[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:data-formulator":3},"\u003Ch1>\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fmicrosoft\u002Fdata-formulator\u002FHEAD\u002Fpublic\u002Ffavicon.ico\" alt=\"Data Formulator icon\" width=\"28\" \u002F> \n  Data Formulator: AI-powered Data Visualization\n\u003C\u002Fh1>\u003Cp align=\"center\">\n  🪄 Explore data with visualizations, powered by AI agents.\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdata-formulator.ai\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F🚀_Try_Online_Demo-data--formulator.ai-F59E0B?style=for-the-badge\" alt=\"Try Online Demo\" \u002F>\u003C\u002Fa>\n   \n  \u003Ca href=\"#get-started\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F💻_Install_Locally-uvx_|_pip-3776AB?style=for-the-badge\" alt=\"Install Locally\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fdata_formulator\u002F\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fdata_formulator.svg?label=pypi%3A%20data_formulator\" alt=\"PyPI\" \u002F>\u003C\u002Fa> \n  \u003Ca href=\"https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg\" alt=\"License: MIT\" \u002F>\u003C\u002Fa> \n  \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=GfTE2FLyMrs\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FYouTube-white?logo=youtube&logoColor=%23FF0000\" alt=\"YouTube\" \u002F>\u003C\u002Fa> \n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdata-formulator\u002Factions\u002Fworkflows\u002Fpython-build.yml\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdata-formulator\u002Factions\u002Fworkflows\u002Fpython-build.yml\u002Fbadge.svg\" alt=\"build\" \u002F>\u003C\u002Fa> \n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FmYCZMQKYZb\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdiscord-chat-green?logo=discord\" alt=\"Discord\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\n\u003Ch2>Why Data Formulator?\u003C\u002Fh2>\n\u003Cp>Working with data is hard for two simple reasons:\u003C\u002Fp>\n\u003Col>\n\u003Cli>\u003Cstrong>Data lives everywhere.\u003C\u002Fstrong> Connecting agents to files, databases,\nwarehouses, and BI tools takes time. It is even harder when agents start\nanswering before the relationships between data sources are clear.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Questions evolve as you explore.\u003C\u002Fstrong> Each answer can lead to follow-up\nquestions, comparisons, and new directions. A long chat history makes it\nhard to see where you are and how you got there.\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cp>Data Formulator provides one visual workspace for exploring and analyzing data:\u003C\u002Fp>\n\u003Col>\n\u003Cli>\u003Cstrong>Data connectors\u003C\u002Fstrong> give agents a common way to connect to different data\nsources and maintains a data memory to remember the relationships between them.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Data Threads\u003C\u002Fstrong> let you branch into different questions, compare paths,\nand use visualizations to discover deeper insights without losing context.\u003C\u002Fli>\n\u003C\u002Fol>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F8e4f8a08-6423-4227-a1f7-559e0126ce31\" rel=\"nofollow ugc noopener\">https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F8e4f8a08-6423-4227-a1f7-559e0126ce31\u003C\u002Fa>\u003C\u002Fp>\n\u003Cblockquote>\n\u003Cp>[!TIP]\n\u003Cstrong>Love the charts?\u003C\u002Fstrong> They're built on \u003Ca href=\"https:\u002F\u002Fmicrosoft.github.io\u002Fflint-chart\u002F\" rel=\"nofollow ugc noopener\">\u003Cstrong>Flint\u003C\u002Fstrong>\u003C\u002Fa>. It's an open-source visualization language that compiles compact chart specs into polished visualizations.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Ch2>News 🔥🔥🔥\u003C\u002Fh2>\n\u003Cp>[08-15-2026] \u003Cstrong>Data Formulator 0.8 beta 1\u003C\u002Fstrong> (\u003Ccode>0.8.0b1\u003C\u002Fcode>) introduces:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>One unified flow:\u003C\u002Fstrong> load data, ask questions, review results, and branch in the Data Thread.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>More data sources:\u003C\u002Fstrong> use files, local folders, databases, and platforms such as Databricks.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Better charts:\u003C\u002Fstrong> explore more Flint-powered charts, recommendations, themes, and styling tools.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cblockquote>\n\u003Cp>Preview with \u003Ccode>pip install --pre data_formulator==0.8.0b1\u003C\u002Fcode> or \u003Ccode>uvx data_formulator@0.8.0b1\u003C\u002Fcode>.\nInstall the latest stable release (0.7) with \u003Ccode>pip install data_formulator\u003C\u002Fcode> or run instantly with \u003Ccode>uvx data_formulator\u003C\u002Fcode>.\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp>See the \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fdata-formulator\u002Fblob\u002FHEAD\u002FCHANGELOG.md\" rel=\"nofollow ugc noopener\">changelog\u003C\u002Fa> for release details.\u003C\u002Fp>\n\u003Ch2>Previous Updates\u003C\u002Fh2>\n\u003Cp>Here are milestones that lead to the current design:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>v0.7\u003C\u002Fstrong> (05-28-2026): Turn ANY data into insights in five steps — connect governed data sources, load via agents, explore with the unified \u003Ccode>DataAgent\u003C\u002Fcode> + Data Thread, refine 30+ chart types (semantic chart engine powered by \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fflint-chart\" rel=\"nofollow ugc noopener\">Flint\u003C\u002Fa>) with a style-refinement agent, and share as reports. Plus persistent sessions & workspaces and a multilingual (English\u002FChinese) UI\u003C\u002Fli>\n\u003C\u002Ful>\n",1787445486866]