> ## Documentation Index
> Fetch the complete documentation index at: https://docs.chonkie.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Late Chunker

> Split text into chunks based on a late-bound token count

The **LateChunker** implements the late chunking strategy described in the [Late Chunking](https://arxiv.org/abs/2409.04701) paper. It builds on top of the `RecursiveChunker` and uses document-level embeddings to create more semantically rich chunk representations.

Instead of generating embeddings for each chunk independently, the LateChunker first encodes the entire text into a single embedding.
It then splits the text using recursive rules and derives each chunk’s embedding by averaging relevant parts of the
full document embedding. This allows each chunk to carry broader contextual information,
improving retrieval performance in RAG systems.

## API Reference

To use the `LateChunker` via the API, check out the [API reference documentation](../../api/chunkers/late-chunker).

## Installation

LateChunker requires the `sentence-transformers` library to be installed, and currently only supports SentenceTransformer models.
You can install it with:

The LateChunker uses `RecursiveRules` to determine how to chunk the text.
The rules are a list of `RecursiveLevel` objects, which define the delimiters and whitespace rules for each level of the recursive tree.
Find more information about the rules in the [Additional Information](#additional-information) section.

```bash theme={"system"}
pip install "chonkie[st]"
```

<Info>
  For installation instructions, see the [Installation
  Guide](/oss/installation).
</Info>

## Initialization

```python theme={"system"}
from chonkie import LateChunker

chunker = LateChunker(
    embedding_model="nomic-ai/modernbert-embed-base",
    chunk_size=2048,
    rules=RecursiveRules(),
    min_characters_per_chunk=24,
)
```

You can also initialize the LateChunker using a recipe. Recipes are pre-defined rules for common chunking tasks.
Find all available recipes on our Hugging Face Hub [here](https://huggingface.co/datasets/chonkie-ai/recipes).

```python theme={"system"}
from chonkie import LateChunker

# Initialize the late chunker to chunk Markdown
chunker = LateChunker.from_recipe("markdown", lang="en")

# Initialize the late chunker to chunk Hindi texts
chunker = LateChunker.from_recipe(lang="hi")
```

## Parameters

<ParamField path="embedding_model" type="str" default="nomic-ai/modernbert-embed-base">
  SentenceTransformer model to use for embedding
</ParamField>

<ParamField path="chunk_size" type="int" default="2048">
  Maximum number of tokens per chunk
</ParamField>

<ParamField path="rules" type="RecursiveRules" default="RecursiveRules()">
  Rules to use for chunking
</ParamField>

<ParamField path="min_characters_per_chunk" type="int" default="24">
  Minimum number of characters per sentence
</ParamField>

## Usage

### Single Text Chunking

```python theme={"system"}
text = """First paragraph about a specific topic.
Second paragraph continuing the same topic.
Third paragraph switching to a different topic.
Fourth paragraph expanding on the new topic."""

chunks = chunker(text)

for chunk in chunks:
    print(f"Chunk text: {chunk.text}")
    print(f"Token count: {chunk.token_count}")
    print(f"Embedding shape: {chunk.embedding.shape}")
```

### Batch Chunking

```python theme={"system"}
texts = [
    "First document about topic A...",
    "Second document about topic B..."
]

batch_chunks = chunker(texts)

for chunk in batch_chunks:
    print(f"Chunk text: {chunk.text}")
    print(f"Token count: {chunk.token_count}")
    print(f"Embedding shape: {chunk.embedding.shape}")
```

## Return Type

LateChunker returns chunks as `Chunk` objects:

```python theme={"system"}
@dataclass
class Chunk:
    text: str           # The chunk text
    start_index: int    # Starting position in original text
    end_index: int      # Ending position in original text
    token_count: int    # Number of tokens in chunk
    context: Optional[Context] = None    # Optional context metadata
    embedding: Union[list[float], "np.ndarray", None] = None  # Optional embedding vector
```

<Note>
  As of version 1.3.0, LateChunker returns the base `Chunk` type instead of the
  specialized `LateChunk` type. The embedding is automatically populated by the
  LateChunker during the chunking process.
</Note>

## Additional Information

LateChunker uses the `RecursiveRules` class to determine the chunking rules.
The rules are a list of `RecursiveLevel` objects, which define the delimiters and whitespace rules for each level of the recursive tree.

```python theme={"system"}
@dataclass
class RecursiveRules:
    rules: list[RecursiveLevel]

@dataclass
class RecursiveLevel:
    delimiters: Union[None, str, list[str]]
    whitespace: bool = False
    include_delim: Optional[Literal["prev", "next"]]  # Whether to include the delimiter in the previous chunk or the next chunk.
```

You can pass in custom rules to the LateChunker, or use the default ones.
Default rules are designed to be a good starting point for most documents, but you can customize them to your needs.

<Info>
  `RecursiveLevel` expects the list of custom delimiters to **not** include
  whitespace. If whitespace as a delimiter is required, you can set the
  `whitespace` parameter in the `RecursiveLevel` class to True. Note that if
  `whitespace = True`, you cannot pass a list of custom delimiters.
</Info>