SentenceTransformersTokenTextSplitter#

class langchain_text_splitters.sentence_transformers.SentenceTransformersTokenTextSplitter(
chunk_overlap: int = 50,
model_name: str = 'sentence-transformers/all-mpnet-base-v2',
tokens_per_chunk: int | None = None,
**kwargs: Any,
)[source]#

Splitting text to tokens using sentence model tokenizer.

Create a new TextSplitter.

Methods

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

Create a new TextSplitter.

atransform_documents(documents, **kwargs)

Asynchronously transform a list of documents.

count_tokens(*, text)

Counts the number of tokens in the given text.

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)

Splits the input text into smaller components by splitting text on tokens.

transform_documents(documents, **kwargs)

Transform sequence of documents by splitting them.
Parameters:

  • chunk_overlap (int)

  • model_name (str)

  • tokens_per_chunk (Optional[int])

  • kwargs (Any)

__init__(
chunk_overlap: int = 50,
model_name: str = 'sentence-transformers/all-mpnet-base-v2',
tokens_per_chunk: int | None = None,
**kwargs: Any,
) → None[source]#

Create a new TextSplitter.

Parameters:

  • chunk_overlap (int)

  • model_name (str)

  • tokens_per_chunk (int | None)

  • kwargs (Any)

Return type:

None

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

Asynchronously transform a list of documents.

Parameters:

  • documents (Sequence[Document]) – A sequence of Documents to be transformed.

  • kwargs (Any)

Returns:

A sequence of transformed Documents.

Return type:

Sequence[Document]

count_tokens(
*,
text: str,
) → int[source]#

Counts the number of tokens in the given text.

This method encodes the input text using a private _encode method and calculates the total number of tokens in the encoded result.

Parameters:

text (str) – The input text for which the token count is calculated.

Returns:

The number of tokens in the encoded text.

Return type:

int

create_documents(
texts: list[str],
metadatas: list[dict[Any, Any]] | None = None,
) → List[Document]#

Create documents from a list of texts.

Parameters:

  • texts (list[str])

  • metadatas (list[dict[Any, Any]] | None)

Return type:

List[Document]

classmethod from_huggingface_tokenizer(
tokenizer: Any,
**kwargs: Any,
) → TextSplitter#

Text splitter that uses HuggingFace tokenizer to count length.

Parameters:

  • tokenizer (Any)

  • kwargs (Any)

Return type:

TextSplitter

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

Text splitter that uses tiktoken encoder to count length.

Parameters:

  • encoding_name (str)

  • model_name (str | None)

  • allowed_special (Literal['all'] | ~typing.AbstractSet[str])

  • disallowed_special (Literal['all'] | ~typing.Collection[str])

  • kwargs (Any)

Return type:

TS

split_documents(
documents: Iterable[Document],
) → List[Document]#

Split documents.

Parameters:

documents (Iterable[Document])

Return type:

List[Document]

split_text(
text: str,
) → List[str][source]#

Splits the input text into smaller components by splitting text on tokens.

This method encodes the input text using a private _encode method, then strips the start and stop token IDs from the encoded result. It returns the processed segments as a list of strings.

Parameters:

text (str) – The input text to be split.

Returns:

A list of string components derived from the input text after encoding and processing.

Return type:

List[str]

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

Transform sequence of documents by splitting them.

Parameters:

  • documents (Sequence[Document])

  • kwargs (Any)

Return type:

Sequence[Document]

Examples using SentenceTransformersTokenTextSplitter