diff --git a/agent_system/evaluetor/__init__.py b/agent_system/evaluetor/__init__.py new file mode 100644 index 0000000..e8a40ae --- /dev/null +++ b/agent_system/evaluetor/__init__.py @@ -0,0 +1,5 @@ +from .agent import Evaluator +from .prompt import EvaluatorPrompt +from .response_model import EvaluatorResult, EvaluationDimension + +__all__ = ["Evaluator", "EvaluatorPrompt", "EvaluatorResult", "EvaluationDimension"] \ No newline at end of file diff --git a/workflow/medical_workflow.py b/workflow/medical_workflow.py index 084956d..9587089 100644 --- a/workflow/medical_workflow.py +++ b/workflow/medical_workflow.py @@ -11,7 +11,8 @@ class MedicalWorkflow: """ def __init__(self, case_data: Dict[str, Any], model_type: str = "gpt-oss:latest", - llm_config: Optional[Dict] = None, max_steps: int = 30, log_dir: str = "logs"): + llm_config: Optional[Dict] = None, max_steps: int = 30, log_dir: str = "logs", + case_index: Optional[int] = None): """ 初始化医疗问诊工作流 @@ -21,6 +22,7 @@ class MedicalWorkflow: llm_config: 语言模型配置，默认为None max_steps: 最大执行步数，默认为30 log_dir: 日志目录，默认为"logs" + case_index: 病例序号，用于日志文件命名 """ self.case_data = case_data self.model_type = model_type @@ -30,7 +32,7 @@ class MedicalWorkflow: # 初始化核心组件 self.task_manager = TaskManager() self.step_executor = StepExecutor(model_type=model_type, llm_config=self.llm_config) - self.logger = WorkflowLogger(case_data=case_data, log_dir=log_dir) + self.logger = WorkflowLogger(case_data=case_data, log_dir=log_dir, case_index=case_index) # 初始化工作流状态 self.current_step = 0 diff --git a/workflow/step_executor.py b/workflow/step_executor.py index 1124286..7911ded 100644 --- a/workflow/step_executor.py +++ b/workflow/step_executor.py @@ -6,6 +6,7 @@ from agent_system.controller import TaskController from agent_system.prompter import Prompter from agent_system.inquirer import Inquirer from agent_system.virtual_patient import VirtualPatientAgent +from agent_system.evaluetor import Evaluator from .task_manager import TaskManager, TaskPhase from .workflow_logger import WorkflowLogger @@ -32,6 +33,7 @@ class StepExecutor: self.controller = TaskController(model_type=model_type, llm_config=self.llm_config) self.prompter = Prompter(model_type=model_type, llm_config=self.llm_config) self.virtual_patient = VirtualPatientAgent(model_type=model_type, llm_config=self.llm_config) + self.evaluator = Evaluator(model_type=model_type, llm_config=self.llm_config) def execute_step(self, step_num: int, @@ -123,7 +125,13 @@ class StepExecutor: ) step_result["doctor_question"] = doctor_question - # Step 8: 获取任务完成情况摘要 + # Step 8: 使用Evaluator进行评分 + evaluator_result = self._execute_evaluator( + step_num, logger, case_data, step_result + ) + step_result["evaluator_result"] = evaluator_result + + # Step 9: 获取任务完成情况摘要 step_result["task_completion_summary"] = task_manager.get_completion_summary() step_result["success"] = True @@ -371,4 +379,74 @@ class StepExecutor: error_msg = f"Inquirer执行失败: {str(e)}" logger.log_error(step_num, "inquirer_error", error_msg) # 返回默认问题 - return "请您详细描述一下您的症状，包括什么时候开始的，有什么特点？" \ No newline at end of file + return "请您详细描述一下您的症状，包括什么时候开始的，有什么特点？" + + def _execute_evaluator(self, step_num: int, logger: WorkflowLogger, + case_data: Dict[str, Any], step_result: Dict[str, Any]): + """执行Evaluator agent""" + start_time = time.time() + + try: + # 准备评价器需要的数据格式 + round_data = { + "patient_response": step_result.get("patient_response", ""), + "doctor_inquiry": step_result.get("doctor_question", ""), + "HPI": step_result.get("updated_hpi", ""), + "PH": step_result.get("updated_ph", ""), + "chief_complaint": step_result.get("updated_chief_complaint", "") + } + + # 调用评价器进行单轮评价 + input_data = { + "patient_case": case_data, + "current_round": step_num, + "round_data": round_data + } + + result = self.evaluator.evaluate_single_round( + patient_case=case_data, + round_data=round_data + ) + + execution_time = time.time() - start_time + + output_data = { + "clinical_inquiry": { + "score": result.clinical_inquiry.score, + "comment": result.clinical_inquiry.comment + }, + "communication_quality": { + "score": result.communication_quality.score, + "comment": result.communication_quality.comment + }, + "overall_professionalism": { + "score": result.overall_professionalism.score, + "comment": result.overall_professionalism.comment + }, + "summary": result.summary, + "key_suggestions": result.key_suggestions + } + + logger.log_agent_execution(step_num, "evaluator", input_data, output_data, execution_time) + + return result + + except Exception as e: + error_msg = f"Evaluator执行失败: {str(e)}" + logger.log_error(step_num, "evaluator_error", error_msg) + # 返回默认评价结果 + from agent_system.evaluetor.response_model import EvaluatorResult, EvaluationDimension + + default_dimension = EvaluationDimension(score=0.0, comment="评价失败") + return EvaluatorResult( + clinical_inquiry=default_dimension, + diagnostic_reasoning=default_dimension, + communication_quality=default_dimension, + multi_round_consistency=default_dimension, + overall_professionalism=default_dimension, + present_illness_similarity=default_dimension, + past_history_similarity=default_dimension, + chief_complaint_similarity=default_dimension, + summary="评价失败", + key_suggestions=["系统需要调试"] + ) \ No newline at end of file diff --git a/workflow/workflow_logger.py b/workflow/workflow_logger.py index 6624e7f..610aaa7 100644 --- a/workflow/workflow_logger.py +++ b/workflow/workflow_logger.py @@ -10,16 +10,18 @@ class WorkflowLogger: 负责将每个step的详细信息记录到jsonl格式文件中 """ - def __init__(self, case_data: Dict[str, Any], log_dir: str = "logs"): + def __init__(self, case_data: Dict[str, Any], log_dir: str = "logs", case_index: Optional[int] = None): """ 初始化日志记录器 Args: case_data: 病例数据 - log_dir: 日志目录，默认为"logs" + log_dir: 日志目录，默认为"logs" + case_index: 病例序号，用于文件名标识 """ self.case_data = case_data self.log_dir = log_dir + self.case_index = case_index self.log_file_path = self._generate_log_file_path() self.step_count = 0 @@ -36,15 +38,18 @@ class WorkflowLogger: Returns: str: 日志文件路径 """ - # 生成基于病例内容的唯一标识 - case_str = json.dumps(self.case_data, ensure_ascii=False, sort_keys=True) - case_hash = hashlib.md5(case_str.encode('utf-8')).hexdigest()[:8] - # 生成时间戳 timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") - # 构建文件名 - filename = f"workflow_{timestamp}_{case_hash}.jsonl" + # 构建文件名，如果有序号则包含序号 + if self.case_index is not None: + filename = f"workflow_{timestamp}_case_{self.case_index:04d}.jsonl" + else: + # 生成基于病例内容的唯一标识作为后备 + case_str = json.dumps(self.case_data, ensure_ascii=False, sort_keys=True) + case_hash = hashlib.md5(case_str.encode('utf-8')).hexdigest()[:8] + filename = f"workflow_{timestamp}_{case_hash}.jsonl" + return os.path.join(self.log_dir, filename) def _log_workflow_start(self):