engineering/megafarce
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
Migrated from https://git2.unturf.com/engineering/unturf/megafarce.git
3 commits 1 branch 0 tags 52 KiB
Find a file
Exact
Russell Ballestrini 36e2c681f9 modified: app.py
2025-04-11 20:38:47 -04:00
app.py modified: app.py 2025-04-11 20:38:47 -04:00
docker-compose.yml MegaParce is now MegaFarce 2024-12-08 15:02:15 -05:00
Dockerfile modified: app.py 2025-04-11 20:38:47 -04:00
LICENSE MegaParce is now MegaFarce 2024-12-08 15:02:15 -05:00
pyproject.toml MegaParce is now MegaFarce 2024-12-08 15:02:15 -05:00
README.md MegaParce is now MegaFarce 2024-12-08 15:02:15 -05:00
requirements.lock MegaParce is now MegaFarce 2024-12-08 15:02:15 -05:00

README.md

MegaFarse - Your Parser for every type of documents

this is a MegaFarse fork by the community.

MegaFarse is a powerful and versatile parser that can handle various types of documents with ease. Whether you're dealing with text, PDFs, Powerpoint presentations, Word documents MegaFarse has got you covered. Focus on having no information loss during parsing.

Key Features 🎯

  • Versatile Parser: MegaFarse is a powerful and versatile parser that can handle various types of documents with ease.
  • No Information Loss: Focus on having no information loss during parsing.
  • Fast and Efficient: Designed with speed and efficiency at its core.
  • Wide File Compatibility: Supports Text, PDF, Powerpoint presentations, Excel, CSV, Word documents.
  • Open Source: Freedom is beautiful, and so is MegaFarse. Open source and free to use.

Support

  • Files: ✅ PDF ✅ Powerpoint ✅ Word
  • Content: ✅ Tables ✅ TOC ✅ Headers ✅ Footers ✅ Images

Installation

Docker only for now...

docker build -t megaparse:latest .
docker compose -f docker-compose.yml up --build

at the root of the project and you are good to go.

See localhost:8001/docs for more info on the different endpoints !

BenchMark

Parser similarity_ratio
megaparse_vision 0.87
unstructured_with_check_table 0.77
unstructured 0.59
llama_parser 0.33

Higher the better

Note: Want to evaluate and compare your MegaFarse module with ours ? Please add your config in evaluations/script.py and then run python evaluations/script.py. If it is better, do a PR, I mean, let's go higher together!