synthetic historical documents used for benchmarking VLLM-OCR tools for GLAM

Maps LLM-cleaned text to ALTO XML OCR elements using fuzzy string matching, context-based scoring, and geometric proximity analysis. Corrects OCR errors, handles hyphenated words and word boundary …

Editor to create (scientific) publications and export as HTML, PDF or ePUB

sandbox

Evaluating RAG Technology for Enhancing LLM Usability in Climate Literature Applications?

A modular toolkit for designing, analyzing, and validating hybrid AI systems using Boxology visual patterns.

Semantic Glossary Demo

Wikidata-based scholarly profiles

A collection of open source tools and resources related to Wikibase knowledge graphs

Links and description of Knowledge Graphs Construction Tools

Live editor and image creator for mermaid.js in Visual Studio Code

Mirror of the official development repository of PHAIDRA. We monitor our public github repo, so contributions via issues & pull requests are welcome.

Model Context Protocol Servers

Python library of `ami` software especially NLP, HTML, downloading and related convenience utilities

Collect and Share Health Data over FHIR

Simon Worthington — blog, projects & CV #bookliberationist publishing infrastructure R&D

A curated list of resources for graph-related topics, including graph databases, analytics and science

speedata Publisher - a professional database Publishing system

The Climate Knowledge Graph (#ClimateKG) is an R&D project to make a knowledge graph of the Open Access parts of the United Nations — Intergovernmental Panel on Climate Change (IPCC) Sixth Assessme…

A template Github repository for running your own AI LLM RAG for a literature review project

Open Museum Guidebooks: A Citizen Science Experience - CPS Proof of Concept Prototype

RAG pipeline for climate literature using open models (Llama 3), local embeddings (FAISS), and semantic HTML chunking.

Assisted Literature Review (ALR) - global south, knowledge equity, open-source, open-science, FAIR, CARE

A system for agentic LLM-powered data processing and ETL

The core data of the Iconclass Classification System

21 Lessons, Get Started Building with Generative AI