■ MarkdownHeaderTextSplitter 클래스의 생성자에서 return_each_line 인자를 사용해 마크다운 라인별로 문서 리스트를 구하는 방법을 보여준다.
▶ main.py
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 |
from langchain_text_splitters import MarkdownHeaderTextSplitter codeString = "# 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" headerListToSplitOn = [ ("#" , "Header 1"), ("##" , "Header 2"), ("###", "Header 3") ] markdownHeaderTextSplitter = MarkdownHeaderTextSplitter(headerListToSplitOn, return_each_line = True) documentList = markdownHeaderTextSplitter.split_text(codeString) for document in documentList: print(document) """ page_content='Hi this is Jim' metadata={'Header 1': 'Foo', 'Header 2': 'Bar'} page_content='Hi this is Joe' metadata={'Header 1': 'Foo', 'Header 2': 'Bar'} page_content='Hi this is Lance' metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'} page_content='Hi this is Molly' metadata={'Header 1': 'Foo', 'Header 2': 'Baz'} """ |
▶ requirements.txt
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 |
annotated-types==0.7.0 certifi==2024.6.2 charset-normalizer==3.3.2 idna==3.7 jsonpatch==1.33 jsonpointer==3.0.0 langchain-core==0.2.10 langchain-text-splitters==0.2.2 langsmith==0.1.82 orjson==3.10.5 packaging==24.1 pydantic==2.7.4 pydantic_core==2.18.4 PyYAML==6.0.1 requests==2.32.3 tenacity==8.4.2 typing_extensions==4.12.2 urllib3==2.2.2 |
※ pip install langchain-text-splitters 명령을 실행했다.