Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
BetaRare

emcf/thepipe

Get clean data from tricky documents, powered by vision-language models ⚡

Owner
emcf (personal account)
Stars
Stars: 1,530
Forks
Forks: 100
Language
Python
License
MIT
Created
2024
Topics
multimodalpdflarge-language-modelsscraperspythonscrapingvision-language-modelunstructured-datadocument-aimicrosoft-word
Tier
Beta (700 to 1,999 ★) What this tier means
View on GitHub

More repos by emcf

All 2 repos by emcf

Nearby in Python

All Python repos