sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-23 15:38:55 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

Remove extract_images flag from PDF loader

Browse source
This commit is contained in:
sabaimran 2024-11-15 21:46:35 -08:00
parent 15b4cec1e8
commit a1b4587b34
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

@ -101,7 +101,7 @@ class PdfToEntries(TextToEntries):
tmpf.flush() # Ensure all data is written
# Load the content using PyMuPDFLoader
loader = PyMuPDFLoader(tmpf.name, extract_images=True)
loader = PyMuPDFLoader(tmpf.name)
pdf_entries_per_file = loader.load()
# Convert the loaded entries into the desired format