from langchain.document_loaders import SitemapLoader, textfrom langchain.text_splitter import RecursiveCharacterTextSplitterfrom bs4 import BeautifulSoupimport streamlit as stimport asyncioimport sysdef parse_page(soup: BeautifulSoup): header = soup.find("header") footer = soup.find("footer") if header: header.decompose() if footer: footer.decompose() return ( ..
