klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-07 13:23:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

Properly filter out empty PDFs for indexing

Browse Source
This commit is contained in:
sabaimran
2023-12-04 16:15:17 -05:00
parent 62a89f79b7
commit d20746613a
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/khoj/processor/content/pdf/pdf_to_entries.py
View File

@@ -28,7 +28,7 @@ class PdfToEntries(TextToEntries):
) -> Tuple[int, int]: ) -> Tuple[int, int]:
# Extract required fields from config # Extract required fields from config
if not full_corpus: if not full_corpus:
deletion_file_names = set([file for file in files if files[file] == ""]) deletion_file_names = set([file for file in files if files[file] == b""])
files_to_process = set(files) - deletion_file_names files_to_process = set(files) - deletion_file_names
files = {file: files[file] for file in files_to_process} files = {file: files[file] for file in files_to_process}
else: else: