Update test.py

test.py

@@ -12,7 +12,6 @@ from docx import Document
 from PIL import Image
 import pytesseract
 import io
-import base64
 
 app = FastAPI()
 oauth2_scheme = OAuth2PasswordBearer(tokenUrl="token")
@@ -124,7 +123,7 @@ async def send_chunked_data(websocket: WebSocket, filename: str, data: str):
 
 
 async def extract_text_from_pdf(pdf_data):
-    with io.BytesIO(base64.b64decode(pdf_data)) as pdf_file:
+    with io.BytesIO(pdf_data) as pdf_file:
         pdf_reader = PyPDF2.PdfReader(pdf_file)
         text = ""
         for page_num in range(pdf_reader.numPages):
@@ -133,7 +132,7 @@ async def extract_text_from_pdf(pdf_data):
         return text
 
 async def extract_text_from_docx(docx_data):
-    doc = Document(io.BytesIO(base64.b64decode(docx_data)))
+    doc = Document(io.BytesIO(docx_data))
     text = ""
     for para in doc.paragraphs:
         text += para.text + "\n"