klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-05 21:29:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use OCR to extract image text in PDFs

Browse Source
This commit is contained in:
sabaimran
2023-11-04 17:15:28 -07:00
parent d1d210605e
commit b5972e9311
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -68,7 +68,7 @@ class PdfToEntries(TextToEntries):
with open(f"{tmp_file}", "wb") as f:
bytes = pdf_files[pdf_file]
f.write(bytes)
loader = PyMuPDFLoader(f"{tmp_file}")
loader = PyMuPDFLoader(f"{tmp_file}", extract_images=True)
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)