Amazon Web Services

This video from AWS re:Invent 2023 explores how to build production-ready semantic search and retrieval-augmented generation (RAG) applications. Speakers from Elastic, AWS, and Adobe discuss the challenges of integrating private data with large language models securely and at scale. They cover key components like vector search, natural language processing, and data security. Elastic demonstrates how their Elasticsearch Relevance Engine provides comprehensive capabilities for vector search, hybrid search, and data processing in a single API. AWS highlights their Amazon Bedrock service for accessing foundation models. Adobe shares a real-world use case of enriching e-commerce product catalogs using domain-specific language models. The speakers emphasize the importance of having a flexible platform to experiment with different approaches as generative AI applications evolve.

product-information
skills-and-how-to
retail
generative-ai
ai-ml
Show 6 more

Up Next

VideoThumbnail
15:58

Revolutionizing Business Intelligence: Generative AI Features in Amazon QuickSight

Nov 22, 2024
VideoThumbnail
6:45

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

Nov 22, 2024
VideoThumbnail
2:53:33

Streamlining Patch Management: AWS Systems Manager's Comprehensive Solution for Multi-Account and Multi-Region Patching Operations

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