评估生成式 AI 智能体

reference_trajectory = [
# example 1
[
  {
    "tool_name": "set_device_info",
    "tool_input": {
        "device_id": "device_2",
        "updates": {
            "status": "OFF"
        }
    }
  }
],
# example 2
[
    {
      "tool_name": "get_user_preferences",
      "tool_input": {
          "user_id": "user_y"
      }
  },
  {
      "tool_name": "set_temperature",
      "tool_input": {
          "location": "Living Room",
          "temperature": 23
      }
    },
  ]
]

predicted_trajectory = [
# example 1
[
  {
    "tool_name": "set_device_info",
    "tool_input": {
        "device_id": "device_3",
        "updates": {
            "status": "OFF"
        }
    }
  }
],
# example 2
[
    {
      "tool_name": "get_user_preferences",
      "tool_input": {
          "user_id": "user_z"
      }
    },
    {
      "tool_name": "set_temperature",
      "tool_input": {
          "location": "Living Room",
          "temperature": 23
      }
    },
  ]
]

eval_dataset = pd.DataFrame({
    "predicted_trajectory": predicted_trajectory,
    "reference_trajectory": reference_trajectory,
})

# dataset name to be imported
dataset = "on-device" # Alternatives: "customer-support", "content-creation"

# copy the tools and dataset file
!gcloud storage cp gs://cloud-ai-demo-datasets/agent-eval-datasets/{dataset}/tools.py .
!gcloud storage cp gs://cloud-ai-demo-datasets/agent-eval-datasets/{dataset}/eval_dataset.json .

# load the dataset examples
import json

eval_dataset = json.loads(open('eval_dataset.json').read())

# run the tools file
%run -i tools.py

single_tool_use_metric = TrajectorySingleToolUse(tool_name='tool_name')

eval_task = EvalTask(
    dataset=EVAL_DATASET,
    metrics=[
        "rouge_l_sum",
        "bleu",
        custom_trajectory_eval_metric, # custom computation-based metric
        "trajectory_exact_match",
        "trajectory_precision",
        single_tool_use_metric,
        response_follows_trajectory_metric # llm-based metric
    ],
)
eval_result = eval_task.evaluate(
    runnable=RUNNABLE,
)

response_follows_trajectory_prompt_template = PointwiseMetricPromptTemplate(
    criteria={
        "Follows trajectory": (
            "Evaluate whether the agent's response logically follows from the "
            "sequence of actions it took. Consider these sub-points:\n"
            "  - Does the response reflect the information gathered during the trajectory?\n"
            "  - Is the response consistent with the goals and constraints of the task?\n"
            "  - Are there any unexpected or illogical jumps in reasoning?\n"
            "Provide specific examples from the trajectory and response to support your evaluation."
        )
    },
    rating_rubric={
        "1": "Follows trajectory",
        "0": "Does not follow trajectory",
    },
    input_variables=["prompt", "predicted_trajectory"],
)

response_follows_trajectory_metric = PointwiseMetric(
    metric="response_follows_trajectory",
    metric_prompt_template=response_follows_trajectory_prompt_template,
)

def essential_tools_present(instance, required_tools = ["tool1", "tool2"]):
    trajectory = instance["predicted_trajectory"]
    tools_present = [tool_used['tool_name'] for tool_used in trajectory]
    if len(required_tools) == 0:
      return {"essential_tools_present": 1}
    score = 0
    for tool in required_tools:
      if tool in tools_present:
        score += 1
    return {
        "essential_tools_present": score/len(required_tools),
    }

custom_trajectory_eval_metric = CustomMetric(name="essential_tools_present", metric_function=essential_tools_present)