From d2ddbef08f7dbf2e591430d81e353cd92f995d75 Mon Sep 17 00:00:00 2001 From: sabaimran Date: Mon, 4 Dec 2023 19:27:00 -0500 Subject: [PATCH] Use a unique name for the temp PDF generated --- src/khoj/processor/content/pdf/pdf_to_entries.py | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/src/khoj/processor/content/pdf/pdf_to_entries.py b/src/khoj/processor/content/pdf/pdf_to_entries.py index 28e89bbe..101e582b 100644 --- a/src/khoj/processor/content/pdf/pdf_to_entries.py +++ b/src/khoj/processor/content/pdf/pdf_to_entries.py @@ -3,6 +3,7 @@ import base64 import logging import os from typing import List, Tuple +from datetime import datetime # External Packages from langchain.document_loaders import PyMuPDFLoader @@ -66,7 +67,8 @@ class PdfToEntries(TextToEntries): for pdf_file in pdf_files: try: # Write the PDF file to a temporary file, as it is stored in byte format in the pdf_file object and the PDF Loader expects a file path - tmp_file = f"tmp_pdf_file.pdf" + timestamp_now = datetime.utcnow().timestamp() + tmp_file = f"tmp_pdf_file_{timestamp_now}.pdf" with open(f"{tmp_file}", "wb") as f: bytes = pdf_files[pdf_file] f.write(bytes)