Harrison/unstructured structured (#1004)

docs/modules/document_loaders/examples/microsoft_word.ipynb

@@ -61,10 +61,61 @@
     "data"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "5d1472e9",
+   "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": 2,
+   "id": "93abf60b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredDocxLoader('example_data/fake.docx', mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "c35cdbcc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "fae2d730",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "61953c83",
+   "id": "961a7b1d",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -86,7 +137,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,