Data Formulator

<h1 align="center"> <img src="https://raw.githubusercontent.com/microsoft/data-formulator/main/public/favicon.ico" alt="Data Formulator icon" width="28">&nbsp; Data Formulator: AI-powered Data Visualization </h1> <p align="center"> 🪄 Explore data with visualizations, powered by AI agents. </p> <p align="center"> &nbsp; </p> <p align="center"> <a href="https://github.com/microsoft/data-formulator/actions/workflows/python-build.yml"><img src="https://github.com/microsoft/data-formulator/actions/workflows/python-build.yml/badge.svg" alt="build"></a>&ensp; </p> <!-- [](https://codespaces.new/microsoft/data-formulator?quickstart=1) --> <!-- https://github.com/user-attachments/assets/8ca57b68-4d7a-42cb-bcce-43f8b1681ce2 --> <kbd> <img src="https://github.com/user-attachments/assets/3ffb15aa-93ce-42b8-92cf-aaf321f9a06a"> </kbd>

News 🔥🔥🔥

[03-02-2026] Data Formulator 0.7 (alpha) — More charts, new experience, enterprise-ready

• 📊 30 chart types with a new semantic chart engine (area, streamgraph, candlestick, pie, radar, maps, and more).
• 💬 Hybrid chat + data thread — chat woven into the exploration timeline with lineage, previews, and reasoning.
• 🤖 Unified DataAgent replacing four separate agents, plus new recommendation and insight agents.
• 🏗️ Workspace / Data Lake — persistent, identity-based data management with local and Azure Blob backends.
• 🔒 Security hardening — code signing, sandboxed execution, authentication, and rate limiting.
• 📦 UV-first build — reproducible builds via uv.lock; uv sync + uv run data_formulator.
• 📝 Detailed writeup on the new architecture coming soon — stay tuned!

Previous Updates

Here are milestones that lead to the current design:

• v0.6 (Demo): Real-time insights from live data — connect to URLs and databases with automatic refresh
• uv support: Faster installation with uv — uvx data_formulator or uv pip install data_formulator
• v0.5.1 (Demo): Community data loaders, US Map & Pie Chart, editable reports, snappier UI
• v0.5: Vibe with your data, in control — agent mode, data extraction, reports
• v0.2.2 (Demo): Goal-driven exploration with agent recommendations and performance improvements
• v0.2.1.3/4 (Readme | Demo): External data loaders (MySQL, PostgreSQL, MSSQL, Azure Data Explorer, S3, Azure Blob)
• v0.2 (Demos): Large data support with DuckDB integration
• v0.1.7 (Demos): Dataset anchoring for cleaner workflows
• v0.1.6 (Demo): Multi-table support with automatic joins
• Model Support: OpenAI, Azure, Ollama, Anthropic via LiteLLM (feedback)
• Python Package: Easy local installation (try it)
• Visualization Challenges: Test your skills (challenges)
• Data Extraction: Parse data from images and text (demo)
• Initial Release: Blog | Video

<details> <summary><b>View detailed update history</b></summary>

• [07-10-2025] Data Formulator 0.2.2: Start with an analysis goal

  • Some key frontend performance updates.
  • You can start your exploration with a goal, or, tab and see if the agent can recommend some good exploration ideas for you. Demo

• [05-13-2025] Data Formulator 0.2.1.3/4: External Data Loader

  • We introduced external data loader class to make import data easier. Readme and Demo
    • Current data loaders: MySQL, Azure Data Explorer (Kusto), Azure Blob and Amazon S3 (json, parquet, csv).
    • [07-01-2025] Updated with: Postgresql, mssql.
  • Call for action link:
    • Users: let us know which data source you'd like to load data from.
    • Developers: let's build more data loaders.

• [04-23-2025] Data Formulator 0.2: working with large data 📦📦📦

  • Explore large data by:
    1. Upload large data file to the local database (powered by DuckDB).
    2. Use drag-and-drop to specify charts, and Data Formulator dynamically fetches data from the database to create visualizations (with ⚡️⚡️⚡️ speeds).
    3. Work with AI agents: they generate SQL queries to transform the data to create rich visualizations!
    4. Anchor the result / follow up / create a new branch / join tables; let's dive deeper.
  • Checkout the demos at [https://github.com/microsoft/data-formulator/releases/tag/0.2]
  • Improved overall system performance, and enjoy the updated derive concept functionality.

• [03-20-2025] Data Formulator 0.1.7: Anchoring ⚓︎

  • Anchor an intermediate dataset, so that followup data analysis are built on top of the anchored data, not the original one.
  • Clean a data and work with only the cleaned data; create a subset from the original data or join multiple data, and then go from there. AI agents will be less likely to get confused and work faster. ⚡️⚡️
  • Check out the demos at [https://github.com/microsoft/data-formulator/releases/tag/0.1.7]
  • Don't forget to update Data Formulator to test it out!

• [02-20-2025] Data Formulator 0.1.6 released!

  • Now supports working with multiple datasets at once! Tell Data Formulator which data tables you would like to use in the encoding shelf, and it will figure out how to join the tables to create a visualization to answer your question. 🪄
  • Checkout the demo at [https://github.com/microsoft/data-formulator/releases/tag/0.1.6].
  • Update your Data Formulator to the latest version to play with the new features.

• [02-12-2025] More models supported now!

  • Now supports OpenAI, Azure, Ollama, and Anthropic models (and more powered by LiteLLM);
  • Models with strong code generation and instruction following capabilities are recommended (gpt-4o, claude-3-5-sonnet etc.);
  • You can store API keys in .env to avoid typing them every time (copy .env.template to .env and fill in your keys).
  • Let us know which models you have good/bad experiences with, and what models you would like to see supported! [comment here]

• [11-07-2024] Minor fun update: data visualization challenges!

  • We added a few visualization challenges with the sample datasets. Can you complete them all? [try them out!]
  • Comment in the issue when you did, or share your results/questions with others! [comment here]

• [10-11-2024] Data Formulator python package released!

  • You can now install Data Formulator using Python and run it locally, easily. [check it out].
  • Our Codespaces configuration is also updated for fast start up ⚡️. [try it now!]
  • New experimental feature: load an image or a messy text, and ask AI to parse and clean it for you(!). [demo]

• [10-01-2024] Initial release of Data Formulator, check out our [blog] and [video]!

</details>

Overview

Data Formulator is a Microsoft Research prototype for data exploration with visualizations powered by AI agents.

Data Formulator enables analysts to iteratively explore and visualize data. Started with data in any format (screenshot, text, csv, or database), users can work with AI agents with a novel blended interface that combines user interface interactions (UI) and natural language (NL) inputs to communicate their intents, control branching exploration directions, and create reports to share their insights.

Get Started

Play with Data Formulator with one of the following options:

• Option 1: Install via uv (recommended)

  uv is an extremely fast Python package manager. If you have uv installed, you can run Data Formulator directly without any setup:

  # Run data formulator directly (no install needed)
  uvx data_formulator
  

  Or install it in a project/virtual environment:

  # Install data_formulator
  uv pip install data_formulator
  
  # Run data formulator
  python -m data_formulator
  

  Data Formulator will be automatically opened in the browser at http://localhost:5567.