langchain_experimental.text_splitter.SemanticChunker

class langchain_experimental.text_splitter.SemanticChunker(embeddings: Embeddings, buffer_size: int = 1, add_start_index: bool = False, breakpoint_threshold_type: Literal['percentile', 'standard_deviation', 'interquartile'] = 'percentile', breakpoint_threshold_amount: Optional[float] = None, number_of_chunks: Optional[int] = None, sentence_split_regex: str = '(?<=[.?!])\\s+')

根据语义相似性分割文本。

参考自Greg Kamradt的优秀笔记： https://github.com/FullStackRetrieval-com/RetrievalTutorials/blob/main/tutorials/LevelsOfTextSplitting/5_Levels_Of_Text_Splitting.ipynb

所有功绩归于他。

在高层次上，这将文本分割为句子，然后分组为三句一组，然后合并在嵌入空间中相似的句子。

Methods

__init__(embeddings[, buffer_size, ...])
atransform_documents(documents, **kwargs)	异步转换文档列表。
create_documents(texts[, metadatas])	从文本列表创建文档。
split_documents(documents)	拆分文档.
split_text(text)
transform_documents(documents, **kwargs)	通过分割文档的序列来转换它们。

Parameters

• embeddings (Embeddings) –

• buffer_size (int) –

• add_start_index (bool) –

• breakpoint_threshold_type (Literal['percentile', 'standard_deviation', 'interquartile']) –

• breakpoint_threshold_amount (Optional[float]) –

• number_of_chunks (Optional[int]) –

• sentence_split_regex (str) –

__init__(embeddings: Embeddings, buffer_size: int = 1, add_start_index: bool = False, breakpoint_threshold_type: Literal['percentile', 'standard_deviation', 'interquartile'] = 'percentile', breakpoint_threshold_amount: Optional[float] = None, number_of_chunks: Optional[int] = None, sentence_split_regex: str = '(?<=[.?!])\\s+')

Parameters

• embeddings (Embeddings) –

• buffer_size (int) –

• add_start_index (bool) –

• breakpoint_threshold_type (Literal['percentile', 'standard_deviation', 'interquartile']) –

• breakpoint_threshold_amount (Optional[float]) –

• number_of_chunks (Optional[int]) –

• sentence_split_regex (str) –

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

异步转换文档列表。

参数：

documents：要转换的文档序列。

返回：

转换后的文档列表。

Parameters

• documents (Sequence[Document]) –

• kwargs (Any) –

Return type

Sequence[Document]

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

从文本列表创建文档。

Parameters

• texts (List[str]) –

• metadatas (Optional[List[dict]]) –

Return type

List[Document]

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

拆分文档.

Parameters

documents (Iterable[Document]) –

Return type

List[Document]

split_text(text: str) → List[str]

Parameters

text (str) –

Return type

List[str]

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

通过分割文档的序列来转换它们。

Parameters

• documents (Sequence[Document]) –

• kwargs (Any) –

Return type

Sequence[Document]

Examples using SemanticChunker

• This is a long document we can split up.