Back to Llama Index

NougatOCR

llama-index-integrations/readers/llama-index-readers-nougat-ocr/examples/NougatOCR.ipynb

0.14.21411 B
Original Source
python
!pip install -qU nougat-ocr llama-index
python
from google.colab import files

upload = files.upload()
python
from google.colab import files

upload = files.upload()
python
from base import PDFNougatOCR
from pathlib import Path
python
reader = PDFNougatOCR()
pdf_path = Path("mathpaper.pdf")
python
docs = reader.load_data(pdf_path)
python
len(docs)