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()
```

docs/modules/document_loaders/examples/word_document.ipynb

@@ -0,0 +1,137 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "39af9ecd",
+   "metadata": {},
+   "source": [
+    "# Word Documents\n",
+    "\n",
+    "This covers how to load Word documents into a document format that we can use downstream."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "721c48aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredWordDocumentLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9d3d0e35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredWordDocumentLoader(\"fake.docx\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "06073f91",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "c9adc5cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "525d6b67",
+   "metadata": {},
+   "source": [
+    "## Retain Elements\n",
+    "\n",
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "064f9162",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredWordDocumentLoader(\"fake.docx\", mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "abefbbdb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a547c534",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'fake.docx', 'filename': 'fake.docx', 'category': 'Title'}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data[0]"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

langchain/document_loaders/__init__.py

@@ -36,6 +36,7 @@ from langchain.document_loaders.unstructured import (
 )
 from langchain.document_loaders.url import UnstructuredURLLoader
 from langchain.document_loaders.web_base import WebBaseLoader
+from langchain.document_loaders.word_document import UnstructuredWordDocumentLoader
 from langchain.document_loaders.youtube import YoutubeLoader
 
 __all__ = [
@@ -48,6 +49,7 @@ __all__ = [
     "GoogleDriveLoader",
     "UnstructuredHTMLLoader",
     "UnstructuredPowerPointLoader",
+    "UnstructuredWordDocumentLoader",
     "UnstructuredPDFLoader",
     "ObsidianLoader",
     "UnstructuredDocxLoader",

langchain/document_loaders/word_document.py

@@ -0,0 +1,43 @@
+"""Loader that loads word documents."""
+import os
+from typing import List
+
+from langchain.document_loaders.unstructured import UnstructuredFileLoader
+
+
+class UnstructuredWordDocumentLoader(UnstructuredFileLoader):
+    """Loader that uses unstructured to load word documents."""
+
+    def _get_elements(self) -> List:
+        from unstructured.__version__ import __version__ as __unstructured_version__
+        from unstructured.file_utils.filetype import FileType, detect_filetype
+
+        unstructured_version = tuple(
+            [int(x) for x in __unstructured_version__.split(".")]
+        )
+        # NOTE(MthwRobinson) - magic will raise an import error if the libmagic
+        # system dependency isn't installed. If it's not installed, we'll just
+        # check the file extension
+        try:
+            import magic  # noqa: F401
+
+            is_doc = detect_filetype(self.file_path) == FileType.DOC
+        except ImportError:
+            _, extension = os.path.splitext(self.file_path)
+            is_doc = extension == ".doc"
+
+        if is_doc and unstructured_version < (0, 4, 11):
+            raise ValueError(
+                f"You are on unstructured version {__unstructured_version__}. "
+                "Partitioning .doc files is only supported in unstructured>=0.4.11. "
+                "Please upgrade the unstructured package and try again."
+            )
+
+        if is_doc:
+            from unstructured.partition.doc import partition_doc
+
+            return partition_doc(filename=self.file_path)
+        else:
+            from unstructured.partition.docx import partition_docx
+
+            return partition_docx(filename=self.file_path)