yujunjun/llama-hub
1
0
Fork 0
mirror of https://github.com/run-llama/llama-hub.git synced 2025-08-14 03:31:41 +00:00
Code Issues Packages Projects Releases Wiki Activity
llama-hub/loader_hub/file/flat_pdf
History
bhavishpahwa f4ff2f95a6
Fix base.py for flat_pdf (#285) 
Fixed the bug that was coming up due to this commit and ImageReader output being changed due to this commit:- a37df8c221 (diff-d4cdba126dd16c86090107c1c66621a520d20d8962f7f4dd461146cedbb1135d)
2023-05-22 20:50:36 -07:00
..
__init__.py
feat: Created a loader for flattened pdfs (#148)
2023-04-01 10:25:17 -07:00
base.py
Fix base.py for flat_pdf (#285)
2023-05-22 20:50:36 -07:00
README.md
fix flat_pdf readme (#184)
2023-04-12 13:46:05 -07:00
requirements.txt
feat: Created a loader for flattened pdfs (#148)
2023-04-01 10:25:17 -07:00

README.md

Flat PDF Loader

This loader extracts the text from a local flat PDF file using the PyMuPDF Python package and image loader. A single local file is passed in each time you call load_data.

Usage

To use this loader, you need:

  • Download ImageReader and FlatPdfReader using download_loader
  • Init a ImageReader
  • Init a FlatPdfReader and pass ImageReader on init
  • Pass a Path to a local file in method load_data.
from pathlib import Path
from llama_index import download_loader


ImageReader = download_loader("ImageReader")
imageLoader = ImageReader(text_type="plain_text")
FlatPdfReader = download_loader("FlatPdfReader")
pdfLoader = FlatPdfReader(image_loader=imageLoader)

document = pdfLoader.load_data(file=Path('./file.pdf'))

This loader is designed to be used as a way to load data into LlamaIndex and/or subsequently used as a Tool in a LangChain Agent. See here for examples.