以编程方式使用文档

许多聊天或问答应用程序在嵌入和向量存储之前会先将输入文档分块。

这些笔记 来自 Pinecone 的内容提供了一些有用的提示：

When a full paragraph or document is embedded, the embedding process considers both the overall context and the relationships between the sentences and phrases within the text. This can result in a more comprehensive vector representation that captures the broader meaning and themes of the text.

如前所述，分块通常旨在将具有共同上下文的文本保持在一起。考虑到这一点，我们可能希望特别尊重文档本身的结构。例如，markdown 文件按标题组织。在特定标题组内创建块是一个直观的思路。为了解决这个挑战，我们可以使用 MarkdownHeaderTextSplitter。这将按指定的标题集分割 markdown 文件。

例如，如果我们想要分割这个 markdown：

md = '# Foo\n\n ## Bar\n\nHi this is Jim  \nHi this is Joe\n\n ## Baz\n\n Hi this is Molly'

我们可以指定要分割的标题：

[("#", "Header 1"),("##", "Header 2")]

内容按共同标题分组或分割：

{'content': 'Hi this is Jim  \nHi this is Joe', 'metadata': {'Header 1': 'Foo', 'Header 2': 'Bar'}}
{'content': 'Hi this is Molly', 'metadata': {'Header 1': 'Foo', 'Header 2': 'Baz'}}

让我们看看下面的一些示例。

基本用法：

pip install -qU langchain-text-splitters
from langchain_text_splitters import MarkdownHeaderTextSplitter
markdown_document = "# Foo\n\n    ## Bar\n\nHi this is Jim\n\nHi this is Joe\n\n ### Boo \n\n Hi this is Lance \n\n ## Baz\n\n Hi this is Molly"

headers_to_split_on = [
    ("#", "Header 1"),
    ("##", "Header 2"),
    ("###", "Header 3"),
]

markdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on)
md_header_splits = markdown_splitter.split_text(markdown_document)
md_header_splits
[Document(metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}, page_content='Hi this is Jim  \nHi this is Joe'),
 Document(metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'}, page_content='Hi this is Lance'),
 Document(metadata={'Header 1': 'Foo', 'Header 2': 'Baz'}, page_content='Hi this is Molly')]
type(md_header_splits[0])
langchain_core.documents.base.Document

默认情况下， MarkdownHeaderTextSplitter 会从输出块的内容中剥离正在分割的标题。可以通过设置来禁用此功能 strip_headers = False.

markdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on, strip_headers=False)
md_header_splits = markdown_splitter.split_text(markdown_document)
md_header_splits
[Document(metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}, page_content='# Foo  \n## Bar  \nHi this is Jim  \nHi this is Joe'),
 Document(metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'}, page_content='### Boo  \nHi this is Lance'),
 Document(metadata={'Header 1': 'Foo', 'Header 2': 'Baz'}, page_content='## Baz  \nHi this is Molly')]

如何将 markdown 行作为单独的文档返回

默认情况下， MarkdownHeaderTextSplitter 会根据中指定的标题聚合行 headers_to_split_on。我们可以通过指定来禁用此功能 return_each_line:

markdown_splitter = MarkdownHeaderTextSplitter(
    headers_to_split_on,
    return_each_line=True,
)
md_header_splits = markdown_splitter.split_text(markdown_document)
md_header_splits
[Document(metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}, page_content='Hi this is Jim'),
 Document(metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}, page_content='Hi this is Joe'),
 Document(metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'}, page_content='Hi this is Lance'),
 Document(metadata={'Header 1': 'Foo', 'Header 2': 'Baz'}, page_content='Hi this is Molly')]

请注意，此处标题信息保留在 metadata 每个文档中。

如何限制块大小：

在每个 markdown 组中，我们可以应用任何我们想要的分词器，例如 RecursiveCharacterTextSplitter，它允许对块大小进行进一步控制。

markdown_document = "# Intro \n\n    ## History \n\n Markdown[9] is a lightweight markup language for creating formatted text using a plain-text editor. John Gruber created Markdown in 2004 as a markup language that is appealing to human readers in its source code form.[9] \n\n Markdown is widely used in blogging, instant messaging, online forums, collaborative software, documentation pages, and readme files. \n\n ## Rise and divergence \n\n As Markdown popularity grew rapidly, many Markdown implementations appeared, driven mostly by the need for \n\n additional features such as tables, footnotes, definition lists,[note 1] and Markdown inside HTML blocks. \n\n #### Standardization \n\n From 2012, a group of people, including Jeff Atwood and John MacFarlane, launched what Atwood characterised as a standardisation effort. \n\n ## Implementations \n\n Implementations of Markdown are available for over a dozen programming languages."

headers_to_split_on = [
    ("#", "Header 1"),
    ("##", "Header 2"),
]

# MD splits
markdown_splitter = MarkdownHeaderTextSplitter(
    headers_to_split_on=headers_to_split_on, strip_headers=False
)
md_header_splits = markdown_splitter.split_text(markdown_document)

# Char-level splits
from langchain_text_splitters import RecursiveCharacterTextSplitter

chunk_size = 250
chunk_overlap = 30
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=chunk_size, chunk_overlap=chunk_overlap
)

# Split
splits = text_splitter.split_documents(md_header_splits)
splits
[Document(metadata={'Header 1': 'Intro', 'Header 2': 'History'}, page_content='# Intro  \n## History  \nMarkdown[9] is a lightweight markup language for creating formatted text using a plain-text editor. John Gruber created Markdown in 2004 as a markup language that is appealing to human readers in its source code form.[9]'),
 Document(metadata={'Header 1': 'Intro', 'Header 2': 'History'}, page_content='Markdown is widely used in blogging, instant messaging, online forums, collaborative software, documentation pages, and readme files.'),
 Document(metadata={'Header 1': 'Intro', 'Header 2': 'Rise and divergence'}, page_content='## Rise and divergence  \nAs Markdown popularity grew rapidly, many Markdown implementations appeared, driven mostly by the need for  \nadditional features such as tables, footnotes, definition lists,[note 1] and Markdown inside HTML blocks.'),
 Document(metadata={'Header 1': 'Intro', 'Header 2': 'Rise and divergence'}, page_content='#### Standardization  \nFrom 2012, a group of people, including Jeff Atwood and John MacFarlane, launched what Atwood characterised as a standardisation effort.'),
 Document(metadata={'Header 1': 'Intro', 'Header 2': 'Implementations'}, page_content='## Implementations  \nImplementations of Markdown are available for over a dozen programming languages.')]

Troubleshooting: chunk_overlap 似乎不适用

  • - 基于标题的分隔之后（例如， MarkdownHeaderTextSplitter），使用 **split_documents(docs)** （不是 split_text），以便应用重叠 **在每个部分内** 并且每个部分的元数据（标题）在块上被保留。
  • - 重叠仅在 **单个部分** 超过 chunk_size 并被分割成多个块时出现。
  • - 重叠 **不会跨越** section/document boundaries (e.g., # H1 → ## H2).
  • - 如果标题变成一个很小的第一个块，请考虑设置 strip_headers to True ，以便标题行不会成为一个独立的块。
  • - If your text lacks newlines/spaces, keep a fallback "" in separators ，以便分词器仍然可以分割和应用重叠。