microsoft/lida

Automatic Generation of Visualizations and Infographics using Large Language Models

65
/ 100
Established

Treats visualizations as executable code rather than static outputs, enabling a full pipeline of generation, editing, explanation, evaluation, and repair through natural language interactions. Supports multiple LLM providers (OpenAI, Azure, PaLM, Cohere, HuggingFace) and visualization libraries (matplotlib, seaborn, Altair, D3) through grammar-agnostic code generation. Includes data summarization, goal-based chart recommendation, and infographic generation capabilities, with optional web UI and REST API for interaction.

3,222 stars and 6,280 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 19 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

3,222

Forks

371

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 08, 2024

Monthly downloads

6,280

Commits (30d)

0

Dependencies

20

Get this data via API

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

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