Standard LLMs can hallucinate, lack up-to-date information, and cannot cite sources, making them unreliable for domain-specific tasks.
Retrieval-augmented generation (RAG) solves LLM limitations by providing relevant context from a knowledge base to ground the model's answers in facts.
Unstructured documents like PDFs are chunked, converted into vector embeddings, and stored in a vector database for similarity search against user queries.
Knowledge graphs represent information as nodes and relationships, allowing an LLM to generate precise Cypher queries instead of relying on semantic search.
Knowledge graphs excel at answering multi-hop questions that require connecting multiple pieces of information, which is difficult for unstructured RAG systems.
Knowledge graphs can power chatbots for various domains, including supply chain management, HR and skills mapping, and microservice architecture analysis.
A hybrid approach combines the benefits of both systems by connecting unstructured text chunks as nodes within a structured knowledge graph.
The live demo showcases a chatbot that answers questions by generating Cypher queries for structured data and summarizing connected unstructured articles.
The Q&A covers methods for converting unstructured data into a knowledge graph using named entity extraction and how LLMs handle spelling mistakes in queries.
29:11Michael Hunger
46:51
27:35Stephen Chin
24:42Martin O'Hanlon
29:40Jodie Burchell
21:17Carl Lapierre
26:25Ashish Sharma
58:00Vijay Krishan Gupta & Gauravdeep Singh Lotey
.webp?w=240&auto=compress,format)
Jobs that call for the skills explored in this talk.
Understanding Recruitment Group
Barcelona, Spain
NLP People
Municipality of Valencia, Spain
NLP People
Municipality of Valencia, Spain