Text chunker
Split long text into chunks of a maximum size for search and RAG pipelines, breaking at natural boundaries.
Input
Result
Fill in the input and press Run.
Your input is processed in memory and then discarded. It is not stored or logged. Even so, don't paste live passwords or keys into any online tool.
Use it from code or an agent
curl -s https://setget.net/v1/tools/text-chunk \
-H 'Content-Type: application/json' \
-d '{"input":{"text":"First paragraph here.\n\nSecond paragraph is a little longer. It has two sentences.","max_chars":40}}'
import json, urllib.request
body = {'input': {'text': 'First paragraph here.\n\nSecond paragraph is a little longer. It has two sentences.', 'max_chars': 40}}
request = urllib.request.Request("https://setget.net/v1/tools/text-chunk", json.dumps(body).encode(),
{"Content-Type": "application/json"})
print(json.load(urllib.request.urlopen(request))["result"])
const response = await fetch("https://setget.net/v1/tools/text-chunk", {
method: "POST",
headers: {"Content-Type": "application/json"},
body: JSON.stringify({"input":{"text":"First paragraph here.\n\nSecond paragraph is a little longer. It has two sentences.","max_chars":40}}),
});
console.log((await response.json()).result);
Tool: run_tool
Arguments:
{
"slug": "text-chunk",
"input": {
"text": "First paragraph here.\n\nSecond paragraph is a little longer. It has two sentences.",
"max_chars": 40
}
}
{
"input": {
"text": "First paragraph here.\n\nSecond paragraph is a little longer. It has two sentences.",
"max_chars": 40
}
}
Endpoint: POST /v1/tools/text-chunk. Over MCP: run_tool with slug: "text-chunk".
Machine-readable: input schema, Markdown. Connect an agent.
Inputs
| Name | Type | Required | What it does |
|---|---|---|---|
text |
string | yes | The text to split. |
max_chars |
integer | no | Longest chunk allowed, in characters. Default: 1000. From 1 to 1000000. |
overlap |
integer | no | Characters repeated from the end of one chunk at the start of the next. At most half of max_chars. Default: 0. From 0 to 500000. |
Examples
Input
{
"text": "First paragraph here.\n\nSecond paragraph is a little longer. It has two sentences.",
"max_chars": 40
}Result
{
"count": 3,
"chunks": [
{
"index": 0,
"start": 0,
"end": 21,
"text": "First paragraph here."
},
{
"index": 1,
"start": 23,
"end": 59,
"text": "Second paragraph is a little longer."
},
{
"index": 2,
"start": 60,
"end": 81,
"text": "It has two sentences."
}
]
}With overlap
Input
{
"text": "alpha beta gamma delta epsilon zeta",
"max_chars": 16,
"overlap": 6
}Result
{
"count": 4,
"chunks": [
{
"index": 0,
"start": 0,
"end": 16,
"text": "alpha beta gamma"
},
{
"index": 1,
"start": 11,
"end": 22,
"text": "gamma delta"
},
{
"index": 2,
"start": 17,
"end": 30,
"text": "delta epsilon"
},
{
"index": 3,
"start": 31,
"end": 35,
"text": "zeta"
}
]
}Questions
- Where does it break?
- At the last paragraph break in the second half of the chunk. If there is none, at the last sentence end, then at the last space, and only then in the middle of a word.
- What are start and end?
- Character positions in the original text, counting from 0. "end" is the position just after the chunk, and the chunk has no spaces or line breaks at its edges.
- How do I size chunks in tokens?
- As a rule of thumb one token is about 4 characters of English, so 2,000 characters is roughly 500 tokens.
- Is there a limit on the number of chunks?
- Yes, 10,000. Raise max_chars if you reach it.
Related tools
- Token estimatorEstimate how many LLM tokens a text uses, from its characters and words. An approximation, not an exact count.
token-estimate - Truncate textShorten long text to a maximum length, cutting from the middle, start or end and marking the cut with an ellipsis.
truncate-middle - Wrap and indent textHard-wrap text to a line width, add or remove indentation, and put a prefix such as "> " on every line.
wrap-indent - Apply a patchApply a unified diff to a text and get the patched result, with clear errors when a hunk does not fit.
patch-apply - Case converterConvert text between lower, UPPER, Title, Sentence, camelCase, PascalCase, snake_case, kebab-case and more.
case-convert - Escape and unescape textEscape or unescape text for HTML, URLs, JSON strings, shell commands, regular expressions and CSV fields.
escape-unescape