Mastodawn

📰 LLMをもっと賢くする：ナレッジグラフ実践入門 (👍 41)

🇬🇧 Practical guide to enhancing LLMs with knowledge graphs, covering enterprise implementation challenges beyond RAG
🇰🇷 RAG을 넘어 지식 그래프로 LLM 강화하기: 엔터프라이즈 구현 과제와 실전 가이드

🔗 https://zenn.dev/knowledge_graph/books/knowledge-graph-llm-guide

#LLM #KnowledgeGraph #Zenn

LLMをもっと賢くする：ナレッジグラフ実践入門

「ChatGPTは賢いのに、なぜ業務では使いにくいのか」。その答えがナレッジグラフにあります。本書は、RAGだけでは解けない問題の正体を明らかにし、ナレッジグラフがLLMに何をもたらすかを、入門から世界の活用事例、実装アーキテクチャ、AI Agentとの統合まで一気通貫で解説しま

Zenn

Marcel Otto 2d ago

🔹 RDF.ex 3.0 is out!
The headline feature: the new RDF.Data.Source protocol, following Elixir's Enumerable/Enum pattern for RDF data. Implement a small set of primitives, get a full API for iteration, transformation, navigation, and aggregation - across Descriptions, Graphs, Datasets, and custom implementations.
Plus various other improvements.
Hex: https://hex.pm/packages/rdf User Guide: https://rdf-elixir.dev/rdf-ex/rdf-data
#RDF #SPARQL #SemanticWeb #LinkedData #KnowledgeGraph #Elixir

rdf

An implementation of RDF for Elixir.

Hex

Marcel Otto 2d ago

🔹 Gno is an Elixir library for managing RDF datasets in SPARQL triple stores.
A unified API across Fuseki, Oxigraph, QLever, and GraphDB - with an extensible commit system featuring a middleware pipeline, transactional execution, and automatic rollback.
Ontogen's entire versioning logic is implemented as Gno commit middleware.
Hex: https://hex.pm/packages/gno User Guide: https://rdf-elixir.dev/gno/
#RDF #SPARQL #SemanticWeb #LinkedData #KnowledgeGraph #Elixir

gno

A unified Elixir API for managing RDF data in SPARQL triple stores.

Hex

Marcel Otto 2d ago

🔹 DCAT-R extends W3C DCAT 3 with an intra-service perspective for RDF repositories.
Where DCAT describes what a service looks like from outside, DCAT-R adds vocabulary for how an application organizes its RDF repository internally - graph types, distribution boundaries, directory structures, manifests.
It's designed as a framework for services like Ontogen.
Spec: https://w3id.org/dcatr Elixir implementation: https://hex.pm/packages/dcatr
#RDF #DCAT #LinkedData #SemanticWeb #KnowledgeGraph

Marcel Otto 2d ago

🚀 New releases from the Ontogen and RDF on Elixir ecosystem 🧵
Two new projects and a major update to RDF.ex:
🔹 DCAT-R - a spec + vocabulary for describing RDF repositories 🔹 Gno - a library for managing RDF datasets in SPARQL stores 🔹 RDF.ex 3.0 - with a new protocol for polymorphic RDF data access
Details in the blog post: https://ontogen.io/blog/dcat-r-gno-and-rdf-ex-3
Thanks to @nlnet for making this work possible through the NGI Zero Core fund! 🙏
#RDF #LinkedData #SemanticWeb #KnowledgeGraph #Elixir

Jan Koester 3d ago

I’m exploring how to ground agentic AI in epistemic integrity. By utilizing reified interpretation nodes and the Model Context Protocol, we can map scientific ambiguity directly within the graph.

The goal is a domain-agnostic curator that respects the complexity of the human record rather than simulating certainty.

https://resonism.substack.com/p/real-reasoning

#DigitalHumanities #GraphRAG #ADK #MCP #neo4j #numismatics #knowledgeGraph

Real Reasoning

Trustworthy GraphRAG utilizing ADK, MCP, and Neo4j

A Human in Latent Space

HECHT INS GEFECHT 3d ago

Websites haben keine Autorität. Nur Marken.

