[Community] : Added SentenceWindowRetriever

[rsk2327]

Thank you for contributing to LangChain!

• [x] PR title: "package: description"

Description : Updated TextSplitter to include a new add_chunk_id argument to add a chunk_id variable into document metadata

This is a prerequisite for implementing the Sentence Window Retriever broadly across all databases as it helps easily identify neighboring chunks of text from the same text source

• [x] Add tests and docs This is a simple argument addition thats False by default and has basic logic. Specific unit tests might not be necessary

• [x] Lint and test: Run make format, make lint and make test from the root of the package(s) you've modified.

If no one reviews your PR within a few days, please @-mention one of baskaryan, efriis, eyurtsev, hwchase17.

[vercel[bot]]

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

1 Ignored Deployment

| Name | Status | Preview | Comments | Updated (UTC) | | :--- | :----- | :------ | :------- | :------ | | **langchain** | ⬜️ Ignored ([Inspect](https://vercel.com/langchain/langchain/exyK57mhjfJ6Scx9j7d1x2o3sKEN)) | [Visit Preview](https://langchain-git-fork-rsk2327-master-langchain.vercel.app) | | May 3, 2024 4:33pm |

[rsk2327]

@eyurtsev @baskaryan This metadata variable is a prerequisite for setting up the new implementation of the Sentence Window Retrieval method.

[rsk2327]

@hwchase17 @efriis Can i get a review on this?