mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-19 21:33:31 -04:00
be68f6f8ce
### Summary Adds an `UnstructuredRSTLoader` for loading [reStructuredText](https://en.wikipedia.org/wiki/ReStructuredText) file. ### Testing ```python from langchain.document_loaders import UnstructuredRSTLoader loader = UnstructuredRSTLoader( file_path="example_data/README.rst", mode="elements" ) docs = loader.load() print(docs[0]) ``` ### Reviewers - @hwchase17 - @rlancemartin - @eyurtsev
23 lines
737 B
Python
23 lines
737 B
Python
"""Loader that loads RST files."""
|
|
from typing import Any, List
|
|
|
|
from langchain.document_loaders.unstructured import (
|
|
UnstructuredFileLoader,
|
|
validate_unstructured_version,
|
|
)
|
|
|
|
|
|
class UnstructuredRSTLoader(UnstructuredFileLoader):
|
|
"""Loader that uses unstructured to load RST files."""
|
|
|
|
def __init__(
|
|
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
|
|
):
|
|
validate_unstructured_version(min_unstructured_version="0.7.5")
|
|
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
|
|
|
|
def _get_elements(self) -> List:
|
|
from unstructured.partition.rst import partition_rst
|
|
|
|
return partition_rst(filename=self.file_path, **self.unstructured_kwargs)
|