community: add MarkItDown document loader

[Simon-Stone]

Description:
This pull request introduces a new document loader, MarkItDownLoader, to the langchain_community library. The changes include adding the new loader to the appropriate initialization and attribute handling files, implementing the loader class, and creating a test for the loader.

New document loader implementation:

• libs/community/langchain_community/document_loaders/__init__.py: Added import and registration for MarkItDownLoader in the document loaders module. [1] [2] [3]
• libs/community/langchain_community/document_loaders/markitdown.py: Implemented the MarkItDownLoader class, which uses the MarkItDown library to load files as Markdown documents.

Testing:

• libs/community/tests/integration_tests/document_loaders/test_markitdown_loader.py: Added an integration test for the MarkItDownLoader to ensure it correctly loads and processes documents.

Issue: Discussion #28958

Dependencies: markitdown

TODO:

• an example notebook showing its use. It lives in docs/docs/integrations directory.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

1 Skipped Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchain	⬜️ Ignored (Inspect)	Visit Preview		Dec 29, 2024 10:25pm

[efriis]

Hey! This adds a net-new community integration or feature, which has been replaced by dedicated integration packages. I'll close this PR, and would recommend reopening with just docs updates, as well as registering your package in libs/packages.yml! We'll be able to review simple PRs that only modify these two things much faster :)

Here's the guide, and if you have questions, feel free to leave them in the comments on those pages so others can see them! https://python.langchain.com/docs/contributing/how_to/integrations/