sij/khoj
1
0
Fork 0
mirror of https://github.com/khoj-ai/khoj.git synced 2024-11-27 09:25:06 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 5

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
Show stats Download patch file Download diff file Expand all files Collapse all files

1
pyproject.toml
View file

@ -73,6 +73,7 @@ dependencies = [
"gunicorn == 21.2.0",
"lxml == 4.9.3",
"tzdata == 2023.3",
"rapidocr-onnxruntime == 1.3.8"
]
dynamic = ["version"]

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)