The Document Index / VLM & Understanding / #31
emcf/thepipe
by emcf · VLM & Understanding · updated 9d ago
Get clean data from tricky documents, powered by vision-language models ⚡
66
momentum
1,524
stars
98
forks
#31
rank
document-ailarge-language-modelsmicrosoft-wordmultimodalpdfpowerpointpythonscanned-pdfscrapersscrapingunstructured-datavision-language-model
View on GitHub →
More in VLM & Understanding
html-to-markdown
xberg-io
High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kr
INF-MLLM
infly-ai
INF Tech's open-source MLLMs for SOTA visual-language understanding and advanced document
ARGUS
Azure-Samples
Automated Retrieval and GPT Understanding System by utilizing Azure Document Intelligence
nougat
facebookresearch
Implementation of Nougat Neural Optical Understanding for Academic Documents