如何按字符递归分割文本
这个文本分割器是推荐用于通用文本的。它通过一个字符列表进行参数化。它会尝试按顺序在这些字符上分割,直到块足够小。默认列表是["\n\n", "\n", " ", ""]
。这样做的效果是尽可能保持所有段落(然后是句子,然后是单词)在一起,因为这些通常似乎是语义上最强的文本片段。
- 文本如何分割:按字符列表。
- 块大小的测量方式:按字符数。
下面我们展示示例用法。
要直接获取字符串内容,请使用.split_text
。
要创建LangChain Document 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 Reference:RecursiveCharacterTextSplitter
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.']
让我们来看看上面为RecursiveCharacterTextSplitter
设置的参数:
chunk_size
: 块的最大大小,大小由length_function
决定。chunk_overlap
: 块之间的目标重叠。重叠的块有助于在上下文被分割时减少信息丢失。length_function
: 确定块大小的函数。is_separator_regex
: 分隔符列表(默认为["\n\n", "\n", " ", ""]
)是否应被解释为正则表达式。
从没有词边界的语言中分割文本
一些书写系统没有词边界,例如中文、日文和泰文。使用默认的分隔符列表["\n\n", "\n", " ", ""]
来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,你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),以及表意句号"。
"(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 ",
",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
)