Files
langchain/docs
Matt Robinson 2f15c11b87 feat: document loader for MS Word documents (#1282)
### Summary

Adds a document loader for MS Word Documents. Works with both `.docx`
and `.doc` files as longer as the user has installed
`unstructured>=0.4.11`.

### Testing

The follow workflow test the loader for both `.doc` and `.docx` files
using example docs from the `unstructured` repo.

#### `.docx`

```python
from langchain.document_loaders import UnstructuredWordDocumentLoader

filename = "../unstructured/example-docs/fake.docx"
loader = UnstructuredWordDocumentLoader(filename)
loader.load()
```

#### `.doc`

```python
from langchain.document_loaders import UnstructuredWordDocumentLoader

filename = "../unstructured/example-docs/fake.doc"
loader = UnstructuredWordDocumentLoader(filename)
loader.load()
```
2023-02-24 08:26:19 -08:00
..
2023-02-15 23:07:01 -08:00
2023-02-06 20:30:03 -08:00
2023-02-20 22:54:26 -08:00
2023-01-14 07:39:29 -08:00
2023-01-02 08:24:09 -08:00
2023-02-19 23:14:50 -08:00
2023-01-02 08:24:09 -08:00
2023-01-29 20:49:35 -08:00