---
title: "Semantic Chunker"
method: POST
path: "/v1/chunk/semantic"
---

# Semantic Chunker

`POST /v1/chunk/semantic`

Splits text into chunks based on semantic similarity, ensuring that related content stays together in the same chunk.

## Response `200`

Successful Response: A list of `SemanticChunk` objects.

- SemanticChunkSchema[] — A list containing `SemanticChunk` objects, detailing segments and sentences with optional embeddings.
  - `text` string — The actual text content of the chunk.
  - `start_index` integer — The starting character index of the chunk within the original input text.
  - `end_index` integer — The ending character index (exclusive) of the chunk within the original input text.
  - `token_count` integer — The number of tokens in this specific chunk, according to the tokenizer used.
  - `sentences` SemanticSentenceSchema[] — List of `SemanticSentence` objects contained within this chunk.
    - `text` string — The actual text content of the sentence.
    - `start_index` integer — The starting character index of the sentence within the original input text.
    - `end_index` integer — The ending character index (exclusive) of the sentence within the original input text.
    - `token_count` integer — The number of tokens in this specific sentence, according to the tokenizer used.
    - `embedding` number[], nullable — Optional embedding vector (list of floats) for the sentence.

## Changes

- **2025-04-27** `bc64e1775952` — 1 info
  - endpoint added
- **2025-04-27** `5c8e44804806` — 1 breaking
  - api removed without deprecation
- **2025-04-27** `1762a3ecb81b` — 3 info
  - the `delim` request property default value changed from ` , ., !, ?` to `., !, ?, `
  - the `min_characters_per_sentence` request property default value changed from `1` to `12`
  - the `min_chunk_size` request property default value `2` was removed
- **2025-04-27** `7e3cb743a9ed` — 1 warning
  - removed the request property `text`
- **2025-04-22** `b5fe83cf70c6` — 1 breaking, 1 info
  - removed the media type `application/json` from the request body
  - added the media type `multipart/form-data` to the request body

[Full history](https://skmtc.dev/feyninc/apis/chonkie-api/changes/v1/chunk/semantic/post.md)

---

[API](https://skmtc.dev/feyninc/apis/chonkie-api.md) · [All operations](https://skmtc.dev/feyninc/apis/chonkie-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/feyninc/chonkie-api/revisions/8a6665f478db/schema)