mirror of
https://github.com/hwchase17/langchain.git
synced 2025-05-18 21:41:24 +00:00
b023f0c0f2
This creates a new kind of text splitter for markdown files. The user can supply a set of headers that they want to split the file on. We define a new text splitter class, `MarkdownHeaderTextSplitter`, that does a few things: (1) For each line, it determines the associated set of user-specified headers (2) It groups lines with common headers into splits See notebook for example usage and test cases. |
||
|---|---|---|
| .. | ||
| document_loaders/examples | ||
| retrievers/examples | ||
| text_splitters | ||
| vectorstores | ||
| document_loaders.rst | ||
| getting_started.ipynb | ||
| retrievers.rst | ||
| text_splitters.rst | ||
| vectorstores.rst | ||