upstage[patch] : fix error handling in Layout Analysis parser (#22054)

This pull request addresses and fixes exception handling in the
UpstageLayoutAnalysisParser and enhances the test coverage by adding
error exception tests for the document loader. These improvements ensure
robust error handling and increase the reliability of the system when
dealing with external API calls and JSON responses.

### Changes Made
1. Fix Request Exception Handling:

- Issue: The existing implementation of UpstageLayoutAnalysisParser did
not properly handle exceptions thrown by the requests library, which
could lead to unhandled exceptions and potential crashes.
- Solution: Added comprehensive exception handling for
requests.RequestException to catch any request-related errors. This
includes logging the error details and raising a ValueError with a
meaningful error message.

2. Add Error Exception Tests for Document Loader:

- New Tests: Introduced new test cases to verify the robustness of the
UpstageLayoutAnalysisLoader against various error scenarios. The tests
ensure that the loader gracefully handles:
- RequestException: Simulates network issues or invalid API requests to
ensure appropriate error handling and user feedback.
- JSONDecodeError: Simulates scenarios where the API response is not a
valid JSON, ensuring the system does not crash and provides clear error
messaging.

libs/partners/upstage/langchain_upstage/layout_analysis_parsers.py

@@ -181,19 +181,22 @@ class UpstageLayoutAnalysisParser(BaseBlobParser):
 
             result = response.json().get("elements", [])
 
+            elements = [
+                element for element in result if element["category"] not in self.exclude
+            ]
+
+            return elements
+
         except requests.RequestException as req_err:
             # Handle any request-related exceptions
             print(f"Request Exception: {req_err}")
+            raise ValueError(f"Failed to send request: {req_err}")
         except json.JSONDecodeError as json_err:
             # Handle JSON decode errors
             print(f"JSON Decode Error: {json_err}")
             raise ValueError(f"Failed to decode JSON response: {json_err}")
 
-        elements = [
+        return []
-            element for element in result if element["category"] not in self.exclude
-        ]
-
-        return elements
 
     def _split_and_request(
         self,

libs/partners/upstage/tests/unit_tests/test_layout_analysis.py

@@ -1,7 +1,11 @@
+import json
 from pathlib import Path
 from typing import Any, Dict, get_args
+from unittest import TestCase
 from unittest.mock import MagicMock, Mock, patch
 
+import requests
+
 from langchain_upstage import UpstageLayoutAnalysisLoader
 from langchain_upstage.layout_analysis import OutputType, SplitType
 
@@ -205,3 +209,45 @@ def test_page_split_html_output(mock_post: Mock) -> None:
         assert document.metadata["page"] == MOCK_RESPONSE_JSON["elements"][i]["page"]
         assert document.metadata["type"] == "html"
         assert document.metadata["split"] == "page"
+
+
+@patch("requests.post")
+def test_request_exception(mock_post: Mock) -> None:
+    mock_post.side_effect = requests.RequestException("Mocked request exception")
+
+    loader = UpstageLayoutAnalysisLoader(
+        file_path=EXAMPLE_PDF_PATH,
+        output_type="html",
+        split="page",
+        api_key="valid_api_key",
+        exclude=[],
+    )
+
+    with TestCase.assertRaises(TestCase(), ValueError) as context:
+        loader.load()
+
+    assert "Failed to send request: Mocked request exception" == str(context.exception)
+
+
+@patch("requests.post")
+def test_json_decode_error(mock_post: Mock) -> None:
+    mock_response = Mock()
+    mock_response.status_code = 200
+    mock_response.json.side_effect = json.JSONDecodeError("Expecting value", "", 0)
+    mock_post.return_value = mock_response
+
+    loader = UpstageLayoutAnalysisLoader(
+        file_path=EXAMPLE_PDF_PATH,
+        output_type="html",
+        split="page",
+        api_key="valid_api_key",
+        exclude=[],
+    )
+
+    with TestCase.assertRaises(TestCase(), ValueError) as context:
+        loader.load()
+
+    assert (
+        "Failed to decode JSON response: Expecting value: line 1 column 1 (char 0)"
+        == str(context.exception)
+    )