fix several bugs in proposal and runner

rdagent/scenarios/kaggle/developer/feedback.py

@@ -163,7 +163,7 @@ def generate_feedback(self, exp: Experiment, hypothesis: Hypothesis, trace: Trac
             self.scen.vector_base.add_experience_to_vector_base(experiment_feedback)
             self.scen.vector_base.save()
         elif self.scen.if_using_graph_rag:
-            self.scen.trace.knowledge_base.load_from_documents([experiment_feedback], self.scen)
+            trace.knowledge_base.load_from_documents([experiment_feedback], self.scen)
 
         return HypothesisFeedback(
             observations=observations,

rdagent/scenarios/kaggle/developer/runner.py

@@ -32,6 +32,48 @@ def get_cache_key(self, exp: ASpecificExp) -> str:
         codes = "\n".join(codes)
         return md5_hash(codes)
 
+    def extract_model_task_from_code(self, code: str) -> str:
+        sys_prompt = (
+            Environment(undefined=StrictUndefined)
+            .from_string(prompt_dict["extract_model_task_from_code"]["system"])
+            .render()
+        )
+
+        user_prompt = (
+            Environment(undefined=StrictUndefined)
+            .from_string(prompt_dict["extract_model_task_from_code"]["user"])
+            .render(file_content=code)
+        )
+
+        model_task_description = APIBackend().build_messages_and_create_chat_completion(
+            user_prompt=user_prompt,
+            system_prompt=sys_prompt,
+            json_mode=True,
+        )
+
+        try:
+            response_json_analysis = json.loads(model_task_description)
+            task_desc = f"""name: {response_json_analysis['name']}
+        description: {response_json_analysis['description']}
+        """
+            task_desc += (
+                f"formulation: {response_json_analysis['formulation']}\n"
+                if response_json_analysis.get("formulation")
+                else ""
+            )
+            task_desc += f"architecture: {response_json_analysis['architecture']}\n"
+            task_desc += (
+                f"variables: {json.dumps(response_json_analysis['variables'], indent=4)}\n"
+                if response_json_analysis.get("variables")
+                else ""
+            )
+            task_desc += f"hyperparameters: {json.dumps(response_json_analysis['hyperparameters'], indent=4)}\n"
+            task_desc += f"model_type: {response_json_analysis['model_type']}\n"
+        except json.JSONDecodeError:
+            task_desc = "Failed to parse LLM's response as JSON"
+
+        return task_desc
+
     def init_develop(self, exp: KGFactorExperiment | KGModelExperiment) -> KGFactorExperiment | KGModelExperiment:
         """
         For the initial development, the experiment serves as a benchmark for feature engineering.
@@ -120,48 +162,6 @@ def develop(self, exp: KGModelExperiment) -> KGModelExperiment:
 
 
 class KGFactorRunner(KGCachedRunner[KGFactorExperiment]):
-    def extract_model_task_from_code(self, code: str) -> str:
-        sys_prompt = (
-            Environment(undefined=StrictUndefined)
-            .from_string(prompt_dict["extract_model_task_from_code"]["system"])
-            .render()
-        )
-
-        user_prompt = (
-            Environment(undefined=StrictUndefined)
-            .from_string(prompt_dict["extract_model_task_from_code"]["user"])
-            .render(file_content=code)
-        )
-
-        model_task_description = APIBackend().build_messages_and_create_chat_completion(
-            user_prompt=user_prompt,
-            system_prompt=sys_prompt,
-            json_mode=True,
-        )
-
-        try:
-            response_json_analysis = json.loads(model_task_description)
-            task_desc = f"""name: {response_json_analysis['name']}
-        description: {response_json_analysis['description']}
-        """
-            task_desc += (
-                f"formulation: {response_json_analysis['formulation']}\n"
-                if response_json_analysis.get("formulation")
-                else ""
-            )
-            task_desc += f"architecture: {response_json_analysis['architecture']}\n"
-            task_desc += (
-                f"variables: {json.dumps(response_json_analysis['variables'], indent=4)}\n"
-                if response_json_analysis.get("variables")
-                else ""
-            )
-            task_desc += f"hyperparameters: {json.dumps(response_json_analysis['hyperparameters'], indent=4)}\n"
-            task_desc += f"model_type: {response_json_analysis['model_type']}\n"
-        except json.JSONDecodeError:
-            task_desc = "Failed to parse LLM's response as JSON"
-
-        return task_desc
-
     def develop(self, exp: KGFactorExperiment) -> KGFactorExperiment:
         if exp.based_experiments and exp.based_experiments[-1].result is None:
             exp.based_experiments[-1] = self.init_develop(exp.based_experiments[-1])

rdagent/scenarios/kaggle/proposal/proposal.py

@@ -252,14 +252,15 @@ def convert_response(self, response: str) -> ModelHypothesis:
         response_dict = json.loads(response)
 
         hypothesis = KGHypothesis(
-            hypothesis=response_dict["hypothesis"],
-            reason=response_dict["reason"],
-            concise_reason=response_dict["concise_reason"],
-            concise_observation=response_dict["concise_observation"],
-            concise_justification=response_dict["concise_justification"],
-            concise_knowledge=response_dict["concise_knowledge"],
-            action=response_dict["action"],
+            hypothesis=response_dict.get("hypothesis", "Hypothesis not provided"),
+            reason=response_dict.get("reason", "Reason not provided"),
+            concise_reason=response_dict.get("concise_reason", "Concise reason not provided"),
+            concise_observation=response_dict.get("concise_observation", "Concise observation not provided"),
+            concise_justification=response_dict.get("concise_justification", "Concise justification not provided"),
+            concise_knowledge=response_dict.get("concise_knowledge", "Concise knowledge not provided"),
+            action=response_dict.get("action", "Action not provided"),
         )
+
         return hypothesis
 
 
@@ -309,10 +310,10 @@ def convert_feature_experiment(self, response: str, trace: Trace) -> KGFactorExp
             variables = response_dict[factor_name]["variables"]
             tasks.append(
                 FactorTask(
-                    factor_name=factor_name,
-                    factor_description=description,
-                    factor_formulation=formulation,
-                    variables=variables,
+                    factor_name=response_dict.get("factor_name", "Factor name not provided"),
+                    factor_description=response_dict.get("factor_description", "Factor description not provided"),
+                    factor_formulation=response_dict.get("factor_formulation", "Factor formulation not provided"),
+                    variables=response_dict.get("variables", "Variables not provided"),
                     version=2,
                 )
             )
@@ -327,11 +328,11 @@ def convert_model_experiment(self, response: str, trace: Trace) -> KGModelExperi
         tasks = []
         tasks.append(
             ModelTask(
-                name=response_dict["model_name"],
-                description=response_dict["description"],
-                architecture=response_dict["architecture"],
-                hyperparameters=response_dict["hyperparameters"],
-                model_type=response_dict["model_type"],
+                name=response_dict.get("model_name", "Model name not provided"),
+                description=response_dict.get("description", "Description not provided"),
+                architecture=response_dict.get("architecture", "Architecture not provided"),
+                hyperparameters=response_dict.get("hyperparameters", "Hyperparameters not provided"),
+                model_type=response_dict.get("model_type", "Model type not provided"),
                 version=2,
             )
         )