init

main.py

@@ -82,8 +82,13 @@ async def insert(file: UploadFile = File(...)):
         create_a_collection(milvus_client, collection_name)
 
     contents = pypdf.PdfReader(BytesIO(contents))
+
+    extracted_text = ""
+    for page_num in range(len(contents.pages)):
+        page = contents.pages[page_num]
+        extracted_text += page.extract_text()
     
-    splitted_document_data = split_documents(contents)
+    splitted_document_data = split_documents(extracted_text)
 
     print(splitted_document_data)