Skip to content

Data Formulator 0.7-alpha 2

Choose a tag to compare

@Chenglong-MS Chenglong-MS released this 13 May 01:36
· 46 commits to main since this release
d370faf

Can't explain how exited we are. :) Data Formulator now supports persistent data connection (easy data loading), session management (easy switch and save sessions), full agentic experience, and ability to custom chart styles.

πŸ˜„ If you are one of the few reading this release note, please play with it! I might actually be really good. :)

  • play with it at https://data-formulator.ai/.
  • but for full experience, install it with pip install data-formulator==0.7.0a2 to test out.

The full release will come soon....

-- a message from @Chenglong-MS and @zhb-ai (also thanks to contributions from @WolffM @IAMkecheng)

A new chapter for AI-powered data exploration

  • πŸ”Œ Data connectors β€” first-class persistent connection to Superset, Kusto, Cosmos DB, MySQL, PostgreSQL, MSSQL, S3, Azure Blob, BigQuery, and more, with SSO, lazy catalog loading, search, and smart filters.
  • πŸ’¬ Conversational agent with thread memory β€” a unified DataAgent that weaves explanation, exploration, visualization, and recommendation into one fluid conversation, carrying context across turns so the agent stays in sync with your train of thought.
  • πŸ—‚οΈ Persistent session & workspace management β€” identity-isolated workspaces with local and Azure Blob backends; sessions persist across restarts with timestamps and sort.
  • πŸ“Š Expressive visualization β€” 30+ chart types via a new semantic chart engine (area, streamgraph, candlestick, pie, radar, maps, …), plus a chart style-refinement agent that turns rough charts into presentation-ready visuals: restyle in one click, refine typography, color, layout, and annotations through natural language.
  • πŸ“š Knowledge distillation (experimental) β€” agents distill reusable skills and experiences from your sessions into a shared knowledge library that informs future sessions.
image