hyungkwonko/chart-llm

Vega-Lite Chart Dataset and NL Generation Framework using LLMs

41
/ 100
Emerging

This project helps visualization researchers, data storytellers, and educators generate diverse natural language descriptions from Vega-Lite chart specifications. It takes a Vega-Lite JSON input and outputs varied natural language captions, questions, or descriptions of the chart. The framework is designed for those who need to create large datasets of natural language paired with visualizations for training AI models or studying human-computer interaction.

136 stars. No commits in the last 6 months.

Use this if you are a researcher or data professional looking to generate a large, diverse dataset of natural language descriptions and questions for existing Vega-Lite chart specifications.

Not ideal if you are looking for a simple tool to generate a single caption for a chart or if you need to create charts from natural language descriptions.

visualization-research data-storytelling NLP-for-data-viz chart-annotation AI-training-data
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

136

Forks

17

Language

Python

License

MIT

Last pushed

May 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/hyungkwonko/chart-llm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.