add JiebaLinkExtractor for chinese doc extracting

[andyzhou1982]

Thank you for contributing to LangChain!

• PR title: "community: chinese doc extracting"

• PR message:

  • Description: add jieba_link_extractor.py for chinese doc extracting
  • Dependencies: jieba

• Add tests and docs: If you're adding a new integration, please include
  /doc/doc/integrations/providers/jieba.md
  /doc/doc/integrations/vectorstores/jieba_link_extractor.ipynb
  /libs/packages.yml

[vercel]

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

Name	Status	Preview	Comments	Updated (UTC)
langchain	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Mar 7, 2025 8:21pm

[andyzhou1982]

Hello,I had submitted a PR(#30132) but not passed.Ccurme suggested me provide a separate packages,so I published a package named langchain-jieba on pypi,and added relevant documents.I have not provided PR for Langchain before,I don't know how to get my PR approved

[ccurme]

Hi @andyzhou1982, thanks for this, it's great that you published the package.

We don't currently feature any usage of link extractors in the docs site. They are not in the list of integration components here either. I see you added this under vector stores, but this isn't a vector store.

There is some relevant documentation in the API reference here. So I updated this PR to add a link to langchain-jieba. It will look like this:

[andyzhou1982]

Hello,ccurme.When I submit the PR,I did not known which module would be the most appropriate,so I selected the vector store module, thank you.