Files
langchain-python/langchain
Matt Robinson 3c489be773 feat: optional post-processing for Unstructured loaders (#7850)
### Summary

Adds a post-processing method for Unstructured loaders that allows users
to optionally modify or clean extracted elements.

### Testing

```python
from langchain.document_loaders import UnstructuredFileLoader
from unstructured.cleaners.core import clean_extra_whitespace

loader = UnstructuredFileLoader(
    "./example_data/layout-parser-paper.pdf",
    mode="elements",
    post_processors=[clean_extra_whitespace],
)

docs = loader.load()
docs[:5]
```


### Reviewrs
  - @rlancemartin
  - @eyurtsev
  - @hwchase17
2023-07-17 12:13:05 -07:00
..
2023-07-17 07:09:51 -07:00
2023-07-15 10:04:29 -04:00
2023-07-11 10:11:21 -04:00
2023-07-07 02:42:28 -04:00
2023-07-17 07:30:48 -07:00
2023-07-07 19:57:59 -07:00
2023-07-02 22:38:59 -04:00
2023-06-08 21:15:14 -07:00
2023-06-03 16:48:48 -07:00
2022-11-12 11:22:32 -08:00
2023-07-07 02:42:28 -04:00