Home

Awesome

LIDA: Automatic Generation of Visualizations and Infographics using Large Language Models

PyPI version arXiv PyPI - Downloads

<a target="_blank" href="https://colab.research.google.com/github/microsoft/lida/blob/main/notebooks/tutorial.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a> <!-- <img src="docs/images/lidascreen.png" width="100%" /> -->

LIDA is a library for generating data visualizations and data-faithful infographics. LIDA is grammar agnostic (will work with any programming language and visualization libraries e.g. matplotlib, seaborn, altair, d3 etc) and works with multiple large language model providers (OpenAI, Azure OpenAI, PaLM, Cohere, Huggingface). Details on the components of LIDA are described in the paper here and in this tutorial notebook. See the project page here for updates!.

Note on Code Execution: To create visualizations, LIDA generates and executes code. Ensure that you run LIDA in a secure environment.

Features

lida components

LIDA treats visualizations as code and provides a clean api for generating, executing, editing, explaining, evaluating and repairing visualization code.


from lida import Manager, llm

lida = Manager(text_gen = llm("openai")) # palm, cohere ..
summary = lida.summarize("data/cars.csv")
goals = lida.goals(summary, n=2) # exploratory data analysis
charts = lida.visualize(summary=summary, goal=goals[0]) # exploratory data analysis

Getting Started

Setup and verify that your python environment is python 3.10 or higher (preferably, use Conda). Install the library via pip.

pip install -U lida 

LIDA depends on llmx and openai. If you had these libraries installed previously, consider updating them.

pip install -U llmx openai

Once requirements are met, setup your api key. Learn more about setting up keys for other LLM providers here.

export OPENAI_API_KEY=<your key>

Alternatively you can install the library in dev model by cloning this repo and running pip install -e . in the repository root.

Web API and UI

LIDA comes with an optional bundled ui and web api that you can explore by running the following command:

lida ui  --port=8080 --docs

Then navigate to http://localhost:8080/ in your browser. To view the web api specification, add the --docs option to the cli command, and navigate to http://localhost:8080/api/docs in your browser.

The fastest and recommended way to get started after installation will be to try out the web ui above or run the tutorial notebook.

Building the Web API and UI with Docker

The LIDA web api and ui can be setup using docker and the command below (ensure that you have docker installed, and you have set your OPENAI_API_KEY environment variable).

docker compose up

Data Summarization

Given a dataset, generate a compact summary of the data.

from lida import Manager

lida = Manager()
summary = lida.summarize("data/cars.json") # generate data summary

Goal Generation

Generate a set of visualization goals given a data summary.

goals = lida.goals(summary, n=5, persona="ceo with aerodynamics background") # generate goals

Add a persona parameter to generate goals based on that persona.

Visualization Generation

Generate, refine, execute and filter visualization code given a data summary and visualization goal. Note that LIDA represents visualizations as code.

# generate charts (generate and execute visualization code)
charts = lida.visualize(summary=summary, goal=goals[0], library="matplotlib") # seaborn, ggplot ..

Visualization Editing

Given a visualization, edit the visualization using natural language.

# modify chart using natural language
instructions = ["convert this to a bar chart", "change the color to red", "change y axes label to Fuel Efficiency", "translate the title to french"]
edited_charts = lida.edit(code=code,  summary=summary, instructions=instructions, library=library, textgen_config=textgen_config)

Visualization Explanation

Given a visualization, generate a natural language explanation of the visualization code (accessibility, data transformations applied, visualization code)

# generate explanation for chart
explanation = lida.explain(code=charts[0].code, summary=summary)

Visualization Evaluation and Repair

Given a visualization, evaluate to find repair instructions (which may be human authored, or generated), repair the visualization.

evaluations = lida.evaluate(code=code,  goal=goals[i], library=library)

Visualization Recommendation

Given a dataset, generate a set of recommended visualizations.

recommendations = lida.recommend(code=code, summary=summary, n=2,  textgen_config=textgen_config)

Infographic Generation [WIP]

Given a visualization, generate a data-faithful infographic. This methods should be considered experimental, and uses stable diffusion models from the peacasso library. You will need to run pip install lida[infographics] to install the required dependencies.

infographics = lida.infographics(visualization = charts[0].raster, n=3, style_prompt="line art")

Using LIDA with Locally Hosted LLMs (HuggingFace)

LIDA uses the llmx library as its interface for text generation. llmx supports multiple local models including HuggingFace models. You can use the huggingface models directly (assuming you have a gpu) or connect to an openai compatible local model endpoint e.g. using the excellent vllm library.

Using HuggingFace Models Directly

!pip3 install --upgrade llmx==0.0.17a0

# Restart the colab session

from lida import Manager
from llmx import  llm
text_gen = llm(provider="hf", model="uukuguy/speechless-llama2-hermes-orca-platypus-13b", device_map="auto")
lida = Manager(text_gen=text_gen)
# now you can call lida methods as above e.g.
sumamry = lida.summarize("data/cars.csv") # ....

Using an OpenAI Compatible Endpoint e.g. vllm server

from lida import Manager, TextGenerationConfig , llm

model_name = "uukuguy/speechless-llama2-hermes-orca-platypus-13b"
model_details = [{'name': model_name, 'max_tokens': 2596, 'model': {'provider': 'openai', 'parameters': {'model': model_name}}}]

# assuming your vllm endpoint is running on localhost:8000
text_gen = llm(provider="openai",  api_base="http://localhost:8000/v1", api_key="EMPTY", models=model_details)
lida = Manager(text_gen = text_gen)

Important Notes / Caveats / FAQs

Naturally, some of the limitations above could be addressed by a much welcomed PR.

Community Examples Built with LIDA

Documentation and Citation

A short paper describing LIDA (Accepted at ACL 2023 Conference) is available here.

@inproceedings{dibia2023lida,
    title = "{LIDA}: A Tool for Automatic Generation of Grammar-Agnostic Visualizations and Infographics using Large Language Models",
    author = "Dibia, Victor",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-demo.11",
    doi = "10.18653/v1/2023.acl-demo.11",
    pages = "113--126",
}

LIDA builds on insights in automatic generation of visualization from an earlier paper - Data2Vis: Automatic Generation of Data Visualizations Using Sequence to Sequence Recurrent Neural Networks.