Skip to main content

Community Support

The primary way in which developers will integrate and implement functionality from popular AI frameworks, is via the Predictor and Model abstractions.

The Predictor mixin class, interfaces with all AI frameworks and API providers, which provide self.predict functionality, and is subclassed by:

classframework
superduperdb.ext.sklearn.EstimatorScikit-Learn
superduperdb.ext.transformers.PipelineHugging Face's transformers
superduperdb.ext.torch.TorchModelPyTorch
superduperdb.ext.openai.OpenAIOpenAI
superduperdb.ext.cohere.CohereCohere
superduperdb.ext.anthropic.AnthropicAnthropic
superduperdb.ext.jina.JinaJina

The Model class is subclassed by:

classframework
superduperdb.ext.sklearn.EstimatorScikit-Learn
superduperdb.ext.transformers.PipelineHugging Face's transformers
superduperdb.ext.torch.TorchModelPyTorch

Model instances implement self.predict, but also hold import data, such as model weights, parameters or hyperparameters. In addition, Model may implement self.fit functionality - model training and calibration.