Tuesday, February 4, 2025 12:15pm to 1:15pm
About this Event
Abstract:
This session explores building Generative AI services using Retrieval Augmented Generation (RAG) - a powerful technique that grounds LLMs in external knowledge. We will delve into the architecture of RAG pipelines covering key components like retrieval mechanisms, vector databases, and response generation including multiple data modalities. Attendees will gain practical insights into implementing RAG in research and production environments.
0 people are interested in this event
User Activity
No recent activity