MarkdownHeaderTextSplitter
MarkdownHeaderTextSplitter
from langchain_text_splitters import MarkdownHeaderTextSplitter
splitter = MarkdownHeaderTextSplitter(
headers_to_split_on=[("#", "h1"), ("##", "h2"), ("###", "h3")],
)
docs = splitter.split_text(md_text)
print(docs[0].metadata) # {'h1': ..., 'h2': ...}
print(docs[0].page_content[:80])超长章节可在标题切分后再对每节做递归切分，两级组合兼顾结构与粒度。