pip install langchain-text-splitters

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)print(md_header_splits)

[Document(page_content='Hi this is Jim\nHi this is Joe', metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}), Document(page_content='Hi this is Lance', metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'}), Document(page_content='Hi this is Molly', metadata={'Header 1': 'Foo', 'Header 2': 'Baz'})]

markdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on, strip_headers=False)md_header_splits = markdown_splitter.split_text(markdown_document)print(md_header_splits)

[Document(page_content='# Foo\n## Bar\nHi this is Jim\nHi this is Joe', metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}), Document(page_content='### Boo\nHi this is Lance', metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'}), Document(page_content='## Baz\nHi this is Molly', metadata={'Header 1': 'Foo', 'Header 2': 'Baz'})]

markdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on,return_each_line=True,)md_header_splits = markdown_splitter.split_text(markdown_document)print(md_header_splits)

[Document(page_content='Hi this is Jim', metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}), Document(page_content='Hi this is Joe', metadata={'Header 1': 'Foo', 'Header 2': 'Bar'}), Document(page_content='Hi this is Lance', metadata={'Header 1': 'Foo', 'Header 2': 'Bar', 'Header 3': 'Boo'}), Document(page_content='Hi this is Molly', metadata={'Header 1': 'Foo', 'Header 2': 'Baz'})]

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 splitsmarkdown_splitter = MarkdownHeaderTextSplitter(headers_to_split_on=headers_to_split_on, strip_headers=False)md_header_splits = markdown_splitter.split_text(markdown_document)
# Char-level splitsfrom langchain_text_splitters import RecursiveCharacterTextSplitter
chunk_size = 250chunk_overlap = 30text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
# Splitsplits = text_splitter.split_documents(md_header_splits)splits