Matthew Riedl's starred repositories
llm_aided_ocr
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
botasaurus
The All in One Framework to build Awesome Scrapers.
RAGatouille
Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.
InvoiceNet
Deep neural network to extract intelligent information from invoice documents.
bypass-paywalls-chrome
Bypass Paywalls web browser extension for Chrome and Firefox.
SwiftDefaultApps
Replacement for RCDefaultApps, written in Swift.
awesome-cto
A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups