This is an n8n community node that lets you chunk text using Chonkie for RAG and NLP pipelines.
n8n is a fair-code licensed workflow automation platform.
Installation
Operations
Compatibility
Usage
Resources
Follow the installation guide in the n8n community nodes documentation.
Or install directly:
npm install n8n-nodes-chonkieThe Chonkie node splits text into chunks using one of three strategies:
| Chunker | Description |
|---|---|
| Token Chunker | Splits text by token count with configurable overlap |
| Recursive Chunker | Hierarchy-aware splitting across paragraphs, sentences, and words |
| Fast Chunker | Ultra-fast WASM-based chunking with byte-level precision |
| Parameter | Chunkers | Description |
|---|---|---|
| Text to Chunk | All | The input text to split |
| Chunker Type | All | Strategy to use (token, recursive, fast) |
| Chunk Size | All | Maximum size of each chunk (tokens/characters) |
| Chunk Overlap | Token | Number of units to overlap between consecutive chunks |
| Delimiters | Fast | Characters used as split boundaries (e.g. \n.?) |
| Min Characters Per Chunk | Recursive | Minimum characters before merging a split |
Each chunk is emitted as a separate item with the following fields:
{
"text": "...",
"tokenCount": 42,
"startIndex": 0,
"endIndex": 128
}Compatible with n8n v1.60.0 or later.
- Add the Chonkie node to your workflow.
- Connect a node that produces text (e.g. HTTP Request, Read File).
- Set Text to Chunk to the field containing your text.
- Choose a Chunker Type and configure chunk size.
- Each resulting chunk flows to the next node as its own item — ready for embeddings, vector stores, or further processing.
The node also supports use as a tool in AI agent workflows (usableAsTool: true).