Download src/document_loader.py from Ajeet001/sample: direct link, hf CLI and curl.
- Browser
- Download file 785 Bytes
-
https://huggingface.co/spaces/Ajeet001/sample/resolve/main/src/document_loader.py
- Command line
-
hf download hf://spaces/Ajeet001/sample/src/document_loader.py
-
curl -L -o document_loader.py https://huggingface.co/spaces/Ajeet001/sample/resolve/main/src/document_loader.py
785 Bytes
| 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 |