Amazon Web Services

This video explores how to build a generative AI virtual assistant using Amazon Bedrock, Langchain, and Amazon ElastiCache. The presenters, Sashi Varanasi and Lakshmi Peri, discuss two key application patterns: chat history and messaging broker. They demonstrate how ElastiCache for Redis simplifies implementation by leveraging built-in Redis data structures, offering extreme low latency and versatility. The session covers the basics of generative AI, foundation models, and Amazon Bedrock, highlighting how ElastiCache can serve as an effective short-term memory solution for chatbots. A live demo showcases the integration of these technologies to create a context-aware, scalable virtual assistant.

product-information
skills-and-how-to
generative-ai
ai-ml
databases
Show 5 more

Up Next

VideoThumbnail
6:45

Grindr's Next-Gen Chat System: Leveraging AWS for Massive Scale and Security

Nov 22, 2024
VideoThumbnail
15:58

Revolutionizing Business Intelligence: Generative AI Features in Amazon QuickSight

Nov 22, 2024
VideoThumbnail
1:01:07

Accelerate ML Model Delivery: Implementing End-to-End MLOps Solutions with Amazon SageMaker

Nov 22, 2024
VideoThumbnail
9:30

Deploying ASP.NET Core 6 Applications on AWS Elastic Beanstalk Linux: A Step-by-Step Guide for .NET Developers

Nov 22, 2024
VideoThumbnail
47:39

Simplifying Application Authorization: Amazon Verified Permissions at AWS re:Invent 2023

Nov 22, 2024