klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-10 05:39:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
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 tmpf.flush() # Ensure all data is written
# Load the content using PyMuPDFLoader # Load the content using PyMuPDFLoader
loader = PyMuPDFLoader(tmpf.name, extract_images=True) loader = PyMuPDFLoader(tmpf.name)
pdf_entries_per_file = loader.load() pdf_entries_per_file = loader.load()
# Convert the loaded entries into the desired format # Convert the loaded entries into the desired format