered by RAG with Jina-CLIP-v2 embeddings

Chart Generation Mode:

  • Upload CSV data
  • AI analyzes your data and selects optimal chart type
  • Automatic chart creation via Datawrapper API
  • Publication-ready visualizations with one click

Quick Start

  1. Install dependencies:

    pip install -r requirements.txt

  2. Set up environment variables:

    cp .env.example .env

    Required:

    • SUPABASE_URL - Your Supabase project URL
    • SUPABASE_KEY - Your Supabase anon key
    • HF_TOKEN - Hugging Face API token
    • DATAWRAPPER_ACCESS_TOKEN - Datawrapper API token

  3. Run the app:

    python app.py

Technology Stack

  • UI: Gradio
  • Vector Database: Supabase PGVector
  • Embeddings: Jina-CLIP-v2
  • LLM: Llama 3.1 via Hugging Face Inference Providers
  • Charts: Datawrapper API

License

MIT License

Built for the data visualization community