langchain_text_splitters.character
.RecursiveCharacterTextSplitterΒΆ
- class langchain_text_splitters.character.RecursiveCharacterTextSplitter(separators: Optional[List[str]] = None, keep_separator: bool = True, is_separator_regex: bool = False, **kwargs: Any)[source]ΒΆ
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 list of documents.
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.
- Parameters
separators (Optional[List[str]]) β
keep_separator (bool) β
is_separator_regex (bool) β
kwargs (Any) β
- __init__(separators: Optional[List[str]] = None, keep_separator: bool = True, is_separator_regex: bool = False, **kwargs: Any) None [source]ΒΆ
Create a new TextSplitter.
- Parameters
separators (Optional[List[str]]) β
keep_separator (bool) β
is_separator_regex (bool) β
kwargs (Any) β
- Return type
None
- async atransform_documents(documents: Sequence[Document], **kwargs: Any) Sequence[Document] ΒΆ
Asynchronously transform a list of documents.
- create_documents(texts: List[str], metadatas: Optional[List[dict]] = None) List[Document] ΒΆ
Create documents from a list of texts.
- Parameters
texts (List[str]) β
metadatas (Optional[List[dict]]) β
- Return type
List[Document]
- classmethod from_huggingface_tokenizer(tokenizer: Any, **kwargs: Any) TextSplitter ΒΆ
Text splitter that uses HuggingFace tokenizer to count length.
- Parameters
tokenizer (Any) β
kwargs (Any) β
- Return type
- classmethod from_language(language: Language, **kwargs: Any) RecursiveCharacterTextSplitter [source]ΒΆ
- Parameters
language (Language) β
kwargs (Any) β
- Return type
- 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 ΒΆ
Text splitter that uses tiktoken encoder to count length.
- Parameters
encoding_name (str) β
model_name (Optional[str]) β
allowed_special (Union[Literal['all'], ~typing.AbstractSet[str]]) β
disallowed_special (Union[Literal['all'], ~typing.Collection[str]]) β
kwargs (Any) β
- Return type
TS
- static get_separators_for_language(language: Language) List[str] [source]ΒΆ
- Parameters
language (Language) β
- Return type
List[str]