---
title: "Split a document into chunks"
method: GET
path: "/v1/text/chunk"
tags: ["Text tools"]
---

# Split a document into chunks

`GET /v1/text/chunk`

## Request

- Base URL: `https://api.dharun.dev`
- URL: `https://api.dharun.dev/v1/text/chunk`
- Auth: none declared

Splits at headings, paragraphs, sentences and words, in that order of preference, so chunks stay readable. Markdown chunks never cross a heading and carry their heading path. Each chunk is an exact slice of the input with its character offsets.

## Query parameters

- `text` string
- `size` integer
- `overlap` integer
- `format` 'auto' | 'markdown' | 'text'

## Response `200`

Success

- Envelope
  - `data` unknown, required
  - `meta` object, required
    - `limit` integer
    - `note` string
    - `offset` integer
    - `source` object: Where the data came from and the credit its licence asks for.
      - `attribution` string
      - `licence` string
      - `name` string
      - `retrieved` string
      - `url` string
      - `version` string
    - `total` integer

## Other responses

- `400`: Error
- `404`: Error
- `429`: Error

---

[API](https://skmtc.dev/dharun/apis/india-api-free-open-source-apis-for-indian-data.md) · [All operations](https://skmtc.dev/dharun/apis/india-api-free-open-source-apis-for-indian-data/llms.txt) · [OpenAPI document](https://skmtc.dev/dharun/apis/india-api-free-open-source-apis-for-indian-data/revisions/ecd8b0ec7863?raw)