Cant use streamlit fileuploader with langchian tranform loaders

Question

i want to use st.file_uploader to upload a file based on the extension, use the necessary loader ex:

The normal working is

from langchain.document_loaders import PyPDFLoader

loader = PyPDFLoader("example_data/layout-parser-paper.pdf")
pages = loader.load_and_split()

but in streamlit :

import streamlit as st
import pandas as pd
from io import StringIO

uploaded_file = st.file_uploader("Choose a file")
if uploaded_file is not None:
    # To read file as bytes:
    bytes_data = uploaded_file.getvalue()
    st.write(bytes_data)

    # To convert to a string based IO:
    stringio = StringIO(uploaded_file.getvalue().decode("utf-8"))
    st.write(stringio)

    # To read file as string:
    string_data = stringio.read()
    st.write(string_data)

    # Can be used wherever a "file-like" object is accepted:
    dataframe = pd.read_csv(uploaded_file)
    st.write(dataframe)

how can i upload files in st.file_uploader such that it can be accesed by langchain loaders, should i create a temp file, what the best possible option i have thanks

i tried readings as string data but it messes-up with the loader, o just want the file to be accessible by the loaders