| 123456789101112131415161718192021222324252627282930 |
- from pathlib import Path
- import sys
- sys.path.append(str(Path(__file__).resolve().parents[1]))
- from _chapter2_config import print_dependency_hint
- try:
- from langchain_text_splitters import MarkdownHeaderTextSplitter
- except ModuleNotFoundError as exc:
- print_dependency_hint(exc)
- raise SystemExit(1)
- def main() -> None:
- headers_to_split_on = [
- ("#", "Header 1"),
- ("##", "Header 2"),
- ("###", "Header 3"),
- ]
- markdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers_to_split_on)
- markdown_text = "# Header 1\nSome text\n## Header 2\nMore text\n### Header 3\nEven more text"
- docs = markdown_splitter.split_text(markdown_text)
- print(docs)
- if __name__ == "__main__":
- main()
|