E-E-A-T bezieht sich auf die Marke hinter der Website – nicht die Domain, nicht den Pagerank. Und KI-Systeme wie ChatGPT und Perplexity? Die zitieren Marken, die sie kennen. „Kennen“ heißt: konsistente Attribute über Dutzende Datenquellen.

Unser Hebel: 50+ Citations, Organization Schema auf jeder Seite, eine wortgleiche Markenbeschreibung überall.

https://hechtinsgefecht.de/brand-seo/

#BrandSEO #EntitySEO #KnowledgeGraph

Brand SEO: Starke Marken im Web sichtbar machen 🌟

Brand SEO macht deine Marke zur Entität bei Google & KI-Systemen. Case Study: 199 LLM-Erwähnungen. Schema-Workflow, Citations & subjectOf. 🚀

HECHT INS GEFECHT

FDM Bayern 3d ago

Wie letzte Woche schon angeklungen, sind mit #KI erstellte Inhalte nicht neutral. Es braucht also bei jedem Einsatz dieser Technologie robuste Prüfverfahren. Im Idealfall basieren die Ergebnisse auf Daten, die z. B. in #KnowledgeGraph en effizient gespeichert werden können 💾

📖 Lesetipp dazu: Ibrahim et al. 2024: A survey on augmenting knowledge graphs (KGs) with large language models (LLMs): models, evaluation metrics, benchmarks, and challenges, https://doi.org/10.1007/s44163-024-00175-8

A survey on augmenting knowledge graphs (KGs) with large language models (LLMs): models, evaluation metrics, benchmarks, and challenges - Discover Artificial Intelligence

Integrating Large Language Models (LLMs) with Knowledge Graphs (KGs) enhances the interpretability and performance of AI systems. This research comprehensively analyzes this integration, classifying approaches into three fundamental paradigms: KG-augmented LLMs, LLM-augmented KGs, and synergized frameworks. The evaluation examines each paradigm’s methodology, strengths, drawbacks, and practical applications in real-life scenarios. The findings highlight the substantial impact of these integrations in fundamentally improving real-time data analysis, efficient decision-making, and promoting innovation across various domains. In this paper, we also describe essential evaluation metrics and benchmarks for assessing the performance of these integrations, addressing challenges like scalability and computational overhead, and providing potential solutions. This comprehensive analysis underscores the profound impact of these integrations on improving real-time data analysis, enhancing decision-making efficiency, and fostering innovation across various domains.

SpringerLink

sayzard 6d ago

Min Choi (@minchoi)

GitNexus가 코드베이스를 지식 그래프로 변환해 Claude Code, Cursor 등 AI 코딩 도구들이 MCP를 통해 활용할 수 있도록 한다는 발표. 이를 통해 AI 코딩 어시스턴트가 전체 리포지토리를 이해하도록 돕고 있으며 공개 리포지토리와 데모가 제공된다.

https://x.com/minchoi/status/2033567557941162288

#gitnexus #knowledgegraph #codeassistant #mcp

Min Choi (@minchoi) on X

Ok this is insane. GitNexus turns your codebase into a knowledge graph that Claude Code, Cursor + other AI coding tools can use through MCP. Helps your AI coding assistant understand your entire repo. Public repo + demo in reply 👇

X (formerly Twitter)

Larry Swanson 6d ago

Yale University manages huge collections of precious #culturalHeritage artifacts housed in multiple museums, libraries, and other collections.

Using #knowledgeGraph and #ontology engineering design patterns that he has developed over his career, Robert Sanderson helps scholars, researchers, and the general public access information about — and make connections across — millions of unique items in Yale's collections

https://knowledgegraphinsights.com/rob-sanderson/