⇽ Bruce Momjian ⇽

Postgres Artificial Intelligence Presentations


Postgres and the Artificial Intelligence Landscape

Artificial intelligence, machine learning, and deep learning are intertwined capabilities that attempt to solve problems that defy traditional computational solutions — problems include fraud detection, voice recognition, and search result recommendations. While they defy simple computation, they are computationally expensive, involving computation of perhaps millions of probabilities and weights. While these computations can be done outside of the database, there are specific advantages of doing machine learning inside the database, close to where the data is stored. This presentation explains how to do machine learning inside the Postgres database, and includes an example of discriminative AI using stored procedures.
Duration: 45 minutes, 60 minutes with questions

Databases in the AI Trenches

Since the creation of my presentation, Postgres and the Artificial Intelligence Landscape, artificial intelligence use has exploded, with much anticipation about its future. This talk explores many of the advances that has fueled this explosion, including multi-dimensional vectors, text embeddings, semantic/vector search, transformers, generative AI, Retrieval-Augmented Generation (rag), and Model Context Protocol (mcp). The talk includes semantic/vector search and rag examples. It finally covers how the valuable data stored in databases can be used to enhance AI usage. This can be combined with the previous presentation.
Duration: 45 minutes, 60 minutes with questions

Postgres as an Mcp Server (no slides yet)

Large language models are good at generating text, but can't easily report discrete, dynamic, and always-accurate results. They also can't take external actions. The model context protocol (mcp) has become the standard way for generative AI models to access external data and take external actions. This talk explains the purpose of mcps, how they are used, and shows examples of database and non-database mcp servers. This can be combined with the previous presentation.