import streamlit as st from langchain_community.document_loaders import ( PyPDFLoader, PyMuPDFLoader, PDFPlumberLoader, PDFMinerLoader, UnstructuredWordDocumentLoader, ) def load_document(file_path, loader_type): """Load document based on the selected loader type.""" loaders = { 'PyPDF': PyPDFLoader, 'PyMuPDF': PyMuPDFLoader, 'PDFPlumber': PDFPlumberLoader, 'PDFMiner': PDFMinerLoader, 'Unstructured Word': UnstructuredWordDocumentLoader } loader = loaders.get(loader_type) if not loader: raise ValueError("Unsupported loader type.") documents = loader(file_path).load() st.success(f"Number of documents loaded: {len(documents)}") return documents