GraphRAG - Why, When and How?

Knowledge-Enhanced AI Systems

# Why GraphRAG? (Intro)
## 1.1 State of the art
State of the art alternatives - strengths and limitations of LLMs, Vectors, FTS, LPG, etc.

Demo: Comparison of different retrieval outcomes, using a real-world dataset.
Highlighting wher...

Data products promise decentralised ownership, faster delivery, and business-aligned analytics. For a time, that promise largely held. But with the arrival of AI, a fault line has become impossible to ignore: the business speaks in terms of customers, risk exposure, and supplychain disruptions, w...

https://www.dropbox.com/scl/fo/p5oi87h9800o35bhyua80/AHipulxYW0IQJrinOTB-Qy0?rlkey=x5fvfx8gsusubrqkx55h0obkp&e=5&st=nxa2ste2&dl=0

We are using Graph to build a unified clinical intelligence ecosystem for AbbVie R&D organization with potential to become a foundational capability in supporting a v...

How we Screw up the data... even when we try to fix it

The Life Sciences industry continues to scale data generation and standardization, yet biological insight remains stagnant. This panel will be a lively discussion between those who agree and those who challenge this assumption: that more, cl...

https://drive.google.com/file/d/1uYLqLsrMRgPd6SR1TzyI_SnW3PEC4SMH/view?usp=drive_link

Large Language Models (LLMs) provide new opportunities for AI-assisted ontology engineering, however they often perform poorly, creating complex class hierarchies, inconsistent taxonomies, uncontrolled property...

https://drive.google.com/file/d/1xpWLwHlekc3W5s-nRVvMz7Qxz_mmjV2v/view?usp=share_link
This talk will share how LifeScience Companies have moved from a fragmented reference data architecture, where meaning is recreated in every system and pipeline, to an authoritative context architecture, where m...

https://drive.google.com/file/d/1u9pc2SHI2OeedOquaRVYXjAke5MV1ova/view?usp=share_link

The AbbVie Reasearch and Development Convergence Hub (ARCH) harmonizes over 230 different sources of internal and external experimental, clinical, and biological background knowledge into a single semantically-...

Modern AI systems are increasingly used to support tasks that rely on scientific evidence, precise terminology, and contextual interpretation. Large language models (LLMs) are employed in such implementations, providing flexible and robust natural language interfaces. However, LLMs alone often st...

This tutorial introduces participants to the core concepts of OWL and SHACL, using museum data to walk through ontology modeling and shape validation. We focus on practical decision-making: which technology is appropriate in a given scenario and why. Participants will engage with structured hands...

ttps://drive.google.com/file/d/11pLUjwntRTS0swZbxM4Hul6fEySQlgi4/view?usp=share_link

Semantic reasoning is fast becoming a must-have for anyone running a knowledge graph application as a route to better data, faster queries, and ultimately greater insights. Knowledge-based AI offers a more effec...

When an AI agent denies your insurance claim, can it explain *why*? Not with a hallucinated summary, but with a traceable, auditable chain of reasoning grounded in formal logic.

Most agentic AI systems today are plumbing: retrieve chunks, call an LLM, hope for the best. This workshop takes a fun...

https://drive.google.com/file/d/1XdeAYqvcqzoXWKN2ZfA9sbq_yWFm6i2X/view?usp=share_link

https://drive.google.com/file/d/1l5Xd-bOOj7z-IyF-5kOTjVjoO02wQQZm/view?usp=share_link

Oracle AI Database brings AI to your data, with the flexibility of working with multiple data types and data sources (vecto...

https://drive.google.com/file/d/1lZAFsK7zzak4SSasSAhEYuCMLQawAnBA/view?usp=share_link 

Healthcare is one of the most demanding real-world environments for knowledge-driven AI: data sources include ontologies, biomedical literature, clinical narratives, and regulated patient records that cannot b...

https://drive.google.com/file/d/1vzYTsg6Y05Vn15W2uhBifzrJ58fQaYIr/view?usp=share_link

Organizations increasingly operate across two graph paradigms: RDF/OWL for standards-based semantics and validation, and property graphs for visualization, operational queries, and graph analytics. Bridging the...

https://drive.google.com/file/d/1vFDpYJH0tHc2eDb6d-JGTWmo6Yb3PqF3/view?usp=share_link 

Traditional Retrieval-Augmented Generation (RAG) systems often fall short when queries require multi-step reasoning, relationship traversal, or contextual decision-making. In this hands-on workshop, participan...