localRAG/add_pdfs.py

19 lines
630 B
Python

#!/usr/bin/env python3
"""Add all PDFs under a folder to the RAG vector store. Run from project root."""
from pathlib import Path
from local_rag import LocalRAG
DATA_ROOT = Path("/Users/Philipp/Desktop/workspace/python/gpt_publikationen/data_vs")
VECTORSTORE_PATH = "./vectorstore"
if __name__ == "__main__":
pdfs = sorted(p for p in DATA_ROOT.rglob("*") if p.suffix.lower() == ".pdf")
print(f"Found {len(pdfs)} PDF(s) under {DATA_ROOT}")
if not pdfs:
raise SystemExit("No PDFs found.")
rag = LocalRAG(vectorstore_path=VECTORSTORE_PATH)
rag.add_documents([str(p) for p in pdfs])
print("Done.")