K
pending
Microsoft's Data Formulator: The Open-Source AI Tool for Drag-and-Drop Data Analysis
Grounded / Real
Inflated / Uruttu
Original Content
Microsoft just open-sourced one of the best AI data analysis tools out there.
It’s called data-formulator.
Connect any source, CSV, Postgres, Bigquery, even a live URL, then build charts with a mix of drag-and-drop and plain english.
The AI agent writes the SQL and transforms underneath and hands you a chart you can actually edit, not a code dump.
- drag fields onto x/y/color and it builds the chart
- anchor a cleaned result so follow-ups don't drift back to raw data
- branch any chart to explore a variation
- connect live data with auto-refresh
Link: https://lnkd.in/es58xgrj
bring your own model key and it runs locally.
It’s called data-formulator.
Connect any source, CSV, Postgres, Bigquery, even a live URL, then build charts with a mix of drag-and-drop and plain english.
The AI agent writes the SQL and transforms underneath and hands you a chart you can actually edit, not a code dump.
- drag fields onto x/y/color and it builds the chart
- anchor a cleaned result so follow-ups don't drift back to raw data
- branch any chart to explore a variation
- connect live data with auto-refresh
Link: https://lnkd.in/es58xgrj
bring your own model key and it runs locally.
Validated Content
Data Formulator is an open-source AI-powered data analysis tool from Microsoft Research that connects to sources including CSV files and databases such as PostgreSQL and BigQuery. It combines drag-and-drop interaction with natural language input, using an AI agent to handle the underlying data transformations while producing charts that remain editable rather than static code output. Version 0.7 added persistent connectors across multiple databases, warehouses, and cloud storage systems, along with features to anchor a cleaned dataset for consistent follow-up queries and branch from any chart to explore variations. The tool supports multiple AI model providers, including OpenAI, Azure, Ollama, and Anthropic, and can be run locally using a user-supplied model key.