From ad197be70c3d5b5a6e49862bfd9fe761ca65b271 Mon Sep 17 00:00:00 2001
From: sabaimran <narmiabas@gmail.com>
Date: Sun, 20 Oct 2024 22:25:41 -0700
Subject: [PATCH] Fix PDFs unit test, skip OCR

---
 tests/test_pdf_to_entries.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tests/test_pdf_to_entries.py b/tests/test_pdf_to_entries.py
index 3a25b05d..a62eca8b 100644
--- a/tests/test_pdf_to_entries.py
+++ b/tests/test_pdf_to_entries.py
@@ -1,6 +1,8 @@
 import os
 import re
 
+import pytest
+
 from khoj.processor.content.pdf.pdf_to_entries import PdfToEntries
 from khoj.utils.fs_syncer import get_pdf_files
 from khoj.utils.rawconfig import TextContentConfig
@@ -37,6 +39,7 @@ def test_multi_page_pdf_to_jsonl():
     assert len(entries[1]) == 6
 
 
+@pytest.mark.skip(reason="Temporarily disabled OCR due to performance issues")
 def test_ocr_page_pdf_to_jsonl():
     "Convert multiple pages from single PDF file to jsonl."
     # Arrange