agent_eval
autogen.agentchat.contrib.agent_eval.agent_eval.quantify_criteria
quantify_criteria
Quantifies the performance of a system using the provided criteria.
Parameters:Name | Description |
---|---|
llm_config | llm inference configuration. Type: dict | Literal[False] | None Default: None |
criteria | A list of criteria for evaluating the utility of a given task. Type: list[autogen.agentchat.contrib.agent_eval.criterion.Criterion] Default: None |
task | The task to evaluate. Type: autogen.agentchat.contrib.agent_eval.task.Task Default: None |
test_case | The test case to evaluate. Type: str Default: ” |
ground_truth | The ground truth for the test case. Type: str Default: ” |