如何按字符递归分割文本
此 文本分割器 是用于通用文本的推荐选择。它通过一个字符列表进行参数化,并尝试按顺序在这些字符处进行分割,直到块的大小足够小。默认列表为 ["\n\n", "\n", " ", ""]。这样做会尽可能保持所有段落(然后是句子,再然后是单词)在一起,因为它们通常看起来是语义上联系最紧密的文本片段。
- 文本如何被分割:按字符列表。
- 块大小的测量方式:按字符数量计算。
下面我们将展示示例用法。
要直接获取字符串内容,请使用 .split_text。
要创建 LangChain 文档 对象(例如,用于下游任务),请使用 .create_documents。
%pip install -qU langchain-text-splitters
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])
API 参考:递归字符文本分割器
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.'
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.']
让我们看看上面为RecursiveCharacterTextSplitter设置的参数:
chunk_size: 块的最大大小,其中大小由length_function确定。chunk_overlap: 块之间的目标重叠。重叠的块有助于在上下文被分割成多个块时减少信息丢失。length_function: 确定分块大小的函数。is_separator_regex: 分隔符列表(默认为["\n\n", "\n", " ", ""])是否应被解释为正则表达式。
拆分无单词边界的语言文本
某些书写系统没有单词边界,例如中文、日文和泰文。使用默认的分隔符列表["\n\n", "\n", " ", ""]拆分文本可能导致单词在块之间被切断。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 全角句号"
.",Unicode 全角 句号"."(用于中文文本),以及 汉字全角句号 "。"(用于日语和中文) - 添加 零宽空格,用于泰语、缅甸语、高棉语和日语。
- 添加 ASCII 逗号 "
,",Unicode 全角逗号 ",",以及 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
)