Collected sources and patterns will appear here. Add from search or the patterns library.
StandardizedInferenceRequest -> ProviderSpecificPayload
Translate a standardized text generation request into provider-specific API payloads and parse the varied responses into a uniform output format.
Problem it solves
Integrating and switching between multiple disparate LLM APIs requires writing redundant integration adapters.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.