The Ultimate Guide to Semantic Reasoning: How to enrich your data for practical applications including use with RAG & LLMs
A Talk by Peter Crocker and Tom Vout
About this Talk
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. With ever-improving technology, these benefits are no longer for an exclusive few and are instead widely accessible, and yet, many in the industry still lack the knowledge and understanding to fully capture the power of reasoning.
Join this Ultimate Guide to Semantic Reasoning to learn the best practices of rule writing and how to use it to supercharge applications. Use the W3C standard, OWL, for ontological reasoning, and the widely used Datalog for more advanced functionality such as aggregation, negation, and filtering to build a working solution live in the workshop.
Discover how this enriched data, coupled with the advanced automation feature of incremental reasoning, is enabling real-world applications, including how to enhance RAG and LLM-based solutions.
Key Topics
- Semantic Reasoning & Rules-based AI
- Knowledge Graphs
- Querying Graph Databases
- Writing Rules
- Writing Ontologies
Target Audience
- Knowledge Engineers
- Data Scientists
- Data Engineering
- Data Analysts
- Managers of the above
Aimed at a spectrum of users, from the non-technical to technically minded but unfamiliar. We cover the basics so that everyone has the tools to follow along with the rest of the tutorial but move quickly onto the more advanced sections. Experts in the field will not find this useful.
Goals
Get hands-on experience using Semantic Reasoning and Knowledge Graphs in order to understand the extent to which it can be used to empower real-world use cases.
Session outline:
In this Masterclass, attendees will learn what reasoning is, what it can to do transform data, and crucially, how to do that themselves and how it supports real-world applications.
After a brief theoretical introduction to the subject, attendees will be expected to get hands-on with a reasoning engine in order to learn how to setup a reasoning-ready datastore, and how to reason over it using OWL and Datalog rules.
No prior experience is required as we will run through the process step-by-step, from start to finish. Over the course of the tutorial attendees will learn:
- How to write and run a SPARQL query
- The importance of reasoning and its application
- How to write a Datalog rule
- How to apply and verify the rules they write
- The extended opportunities with reasoning
- How to create a solution that relies on reasoning
- How to achieve RAG (Retrieval-Augmented Generation) with enriched data, KGs and LLMs
Format
This class is very hands-on. Each topic will first be demonstrated to the students so they can copy an ideal example and see the intended results in an informal teacher-student format.
Then they will be given the opportunity to apply their new learned skills without immediate direction, writing rules and queries by themselves.
If at any point a participant requires some assistance, the lecturers will be on hand to help, whether that requires a minor hint, a refresh of the material, or gentle guidance.
Anyone of any skill level should leave this class knowing what reasoning is and how to implement it, so individual support is flexible depending on the needs of the group.
Level
Beginner - Intermediate
Prerequisite Knowledge
None
We’re a cloud tech company that provides organisations around the world with computing infrastructure and software to help them innovate, unlock efficiencies and become more effective. We also created the world’s first – and only – autonomous database to help organise and secure our customers’ data.
