Template·Text & Data

Chunk a Transcript for Indexing

Name: NodeTool
Author: NodeTool

Split a long passage into overlapping windows the way a RAG ingest does, then count them. `length` and `overlap` are counted in WORDS, not characters — a 90 here would swallow this whole passage into one chunk. Overlap is the point: a boundary landing mid-sentence loses the claim that straddles it, so neighbouring chunks share a tail. Counting needs Collection first, because Count consumes a stream and a list handed to it arrives as a single item.

Download NodeTool How to run it

The workflow

Workflow EditorChunk a Transcript for Indexing

String

The keeper climbed the stair each evening. The lamp needed winding twice a night. By the third winter the mechanism had worn, and the light…

Code

Text

Collection

Items

Count

Input Item

Output

Nodes in this workflow

6 nodes · 5 types

Output
nodetool.output.Output
×2
Code
nodetool.code.Code
Collection
nodetool.control.Collection
Count
nodetool.control.Count
String
nodetool.constant.String

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 Chunk a Transcript for Indexing 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.