Merge pull request #408 from truefoundry/S1LV3RJ1NX-patch-1

Update unstructured_io.py for empty text
truefoundry · Nov 11, 2024 · 0c447a7 · 0c447a7
2 parents 2522503 + c860df4
commit 0c447a7
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/backend/modules/parsers/unstructured_io.py b/backend/modules/parsers/unstructured_io.py
@@ -87,6 +87,8 @@ async def get_chunks(self, filepath: str, metadata: dict, **kwargs):
             parsed_data = response.json()
             for payload in parsed_data:
                 text = payload["text"]
+                if not text:
+                    continue
                 metadata = payload["metadata"]
                 final_texts.append(Document(page_content=text, metadata=metadata))
             return final_texts