AWS and Generative AI - Services, Deployments and RAG with Bedrock
Rate this video
✅ Register for Atlas - https://mdb.link/xgqrVhUoey4-register
✅ Vector Search - https://mdb.link/xgqrVhUoey4-vector
-
In this episode, Shane Mc Allister is joined by David Min and Rustem Feyzkhanov to explore a range of approaches for deploying pretrained LLM models to AWS cloud using SageMaker JumpStart, SageMaker SDK and AWS Copilot. In addition, we'll showcase how to leverage Retrieval Augmented Generation (RAG) with MongoDB Atlas, Vector Search, and Amazon Bedrock. To bring these concepts to life, we'll swiftly showcase demos illustrating the deployment process for a generative AI model using SageMaker JumpStart and AWS Copilot and how to enable natural language queries to extract more value and insights from your data.