Exploring RAG Pipelines with Private AI Foundation and NVIDIA
Exploring RAG Pipelines with Private AI…
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!