sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-28 01:45:07 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

Skip indexing a PDF that has an indexing error (#274)

Browse source
This commit is contained in:
sabaimran 2023-07-03 15:55:11 -07:00 committed by GitHub
parent a6f313589e
commit 017e8c1aef
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
src/khoj/processor/pdf/pdf_to_jsonl.py
View file

@ -98,10 +98,14 @@ class PdfToJsonl(TextToJsonl):
entries = []
entry_to_location_map = []
for pdf_file in pdf_files:
loader = PyPDFLoader(pdf_file)
pdf_entries_per_file = [page.page_content for page in loader.load()]
entry_to_location_map += zip(pdf_entries_per_file, [pdf_file] * len(pdf_entries_per_file))
entries.extend(pdf_entries_per_file)
try:
loader = PyPDFLoader(pdf_file)
pdf_entries_per_file = [page.page_content for page in loader.load()]
entry_to_location_map += zip(pdf_entries_per_file, [pdf_file] * len(pdf_entries_per_file))
entries.extend(pdf_entries_per_file)
except Exception as e:
logger.error(f"Error processing file: {pdf_file}. This file will not be indexed.")
logger.error(e)
return entries, dict(entry_to_location_map)