sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2025-02-17 08:04:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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
Show stats 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]:
# Extract required fields from config
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 = {file: files[file] for file in files_to_process}
else: