Challenges You Will Face When Parsing PDFs with Python
theseattledataguy.com·2h·
Discuss: Hacker News
📄PDF Archaeology
Ancient Scripts, Modern AI: Bridging the Divide with Morphology-Aware Tokenization by Arvind Sundararajan
dev.to·1d·
Discuss: DEV
📝Concrete Syntax
Fastest copy
forums.anandtech.com·49m
📄Document Digitization
Semantic Dictionary Encoding
falvotech.com·2h·
Discuss: Hacker News
🌀Brotli Dictionary
Lessons from using AI in Discovery
thoughtbot.com·17h
🕵️Metadata Mining
WorldCat Editions and Holdings Release
annas-archive.org·1d·
Discuss: Hacker News
📚MARC Records
Converting a PDF to text locally with Ollama
huijzer.xyz·2d
👁️OCR Verification
Mike Driscoll: Erys – A TUI for Jupyter Notebooks
blog.pythonlibrary.org·4h
📺Terminal UI
DCP-o-matic • Re: Color Space and Gamma when exporting From Davinci Resolve
dcpomatic.com·2d
🖼️JPEG XL
Show HN: Semlib – Semantic Data Processing
github.com·3h·
Discuss: Hacker News
🌳Incremental Parsing
UTF-8 Is Beautiful
hackaday.com·12h
🔣Unicode
Generating Consistent Illustrations with Gemini Image Generation
tinystruggles.com·1d·
Discuss: Hacker News
🌈Color Archaeology
Towards an AI-based knowledge assistant for goat farmers based on Retrieval-Augmented Generation
arxiv.org·13h
🔍Information Retrieval
From Legal Documents to Knowledge Graphs
neo4j.com·2d·
Discuss: Hacker News
📋Document Grammar
How to Remove Invisible Characters From AI Text (Free Tool)
hackernoon.com·1d
✏️OCR Correction
Analyzing Lisp Redux: One Form At a Time
funcall.blogspot.com·2h·
Discuss: www.blogger.com
🔗Lisp
IETF Draft: Authenticated Transfer Repo and Sync Specification
ietf.org·6h·
Discuss: Hacker News
🌳Archive Merkle Trees
Docling: The Document Alchemist
towardsdatascience.com·3d
📋Document Grammars
How to self-host a web font from Google Fonts
blog.velocifyer.com·2h·
Discuss: Hacker News
🔤Font Archaeology
LLM Rerankers for RAG: A Practical Guide
fin.ai·19h·
Discuss: Hacker News, Hacker News
🔍Information Retrieval