feat: add UnstructuredExcelLoader for .xlsx and .xls files (#5617)

# Unstructured Excel Loader

Adds an `UnstructuredExcelLoader` class for `.xlsx` and `.xls` files.
Works with `unstructured>=0.6.7`. A plain text representation of the
Excel file will be available under the `page_content` attribute in the
doc. If you use the loader in `"elements"` mode, an HTML representation
of the Excel file will be available under the `text_as_html` metadata
key. Each sheet in the Excel document is its own document.

### Testing

```python
from langchain.document_loaders import UnstructuredExcelLoader

loader = UnstructuredExcelLoader(
    "example_data/stanley-cups.xlsx",
    mode="elements"
)
docs = loader.load()
```

## Who can review?

@hwchase17
@eyurtsev

docs/modules/indexes/document_loaders/examples/excel.ipynb

@@ -0,0 +1,79 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "22a849cc",
+   "metadata": {},
+   "source": [
+    "# Microsoft Excel\n",
+    "\n",
+    "The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files. The page content will be the raw text of the Excel file. If you use the loader in `\"elements\"` mode, an HTML representation of the Excel file will be available in the document metadata under the `text_as_html` key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e6616e3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredExcelLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a654e4d9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='\\n  \\n    \\n      Team\\n      Location\\n      Stanley Cups\\n    \\n    \\n      Blues\\n      STL\\n      1\\n    \\n    \\n      Flyers\\n      PHI\\n      2\\n    \\n    \\n      Maple Leafs\\n      TOR\\n      13\\n    \\n  \\n', metadata={'source': 'example_data/stanley-cups.xlsx', 'filename': 'stanley-cups.xlsx', 'file_directory': 'example_data', 'filetype': 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', 'page_number': 1, 'page_name': 'Stanley Cups', 'text_as_html': '<table border=\"1\" class=\"dataframe\">\\n  <tbody>\\n    <tr>\\n      <td>Team</td>\\n      <td>Location</td>\\n      <td>Stanley Cups</td>\\n    </tr>\\n    <tr>\\n      <td>Blues</td>\\n      <td>STL</td>\\n      <td>1</td>\\n    </tr>\\n    <tr>\\n      <td>Flyers</td>\\n      <td>PHI</td>\\n      <td>2</td>\\n    </tr>\\n    <tr>\\n      <td>Maple Leafs</td>\\n      <td>TOR</td>\\n      <td>13</td>\\n    </tr>\\n  </tbody>\\n</table>', 'category': 'Table'})"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader = UnstructuredExcelLoader(\n",
+    "    \"example_data/stanley-cups.xlsx\",\n",
+    "    mode=\"elements\"\n",
+    ")\n",
+    "docs = loader.load()\n",
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ab94bde",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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

@@ -32,6 +32,7 @@ from langchain.document_loaders.email import (
 )
 from langchain.document_loaders.epub import UnstructuredEPubLoader
 from langchain.document_loaders.evernote import EverNoteLoader
+from langchain.document_loaders.excel import UnstructuredExcelLoader
 from langchain.document_loaders.facebook_chat import FacebookChatLoader
 from langchain.document_loaders.figma import FigmaFileLoader
 from langchain.document_loaders.gcs_directory import GCSDirectoryLoader
@@ -223,6 +224,7 @@ __all__ = [
     "UnstructuredAPIFileLoader",
     "UnstructuredEPubLoader",
     "UnstructuredEmailLoader",
+    "UnstructuredExcelLoader",
     "UnstructuredFileIOLoader",
     "UnstructuredFileLoader",
     "UnstructuredHTMLLoader",

langchain/document_loaders/excel.py

@@ -0,0 +1,22 @@
+"""Loader that loads Microsoft Excel files."""
+from typing import Any, List
+
+from langchain.document_loaders.unstructured import (
+    UnstructuredFileLoader,
+    validate_unstructured_version,
+)
+
+
+class UnstructuredExcelLoader(UnstructuredFileLoader):
+    """Loader that uses unstructured to load Microsoft Excel files."""
+
+    def __init__(
+        self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
+    ):
+        validate_unstructured_version(min_unstructured_version="0.6.7")
+        super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
+
+    def _get_elements(self) -> List:
+        from unstructured.partition.xlsx import partition_xlsx
+
+        return partition_xlsx(filename=self.file_path, **self.unstructured_kwargs)

tests/integration_tests/document_loaders/test_excel.py

@@ -0,0 +1,15 @@
+import os
+from pathlib import Path
+
+from langchain.document_loaders import UnstructuredExcelLoader
+
+EXAMPLE_DIRECTORY = file_path = Path(__file__).parent.parent / "examples"
+
+
+def test_unstructured_excel_loader() -> None:
+    """Test unstructured loader."""
+    file_path = os.path.join(EXAMPLE_DIRECTORY, "stanley-cups.xlsx")
+    loader = UnstructuredExcelLoader(str(file_path))
+    docs = loader.load()
+
+    assert len(docs) == 1