langchain.text_splitter.TextSplitter

class langchain.text_splitter.TextSplitter(chunk_size: int = 4000, chunk_overlap: int = 200, length_function: ~typing.Callable[[str], int] = <built-in function len>, keep_separator: bool = False, add_start_index: bool = False, strip_whitespace: bool = True)[source]

Interface for splitting text into chunks.

Create a new TextSplitter.

Parameters
  • chunk_size – Maximum size of chunks to return

  • chunk_overlap – Overlap in characters between chunks

  • length_function – Function that measures the length of given chunks

  • keep_separator – Whether to keep the separator in the chunks

  • add_start_index – If True, includes chunk’s start index in metadata

  • strip_whitespace – If True, strips whitespace from the start and end of every document

Methods

__init__([chunk_size, chunk_overlap, ...])

Create a new TextSplitter.

atransform_documents(documents, **kwargs)

Asynchronously transform a sequence of documents by splitting them.

create_documents(texts[, metadatas])

Create documents from a list of texts.

from_huggingface_tokenizer(tokenizer, **kwargs)

Text splitter that uses HuggingFace tokenizer to count length.

from_tiktoken_encoder([encoding_name, ...])

Text splitter that uses tiktoken encoder to count length.

split_documents(documents)

Split documents.

split_text(text)

Split text into multiple components.

transform_documents(documents, **kwargs)

Transform sequence of documents by splitting them.

__init__(chunk_size: int = 4000, chunk_overlap: int = 200, length_function: ~typing.Callable[[str], int] = <built-in function len>, keep_separator: bool = False, add_start_index: bool = False, strip_whitespace: bool = True) None[source]

Create a new TextSplitter.

Parameters
  • chunk_size – Maximum size of chunks to return

  • chunk_overlap – Overlap in characters between chunks

  • length_function – Function that measures the length of given chunks

  • keep_separator – Whether to keep the separator in the chunks

  • add_start_index – If True, includes chunk’s start index in metadata

  • strip_whitespace – If True, strips whitespace from the start and end of every document

async atransform_documents(documents: Sequence[Document], **kwargs: Any) Sequence[Document][source]

Asynchronously transform a sequence of documents by splitting them.

create_documents(texts: List[str], metadatas: Optional[List[dict]] = None) List[Document][source]

Create documents from a list of texts.

classmethod from_huggingface_tokenizer(tokenizer: Any, **kwargs: Any) TextSplitter[source]

Text splitter that uses HuggingFace tokenizer to count length.

classmethod from_tiktoken_encoder(encoding_name: str = 'gpt2', model_name: Optional[str] = None, allowed_special: Union[Literal['all'], AbstractSet[str]] = {}, disallowed_special: Union[Literal['all'], Collection[str]] = 'all', **kwargs: Any) TS[source]

Text splitter that uses tiktoken encoder to count length.

split_documents(documents: Iterable[Document]) List[Document][source]

Split documents.

abstract split_text(text: str) List[str][source]

Split text into multiple components.

transform_documents(documents: Sequence[Document], **kwargs: Any) Sequence[Document][source]

Transform sequence of documents by splitting them.