langchain/docs/docs/how_to/document_loader_markdown.ipynb

How to load Markdown

Markdown is a lightweight markup language for creating formatted text using a plain-text editor.

Here we cover how to load Markdown documents into LangChain Document objects that we can use downstream.

We will cover:

• Basic usage;
• Parsing of Markdown into elements such as titles, list items, and text.

LangChain implements an UnstructuredMarkdownLoader object which requires the Unstructured package. First we install it:

In [19]:

# !pip install "unstructured[md]"

Basic usage will ingest a Markdown file to a single document. Here we demonstrate on LangChain's readme:

In [1]:

from langchain_community.document_loaders import UnstructuredMarkdownLoader
from langchain_core.documents import Document

markdown_path = "../../../../README.md"
loader = UnstructuredMarkdownLoader(markdown_path)

data = loader.load()
assert len(data) == 1
assert isinstance(data[0], Document)
readme_content = data[0].page_content
print(readme_content[:250])

🦜️🔗 LangChain

⚡ Build context-aware reasoning applications ⚡

Looking for the JS/TS library? Check out LangChain.js.

To help you ship LangChain apps to production faster, check out LangSmith. 
LangSmith is a unified developer platform for building,

Retain Elements

Under the hood, Unstructured creates different "elements" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying mode="elements".

In [2]:

loader = UnstructuredMarkdownLoader(markdown_path, mode="elements")

data = loader.load()
print(f"Number of documents: {len(data)}\n")

for document in data[:2]:
    print(f"{document}\n")

Number of documents: 65

page_content='🦜️🔗 LangChain' metadata={'source': '../../../../README.md', 'last_modified': '2024-04-29T13:40:19', 'page_number': 1, 'languages': ['eng'], 'filetype': 'text/markdown', 'file_directory': '../../../..', 'filename': 'README.md', 'category': 'Title'}

page_content='⚡ Build context-aware reasoning applications ⚡' metadata={'source': '../../../../README.md', 'last_modified': '2024-04-29T13:40:19', 'page_number': 1, 'languages': ['eng'], 'parent_id': 'c3223b6f7100be08a78f1e8c0c28fde1', 'filetype': 'text/markdown', 'file_directory': '../../../..', 'filename': 'README.md', 'category': 'NarrativeText'}

Note that in this case we recover three distinct element types:

In [3]:

print(set(document.metadata["category"] for document in data))

{'Title', 'NarrativeText', 'ListItem'}