))
Exploring RAG Pipelines with Private AI Foundation and NVIDIA
Manage episode 451990262 series 2952236
Inhoud geleverd door Virtually Speaking Podcast. Alle podcastinhoud, inclusief afleveringen, afbeeldingen en podcastbeschrijvingen, wordt rechtstreeks geüpload en geleverd door Virtually Speaking Podcast of hun podcastplatformpartner. Als u denkt dat iemand uw auteursrechtelijk beschermde werk zonder uw toestemming gebruikt, kunt u het hier beschreven proces https://nl.player.fm/legal volgen.
In this episode of the Virtually Speaking Podcast, we delve into the world of AI with Justin Murray, Product Marketing Engineer, and Frank Denneman, Chief Technologist for AI at Broadcom. We discuss retrieval augmented generation (RAG), a powerful approach that combines large language models with real-time, trusted data. Learn how RAG pipelines can be architected using Private AI Foundation with NVIDIA, including insights into key components like LLMs, NVIDIA Inference Microservices, and Vector DB. We also explore best practices for GPU sizing and when to use fractional or multiple GPUs for optimal performance. Join us for this fascinating conversation!
111 afleveringen
Delen
