uniflow-llm-based-pdf-extraction-text-cleaning-data-clustering icon indicating copy to clipboard operation
uniflow-llm-based-pdf-extraction-text-cleaning-data-clustering copied to clipboard

Published 20 hours ago • verified publisher icon CambioML

feat: Add ExtractS3PDFFlow

Open vicshi06 opened this issue 1 year ago • 1 comments

A new PDF flow to allow S3 download and processing.

vicshi06 avatar Feb 01 '24 22:02 vicshi06

@SayaZhang Considering that we have merged in https://github.com/CambioML/uniflow/blob/main/uniflow/op/extract/load/utils.py, please coordinate with @vicshi06 to merge in this PR as well as https://github.com/CambioML/uniflow/pull/150

CambioML avatar Feb 04 '24 14:02 CambioML