Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to build serverless-first chatbot applications by leveraging Amazon Aurora with pgvector as a vector store and Amazon ElastiCache Serverless for Valkey to manage chat history, semantic caching, and agent memory in this 41-minute conference talk from AWS re:Invent 2025. Discover how to harness these AWS services to create contextually aware, scalable chatbots with agentic capabilities that retain conversational memory across interactions. Explore architectural patterns and implementation strategies for building modern chatbot applications using generative AI. Examine real-world use cases and gain insights into optimizing query latency, performance, and cost-effectiveness when developing serverless-powered chatbot solutions. Master the integration of Amazon Aurora PostgreSQL's vector capabilities with ElastiCache Serverless to create sophisticated conversational AI systems that maintain context and provide enhanced user experiences through persistent memory and intelligent caching mechanisms.
