We use PyLance for performing searches in databases which do not have a vector-comparison engine. However we use the primary database as the store of vectors and model outputs.
SuperDuperDB allows you to integrate AI models and APIs. In this case we use the OpenAI API as an example. You can switch for other supported APIs, or models, and even bring your own models and APIs.
Very nice project, after looking into the project, it looks like compute and datalayer are separated, making it possible to scale both parts independently.