Wyvern Architecture

- Retrieval: Wyvern can connect to and retrieve objects from your search index.
- Feature Module: Wyvern has the built-in support for feast, an open source feature store. It also supports connecting to the feature store that you would like to use. Moreover, Wyvern provides interfaces for you to define your batch features and real-time features easily, with the support of feature grouping, feature sharing, features for composite entities and request based features.
- Model Module: Wyvern provides the model interface that allows you to define your own model in place or call your model service. It provides an interface to define features that your model depends on easily.
- Business Logic: Wyvern makes defining your business logic easy after the model inference. For example, if your want to promote a specific brand of tshirt and move it to the top of the ranking result for the “tshirt” query.
- Observability and Event Logging: All the events in your ML application, including real-time feature, model, business logic, product impression, as well your own custom events, are being automatically logged by Wyvern and data can be piped to your data warehouse. Refer to Logging Events for more information.
- Training Dataset: Wyvern provides the feature store serving solution (currently integrated only with feast) to serve all data of the historical batch features and the real-time features that are logged in your data warehouse.