Welcome to SuperDuperDB!
What is SuperDuperDB?​
SuperDuperDB is an open-source framework with the mission to bring AI to the database. With SuperDuperDB, you can integrate any ML model (i.e. from PyTorch, Sklearn, HuggingFace) and AI API (like OpenAI, Anthrophic, Cohere) directly with your existing databases, including streaming inference, scalable model training and vector search.
SuperDuperDB makes your existing preferred database super duper by transforming it into an AI development and deployment environment, eliminating the need for complex MLOps pipelines, specialized vector databases - and the need to migrate and duplicate data. It's not a database; it transforms your database into an AI powerhouse!
It is designed for Python developers, data scientists, ML engineers, and infrastructure engineers to build and manage AI applications with their own data more easily, directly on top of their databases in a single scalable deployment.
By integrating AI at the data's source, we aim to make building AI applications more easily and flexibly: Not just for use in standard machine learning use-cases like classification, segmentation, recommendation etc., but also generative AI & LLM-chat, vector search as well as highly custom AI applications and workflows involving ultra specialized models.
SuperDuperDB provides a simple Python interface, but allows experts to drill down to any level of implementation detail such as models weights or training details. Also it allows you to add any function, program, script or algorithm from the Python ecosystem to enhance your workflows and applications - and to combine it with your favorite tooling like FastAPI.
For a high-level introduction to SuperDuperDB refer to the README.md of the open-source code-base of on GitHub.
This documentation will help you getting started, and with detailed explanations and usage of superduperdb. Let's get started. 🚀