Download backend/app/document_loader.py from AtPeak/cc-rag: direct link, hf CLI and curl.
- Browser
- Download file 358 Bytes
-
https://huggingface.co/spaces/AtPeak/cc-rag/resolve/main/backend/app/document_loader.py
- Command line
-
hf download hf://spaces/AtPeak/cc-rag/backend/app/document_loader.py
-
curl -L -o document_loader.py https://huggingface.co/spaces/AtPeak/cc-rag/resolve/main/backend/app/document_loader.py
358 Bytes
| import io | |
| from pathlib import Path | |
| from pypdf import PdfReader | |
| def load_text(filename: str, content: bytes) -> str: | |
| ext = Path(filename).suffix.lower() | |
| if ext == ".pdf": | |
| reader = PdfReader(io.BytesIO(content)) | |
| return "\n".join(page.extract_text() or "" for page in reader.pages) | |
| return content.decode("utf-8", errors="replace") | |