| |
|
EVENT DETAILS |
|
This is a Bay.Area.AI meetup.nWe have two great talks from the AI Alliance members Neo4j & the host Anyscale!nLLM + Graph Database for RAGnLLMs can provide answers that sound realistic to almost any question, even if those answers are entirely made up. To anchor an LLM in reality & mitigate the risk of generating false information or unauthorized access to sensitive data, try incorporating a Knowledge Graph. This prevents the model from producing inaccurate responses & ensures a more reliable & secure outcome.nThis presentation will show you the benefits of Graph Databases over regular databases & how to use GenAI with RAG to eliminate hallucinations, enforce security, & improve accuracy. We will also discuss why a vector index plus Knowledge Graph provides better, smarter, faster results than a pure vector database.nAndreas Kolleggeris a technological humanist. Starting at NASA, Andreas designed systems from scratch to support science missions. Then in Zambia, he built medical informatics systems to apply technology for social good. Now with Neo4j, he is democratizing graph databases to validate & extend our intuitions about how the world works. Everything is connected.n2. Build RAG-based large language model applications with Ray & KubeRay on KubernetesnLarge Language Models (LLMs) have changed the way we interact with information. A base LLM is only aware of the information it was trained on. Retrieval augmented generation (RAG) can address this issue by providing context of additional data sources. In this session, well build a RAG-based LLM application that incorporates external data sources to augment an OSS LLM. Well show how to scale the workload with Ray & Kubernetes, & showcase a chatbot agent that gives factual answers.nKai-Hsun Chen is a software engineer on the Ray Core team at Anyscale & the primary maintainer of KubeRay. He is an open-source enthusiast, as well as a committer & PMC member of Apache Submarine. Additionally, he is an interdisciplinary researcher with publications spanning electrical design automation, distributed computing, & system reliability.
|
|
|
|
|
|
