Azure Foundry agent evaluator wrappers for LangGraph.
Provides wrappers around Foundry's built-in agent evaluators (TaskCompletion, TaskAdherence, ToolCallAccuracy, etc.) that can be used as LangGraph node functions or standalone evaluators.
These wrappers handle:
client.evals.create()client.evals.runs.create()Usage requires azure-ai-projects >= 2.0.0 and a Foundry project endpoint.
Result from a Foundry evaluation run.
Wrapper around a single Foundry agent evaluator.
Manages the lifecycle of creating an eval definition and running evaluations against it. Each instance corresponds to one evaluator type (e.g., TaskCompletion).
Run multiple Foundry evaluators in sequence.
Convenience class that holds multiple FoundryEvaluator instances
and runs them all against the same input.