I am trying to upload a PDF using st.file_uploader() from streamlit and then parse it using LlamaParse() currently running on localhost.

Issue is I am getting [] in output which is probably happening because of directly using returned uploaded_file from the below code.

I am not sure if a returned uploaded object can directly be used to feed llama_parse as this PDF works when I directly upload the PDF from my local machine directory into LlamaParse() instead of uploaded_file = st.file_uploader()

Is there something that I need to do for using uploaded_file before feeding it into LlamaParse()?

1. Setting up streamlit:

   import streamlit as st
   import pandas as pd
   
   import os
   import nest_asyncio 
   
   nest_asyncio.apply()
   os.environ["LLMA_CLOUD_API_KEY"] = "my_key"
   key_input = "my_key"
   
   from llama_parse import LlamaParse
   
   ############### Setting Configuration ###############
   
   st.set_page_config(page_title="Pdf Parsing",
                       layout='wide',
                       initial_sidebar_state="expanded")
   
   # title
   st.markdown("<h1 style='text-align: center; font-size: 70px;color: black;letter-spacing: 4px;'>PDF Parsing</h1>", unsafe_allow_html=True)
   

2. Uploading file & parsing through Llama:

   st.write("checkpoint1")
   with st.container(border=True):
   
       st.write("checkpoint2")
       uploaded_file = st.file_uploader('Choose your .pdf file to upload', type="pdf")
   
   
       if uploaded_file is not None:
           st.write(uploaded_file.name)
           st.success("File is uploaded")
   
   if uploaded_file:
       if st.button('Parse Uploaded pdf file (Powered by AI)'):
   
           doc_parsed = LlamaParse(result_type="markdown",api_key=key_input
                                   ).load_data(uploaded_file)
   
           st.write('checkpoint3')
           st.write(doc_parsed)
   

UPDATE:

Is this happening Due to Not Using st.session_state ?

Could it be a possibility that when I click the button then the whole app refreshes/runs again and the file gets lost and nothing goes into llama ?