langchain.text_splitter.RecursiveCharacterTextSplitter

class langchain.text_splitter.RecursiveCharacterTextSplitter(separators: Optional[List[str]] = None, keep_separator: bool = True, is_separator_regex: bool = False, **kwargs: Any)

Splitting text by recursively look at characters.

Recursively tries to split by different characters to find one that works.

Create a new TextSplitter.

Methods

__init__([separators, keep_separator, ...])	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_language(language, **kwargs)
from_tiktoken_encoder([encoding_name, ...])	Text splitter that uses tiktoken encoder to count length.
get_separators_for_language(language)
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__(separators: Optional[List[str]] = None, keep_separator: bool = True, is_separator_regex: bool = False, **kwargs: Any) → None

Create a new TextSplitter.

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

Asynchronously transform a sequence of documents by splitting them.

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

Create documents from a list of texts.

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

Text splitter that uses HuggingFace tokenizer to count length.

classmethod from_language(language: Language, **kwargs: Any) → RecursiveCharacterTextSplitter

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

Text splitter that uses tiktoken encoder to count length.

static get_separators_for_language(language: Language) → List[str]

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

Split documents.

split_text(text: str) → List[str]

Split text into multiple components.

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

Transform sequence of documents by splitting them.

Examples using RecursiveCharacterTextSplitter

• RePhraseQueryRetriever

• Cohere Reranker

• Ollama

• Zep

• your local model path

• Loading documents from a YouTube url

• Source Code

• Set env var OPENAI_API_KEY or load from a .env file:

• Set env var OPENAI_API_KEY or load from a .env file

• Question Answering

• Perform context-aware text splitting

• Use local LLMs

• QA using Activeloop’s DeepLake

• !pip install bs4

• MultiVector Retriever

• MultiQueryRetriever

• Parent Document Retriever

• MarkdownHeaderTextSplitter