Files
langchain-python/langchain/document_loaders/org_mode.py
T
Matt Robinson b24472eae3 feat: Add UnstructuredOrgModeLoader (#6842)
### Summary

Adds `UnstructuredOrgModeLoader` for processing
[Org-mode](https://en.wikipedia.org/wiki/Org-mode) documents.

### Testing

```python
from langchain.document_loaders import UnstructuredOrgModeLoader

loader = UnstructuredOrgModeLoader(
    file_path="example_data/README.org", mode="elements"
)
docs = loader.load()
print(docs[0])
```

### Reviewers

- @rlancemartin
- @eyurtsev
- @hwchase17
2023-06-27 16:34:17 -07:00

23 lines
751 B
Python

"""Loader that loads Org-Mode files."""
from typing import Any, List
from langchain.document_loaders.unstructured import (
UnstructuredFileLoader,
validate_unstructured_version,
)
class UnstructuredOrgModeLoader(UnstructuredFileLoader):
"""Loader that uses unstructured to load Org-Mode files."""
def __init__(
self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
):
validate_unstructured_version(min_unstructured_version="0.7.9")
super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
def _get_elements(self) -> List:
from unstructured.partition.org import partition_org
return partition_org(filename=self.file_path, **self.unstructured_kwargs)