Utility ·
Custom Node
A node built from your own hand-written Python. Saved custom nodes show up in the add-node menu, and each one can read up to 8 inputs.
Also known as: Your own tool
How it works
A Custom Node is inserted from the library, which lists the nodes you saved with Save as custom node on a Code Gen or Intelligence node (Classify, Extract, Summarize, Generate). It carries that saved Python with it, reading its inputs as input_0 to input_7 and returning one result, and runs it exactly like a Code Gen node, so you can read and edit the code in the Code tab. The panel has no settings of its own; a node whose code is missing asks you to re-insert it from the library.
Inputs and outputs
Inputs
input_0— Anyinput_1— Anyinput_2— Anyinput_3— Anyinput_4— Anyinput_5— Anyinput_6— Anyinput_7— Any
Outputs
result— Any
Settings
Nothing to set in the Attributes panel: see How it works for where this node is set up.
Example
You generated a "Clean Address Data" step once and saved it as a custom node. In a new project, add it from the add-node menu, wire the raw address table into its first input, and run it; the same code produces the same cleaned columns without writing a prompt again.