adk_eval_llm_judge (erlang_adk v0.7.0)
View SourceBounded first-party rubric judge backed by an ADK LLM provider.
The judge is an explicit full-case metric. It is never selected implicitly by adk_eval_set. Each invocation runs in the caller's existing evaluation sample worker and owns one monitored provider worker; there is no global judge process or serialization point.
Summary
Types
-type judge_error() :: {llm_judge, atom()}.
Functions
-spec score_case(map(), map()) -> {ok, number(), map()} | {error, judge_error()}.
-spec validate_config(map()) -> ok | {error, judge_error()}.