Clean and Rank a Table
A real four-step data chain rather than a single op: import, drop duplicate rows, sort by volume, then keep the top slice. Each step is inspectable on its own, which is the argument for doing this as a graph instead of one opaque query.

The workflow
Nodes in this workflow
5 nodes · 5 types- Drop Duplicatesnodetool.data.DropDuplicates
- Import CSVnodetool.data.ImportCSV
- Outputnodetool.output.Output
- Slicenodetool.data.Slice
- Sort By Columnnodetool.data.SortByColumn
How to run it
- 01
Download NodeTool Studio
Install the free desktop app for macOS, Windows, or Linux. It runs on your own machine, no account required to start.
- 02
Open the Clean and Rank a Table template
Browse the built-in template library inside Studio and open this workflow onto the canvas. Every node is already wired up.
- 03
Add your keys
Connect any model providers this workflow calls with your own API keys, or point it at local models.
- 04
Run and remix
Hit Run to execute the graph and watch results stream in. Swap models, edit prompts, or rewire nodes to make it yours.
Run Clean and Rank a Table on your machine
Free, open source, and yours to run. Download Studio, open the template, and run it with your own keys.








