InferenceTargetConfiguration

The configuration for an inference target. An inference target routes requests to a large language model (LLM) provider, either through a built-in connector or an explicitly configured provider.

Inheritors

Types

Link copied to clipboard

The connector-based inference configuration. Use this option to route requests to an LLM provider through a built-in connector that includes predefined provider rules.

Link copied to clipboard

The provider-based inference configuration. Use this option to explicitly configure the endpoint, model mapping, and operations for an LLM provider.

Link copied to clipboard

Functions