community[patch]: Load list of files using UnstructuredFileLoader (#16216)

- **Description:** Updated `_get_elements()` function of
`UnstructuredFileLoader `class to check if the argument self.file_path
is a file or list of files. If it is a list of files then it iterates
over the list of file paths, calls the partition function for each one,
and appends the results to the elements list. If self.file_path is not a
list, it calls the partition function as before.
  
  - **Issue:** Fixed #15607,
  - **Dependencies:** NA
  - **Twitter handle:** NA

Co-authored-by: H161961 <Raunak.Raunak@Honeywell.com>

docs/docs/integrations/document_loaders/unstructured_file.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "2886982e",
    "metadata": {},
    "outputs": [],
@@ -100,6 +100,54 @@
     "docs[0].page_content[:400]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "b4ab0a79",
+   "metadata": {},
+   "source": [
+    "### Load list of files"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "092d9a0b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "files = [\"./example_data/whatsapp_chat.txt\", \"./example_data/layout-parser-paper.pdf\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f841c4f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredFileLoader(files)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "993c240b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5ce4ff07",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs[0].page_content[:400]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "7874d01d",
@@ -495,7 +543,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.10"
+   "version": "3.9.0"
   }
  },
  "nbformat": 4,

libs/community/langchain_community/document_loaders/unstructured.py

@@ -170,7 +170,13 @@ class UnstructuredFileLoader(UnstructuredBaseLoader):
     def _get_elements(self) -> List:
         from unstructured.partition.auto import partition
 
-        return partition(filename=self.file_path, **self.unstructured_kwargs)
+        if isinstance(self.file_path, list):
+            elements = []
+            for file in self.file_path:
+                elements.extend(partition(filename=file, **self.unstructured_kwargs))
+            return elements
+        else:
+            return partition(filename=self.file_path, **self.unstructured_kwargs)
 
     def _get_metadata(self) -> dict:
         return {"source": self.file_path}

libs/community/tests/integration_tests/document_loaders/test_unstructured.py

@@ -28,6 +28,23 @@ def test_unstructured_loader_with_post_processor() -> None:
     assert docs[0].page_content.endswith("THE END!")
 
 
+def test_unstructured_file_loader_multiple_files() -> None:
+    """Test unstructured loader."""
+    file_paths = [
+        os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper.pdf"),
+        os.path.join(EXAMPLE_DOCS_DIRECTORY, "whatsapp_chat.txt"),
+    ]
+
+    loader = UnstructuredFileLoader(
+        file_path=file_paths,
+        strategy="fast",
+        mode="elements",
+    )
+    docs = loader.load()
+
+    assert len(docs) > 1
+
+
 def test_unstructured_api_file_loader() -> None:
     """Test unstructured loader."""
     file_path = os.path.join(EXAMPLE_DOCS_DIRECTORY, "layout-parser-paper.pdf")