Shayon Sanyal

What if your agent's most convincing answer rests on the wrong evidence? Build agentic hybrid retrieval with Aurora PostgreSQL across more than 500,000 product listings in three connected hands-on labs.

Build an agentic retail assistant that answers from business facts under explicit controls. Across four connected labs, combine Aurora PostgreSQL full-text search and pgvector with reciprocal rank fusion and Cohere Rerank on Amazon Bedrock.

PostgreSQL is now a multi-model powerhouse, but many developers stop at using either pgvector for semantic search or tsvector for full-text. In reality, the best applications combine both.

PostgreSQL has evolved into a multi-model database capable of handling diverse search requirements. While many developers know about pgvector for semantic search or tsvector for full-text search, few have explored combining these capabilities into unified hybrid search systems.

PostgreSQL has evolved into a multi-model database capable of handling diverse search requirements. While many developers know about pgvector for semantic search or tsvector for full-text search, few have explored combining these capabilities into unified hybrid search systems.

Migrating from Oracle to PostgreSQL often raises questions about replacing powerful Oracle features like Materialized Views, Flashback Queries, Virtual Columns, Oracle RAC, and PL/SQL Packages.

In this chalk talk, explore key design principles for building cost-effective generative AI applications. Learn about model choice and optimization, chunking, caching and prompt engineering techniques, focusing on strategies to optimize the Retrieval Augmented Generation (RAG) architecture.

The integration of embeddings generated from LLMs with Amazon Aurora PostgreSQL-Compatible Edition and Amazon RDS for PostgreSQL offers a powerful and efficient solution for optimizing product catalog similarity search experience.

Explore how to build an agentic AI application using Amazon Aurora and Model Context Protocol (MCP). This session introduces design patterns for agents powered by Amazon Bedrock that retrieve live relational data from Amazon Aurora to drive autonomous workflows.

In this session, learn how to build a serverless-first chatbot application 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.

Migrating from Oracle to PostgreSQL often raises questions about replacing powerful Oracle features like Materialized Views, Flashback Queries, Virtual Columns, Oracle RAC, and PL/SQL Packages.

In this chalk talk, explore key design considerations for building cost-effective generative AI applications. Learn about model selection and optimization techniques, focusing on strategies for optimizing the Retrieval Augmented Generation (RAG) architecture.

The integration of embeddings generated from LLMs for Amazon Aurora PostgreSQL-Compatible Edition and Amazon RDS for PostgreSQL presents a powerful and efficient solution for optimizing the product catalog similarity search experience.

In this session, learn how to build a serverless-first chatbot application by leveraging Amazon Aurora as a vector store and Amazon ElastiCache Serverless for chat history storage. Discover how to harness these services to create contextually aware chatbots.

Amazon Aurora is a fully managed relational database designed for high performance and availability at global scale with full MySQL and PostgreSQL compatibility. Aurora provides managed high availability (HA) and disaster recovery (DR) capabilities in and across AWS Regions.

The integration of pgvector into existing Online Transaction Processing (OLTP) systems represents a significant advancement in leveraging vector search capabilities within traditional database environments.

The integration of embeddings generated from LLMs for Amazon Aurora PostgreSQL-Compatible Edition and Amazon RDS for PostgreSQL presents a powerful and efficient solution for optimizing the product catalog similarity search experience.

Amazon Aurora PostgreSQL-Compatible Edition supports Trusted Language Extensions (TLE) for PostgreSQL, which is an open source development kit for building PostgreSQL extensions and managing them from a SQL interface.

In this chalk talk, learn about the vector database capabilities of the pgvector extension in Amazon Aurora PostgreSQL-Compatible Edition and Amazon RDS for PostgreSQL.

The integration of embeddings generated using popular large language models (LLMs) with the pgvector open-source extension for PostgreSQL presents a powerful and efficient solution for optimizing the product catalog similarity search experience.