Tutorials

In this section we guide newcomers through the most basic usage pattern in Superduper.

For more detailed, flexible and realistic use-cases, refer to the use-cases section.

📄️ Vector search

Since vector-search is all-the-rage right now,

📄️ Listening for new data

In Superduper, AI models may be configured to listen for newly inserted data.

📄️ Basic RAG tutorial

In this tutorial we show you how to do retrieval augmented generation (RAG) with Superduper.

📄️ Real time, database integrated agents, with integrated actions

AI agents are relevant for a huge range of computer bound knowledge work, in which the individual component steps can be accessed programmatically. The range of possible agents is limited only by the tools we have to connect data, AI models in a useful environment. A very powerful-scuh environment is superduper.

📄️ Training and Managing MNIST Predictions with superduper

This tutorial guides you through the implementation of a classic machine learning task: MNIST handwritten digit recognition. The twist? We perform the task directly on data hosted in a database using superduper.

📄️ Custom serialization

In this tutorial, we demonstrate how developers can flexibily and portably define

📄️ Reusable Superduper applications and templates

Superduper includes two components, Application and Template, to help users more easily build reusable Superduper applications.

📄️ Superduper-protocol

📄️ Using AI to self-referentially create Superduper components

In this example we create a component which can create tasks which run on Superduper.