Invoice Data Preprocessing for LLM

Опубликовано: 11 Апрель 2026
на канале: Andrej Baranovskij
1,506
32

Data preprocessing is important step for LLM pipeline. I show various approaches to preprocess invoice data, before feeding it to LLM. This is quite challenging step, especially to preprocess tables.

Sparrow GitHub repo:
https://github.com/katanaml/sparrow

0:00 Overview
1:45 Sample doc
2:39 Marker
5:53 PyMuPDF
7:45 Unstructured
9:36 Summary

CONNECT:
Subscribe to this YouTube channel
Twitter:   / andrejusb  
LinkedIn:   / andrej-baranovskij  
Medium:   / andrejusb  

#llm #rag #data