NODES 2023: Knowledge Graph-Based Chatbot

Large Language Models (LLMs) like ChatGPT has inspired the world and started a new AI revolution. However, it seems that the latest trend is supplying ChatGPT with external information to increase its accuracy and give it the ability to answer questions where the answers are not present in public datasets. In this session, Tomaz will demonstrate how using a knowledge graph as a storage object for answers gives you explicit and complete control over the answers provided by the chatbot and helps avoid hallucinations.
Watch all NODES 2023 sessions: dev.neo4j.com/nodes-2023
#neo4j #graphdatabase #nodes2023 #chatbot #knowledgegraphs

[@AdrienSales]

Great talk. You've been a great source of inspiration this year to me. Still a lot to learn and prototype around few-shot templates too and advanced RAG.

[@SDGwynn]

Wonderful. Thank you.

[@user-sf4qd3pj5m]

Thanks for the talk! In my opinion the most important statement is what you said at the end of the video, which is that we need to combine structured and unstructured data. My question is though, how to do this in practice
Let's say we have a knowledge base of documents (unstructured) where some of them contain tables (structured). Also maybe the metadata of the documents can be somehow structured. My question is how are you gonna combine these to build an RAG application?