跳到主要内容
文本分割器是通用文本推荐的分割器。它通过字符列表进行参数化。它会尝试按顺序使用这些字符进行分割,直到块足够小。默认列表是["\n\n", "\n", " ", ""]。这样做的效果是尽可能地将所有段落(然后是句子,然后是单词)保持在一起,因为这些通常被认为是语义上最强的相关文本片段。
  1. 文本如何分割:通过字符列表。
  2. 块大小如何衡量:通过字符数。
下面我们展示了示例用法。
pip install -qU langchain-text-splitters
要直接获取字符串内容,请使用.split_text 要创建 LangChain Document 对象(例如,用于下游任务),请使用.create_documents
from langchain_text_splitters import RecursiveCharacterTextSplitter

# Load example document
with open("state_of_the_union.txt") as f:
    state_of_the_union = f.read()

text_splitter = RecursiveCharacterTextSplitter(
    # Set a really small chunk size, just to show.
    chunk_size=100,
    chunk_overlap=20,
    length_function=len,
    is_separator_regex=False,
)
texts = text_splitter.create_documents([state_of_the_union])
print(texts[0])
print(texts[1])
page_content='Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and'
page_content='of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.'
print(text_splitter.split_text(state_of_the_union)[:2])
['Madam Speaker, Madam Vice President, our First Lady and Second Gentleman. Members of Congress and',
 'of Congress and the Cabinet. Justices of the Supreme Court. My fellow Americans.']
让我们回顾一下为RecursiveCharacterTextSplitter设置的参数
  • chunk_size:块的最大大小,大小由length_function确定。
  • chunk_overlap:块之间的目标重叠。重叠块有助于在上下文在块之间划分时减轻信息丢失。
  • length_function:确定块大小的函数。
  • is_separator_regex:分隔符列表(默认为["\n\n", "\n", " ", ""])是否应解释为正则表达式。

分割没有词边界的语言文本

某些书写系统没有词边界,例如中文、日文和泰文。使用默认分隔符列表["\n\n", "\n", " ", ""]分割文本可能会导致单词在块之间被分割。为了保持单词的完整性,您可以覆盖分隔符列表以包含额外的标点符号
  • 添加 ASCII 句号“.”、Unicode 全角句号“”(用于中文文本)和表意句号”(用于日文和中文)
  • 添加用于泰语、缅甸语、高棉语和日语的零宽度空格
  • 添加 ASCII 逗号“,”、Unicode 全角逗号“”和 Unicode 表意逗号“
text_splitter = RecursiveCharacterTextSplitter(
    separators=[
        "\n\n",
        "\n",
        " ",
        ".",
        ",",
        "\u200b",  # Zero-width space
        "\uff0c",  # Fullwidth comma
        "\u3001",  # Ideographic comma
        "\uff0e",  # Fullwidth full stop
        "\u3002",  # Ideographic full stop
        "",
    ],
    # Existing args
)

以编程方式连接这些文档到 Claude、VSCode 等,通过 MCP 获取实时答案。
© . This site is unofficial and not affiliated with LangChain, Inc.