Payal Singh

As AI systems become more complex, developers are discovering that the database, not the model, is the real foundation of reliable AI. In this talk, I'll explore how Postgres can function as a full AI application server by combining Retrieval-Augmented Generation (RAG) with the Model Context Protocol (MCP).

We’ll walk through a real implementation: ingest pipelines, vector search, metadata ranking, caching, provenance tracking, and LLM tool-calling, all powered by Postgres. Then we’ll expose those capabilities over MCP so LLMs can safely query, transform, and orchestrate data.

The result: an end-to-end AI system where your RAG, your tools, your transforms, your logs, and your automation all live in Postgres.

This talk will discuss what data mining is, and how to approach a mining task with the best open source mining library - Pandas in Python. 

This talk will cover the various features that Postgres provides for data security, from the very basic to the most advanced.

Postgres has a variety of features to secure your data in a multitude of ways, each suitable for a specific set of use cases. The goal of this talk is not just to lay out the features available to secure your data, but also to give an idea of when to leverage these features, and how best to implement it. This session will also cover some of the upcoming security features in Postgres 11, and a few gotchas with the existing features

Disaster recovery is perhaps the most ignored aspect of managing PostgreSQL in production systems. If not done right, it can make us repent for ages. Majority of production systems only have at most one defined backup and recovery strategy, not realizing the benefits of using a hybrid solution. Contrary to common perception of treating disaster management as a one model fits all philosophy, emphasis should be given on how various techniques are optimized for disaster scenarios.