Fix ingestion for case when no images field exists

app/backend/prepdocslib/searchmanager.py

@@ -471,28 +471,33 @@ async def update_content(self, sections: list[Section], url: Optional[str] = Non
 
         async with self.search_info.create_search_client() as search_client:
             for batch_index, batch in enumerate(section_batches):
-                documents = [
-                    {
+                documents = []
+                for section_index, section in enumerate(batch):
+                    image_fields = {}
+                    if self.search_images:
+                        image_fields = {
+                            "images": [
+                                {
+                                    "url": image.url,
+                                    "description": image.description,
+                                    "boundingbox": image.bbox,
+                                    "embedding": image.embedding,
+                                }
+                                for image in section.chunk.images
+                            ]
+                        }
+                    document = {
                         "id": f"{section.content.filename_to_id()}-page-{section_index + batch_index * MAX_BATCH_SIZE}",
                         "content": section.chunk.text,
                         "category": section.category,
                         "sourcepage": BlobManager.sourcepage_from_file_page(
                             filename=section.content.filename(), page=section.chunk.page_num
                         ),
                         "sourcefile": section.content.filename(),
-                        "images": [
-                            {
-                                "url": image.url,
-                                "description": image.description,
-                                "boundingbox": image.bbox,
-                                "embedding": image.embedding,
-                            }
-                            for image in section.chunk.images
-                        ],
+                        **image_fields,
                         **section.content.acls,
                     }
-                    for section_index, section in enumerate(batch)
-                ]
+                    documents.append(document)
                 if url:
                     for document in documents:
                         document["storageUrl"] = url

tests/test_searchmanager.py

@@ -316,6 +316,35 @@ async def mock_upload_documents(self, documents):
     ]
 
 
+@pytest.mark.asyncio
+async def test_update_content_no_images_when_disabled(monkeypatch, search_info):
+    """Ensure no 'images' field is added when search_images is False (baseline case without any images)."""
+
+    documents_uploaded: list[dict] = []
+
+    async def mock_upload_documents(self, documents):
+        documents_uploaded.extend(documents)
+
+    monkeypatch.setattr(SearchClient, "upload_documents", mock_upload_documents)
+
+    manager = SearchManager(search_info, search_images=False)
+
+    test_io = io.BytesIO(b"test file")
+    test_io.name = "test/foo.pdf"
+    file = File(test_io)
+
+    section = Section(
+        chunk=Chunk(page_num=0, text="chunk text"),
+        content=file,
+        category="test",
+    )
+
+    await manager.update_content([section])
+
+    assert len(documents_uploaded) == 1, "Exactly one document should be uploaded"
+    assert "images" not in documents_uploaded[0], "'images' field should not be present when search_images is False"
+
+
 class AsyncSearchResultsIterator:
     def __init__(self, results):
         self.results = results