# microsoft/lida

Automatic Generation of Visualizations and Infographics using Large Language Models

Repository: https://github.com/microsoft/lida
Canonical: https://ross.abutalabs.com/products/lida
Homepage: https://microsoft.github.io/lida/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: datavisualization, llm, openai, visualization, cohere, openai-api, palm2, hacktoberfest
Last push: 2024-08-08T18:44:15+00:00

## Health v2 (maintenance only)
Score: 30/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 90
- inputs: {"age_days": 1273, "days_push": 755, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3273, forks 381 (observed 2026-08-28T04:07:53.217186+00:00)

## What it is
LIDA is a Python library from Microsoft that uses large language models to automatically generate, execute, edit, explain, evaluate, and repair data visualizations and infographics. It is grammar-agnostic (works with matplotlib, seaborn, altair, d3, etc.), supports multiple LLM providers (OpenAI, Azure OpenAI, PaLM, Cohere, Huggingface), and includes an optional web API and UI.

## Use cases
- generate charts from a csv file using an llm
- automate exploratory data analysis visualizations
- create infographics from data with ai
- explain or repair existing visualization code
- recommend what charts to plot for my dataset
- summarize a dataset's semantics for visualization
- edit charts via natural language

## When to choose
- you want LLM-driven automatic chart generation from tabular data
- you need visualization goal exploration for EDA
- you want a provider-agnostic library supporting OpenAI, PaLM, Cohere, etc.
- you want a Python API plus optional web UI for interactive charting

## When to avoid
- you need deterministic, non-LLM charting with no API costs
- you cannot run generated code in a secure sandboxed environment
- you need a fully stable production-grade tool rather than research software
- your data cannot be sent to third-party LLM providers

## Facets
- artifact type: library
- maturity: active
- function: data-visualization, llm-inference, prompt-engineering, data-science
- domain: data-visualization, large-language-models, data-science, artificial-intelligence
- platform: python, cross-platform
- tags: exploratory-data-analysis, infographics, chart-generation, visualization-as-code, grammar-agnostic, openai, cohere, palm2, web-server

## Member repositories
- microsoft/lida (main) score 30

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:53.217186+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:43:48.544539+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/lida (fetched 2026-08-28T04:07:53.217186+00:00, sha 3c544b20e11e)
  - homepage: https://microsoft.github.io/lida/ (fetched 2026-08-29T09:36:26.636409+00:00, sha 021929c0dfa1)
  - registry_pypi: https://pypi.org/pypi/lida/json (fetched 2026-08-29T09:36:26.645731+00:00, sha 04282bd78bfa)
- Data as of 2026-08-30T08:39:29.467469+00:00.