update requirement and example, recover legacy code

examples/di/machine_learning_with_tools.py → examples/di/machine_learning_complex.py

@@ -4,7 +4,7 @@
 
 
 async def main(requirement: str):
-    role = DataInterpreter(tools=["<all>"])
+    role = DataInterpreter(use_reflection=True, tools=["<all>"])
     await role.run(requirement)
 
 

metagpt/strategy/task_type.py

@@ -19,29 +19,31 @@ class TaskTypeDef(BaseModel):
 
 
 class TaskType(Enum):
+    """By identifying specific types of tasks, we can inject human priors (guidance) to help task solving"""
+
     EDA = TaskTypeDef(
         name="eda",
         desc="For performing exploratory data analysis",
         guidance=EDA_PROMPT,
     )
     DATA_PREPROCESS = TaskTypeDef(
-        name="data_preprocess",
+        name="data preprocessing",
         desc="For preprocessing dataset in a data analysis or machine learning task ONLY,"
         "general data operation doesn't fall into this type",
         guidance=DATA_PREPROCESS_PROMPT,
     )
     FEATURE_ENGINEERING = TaskTypeDef(
-        name="feature_engineering",
+        name="feature engineering",
         desc="Only for creating new columns for input data.",
         guidance=FEATURE_ENGINEERING_PROMPT,
     )
     MODEL_TRAIN = TaskTypeDef(
-        name="model_train",
+        name="model train",
         desc="Only for training model.",
         guidance=MODEL_TRAIN_PROMPT,
     )
     MODEL_EVALUATE = TaskTypeDef(
-        name="model_evaluate",
+        name="model evaluate",
         desc="Only for evaluating model.",
         guidance=MODEL_EVALUATE_PROMPT,
     )

metagpt/tools/tool_recommend.py

@@ -62,7 +62,7 @@ class ToolRecommender(BaseModel):
     """
 
     tools: dict[str, Tool] = {}
-    force: bool = False
+    force: bool = False  # whether to forcedly recommend the specified tools
 
     @field_validator("tools", mode="before")
     @classmethod
@@ -145,6 +145,26 @@ async def rank_tools(
         return list(valid_tools.values())[:topk]
 
 
+class TypeMatchToolRecommender(ToolRecommender):
+    """
+    A legacy ToolRecommender using task type matching at the recall stage:
+    1. Recall: Find tools based on exact match between task type and tool tag;
+    2. Rank: LLM rank, the same as the default ToolRecommender.
+    """
+
+    async def recall_tools(self, context: str = "", plan: Plan = None, topk: int = 20) -> list[Tool]:
+        if not plan:
+            return list(self.tools.values())[:topk]
+
+        # find tools based on exact match between task type and tool tag
+        task_type = plan.current_task.task_type
+        candidate_tools = TOOL_REGISTRY.get_tools_by_tag(task_type)
+        candidate_tool_names = set(self.tools.keys()) & candidate_tools.keys()
+        recalled_tools = [candidate_tools[tool_name] for tool_name in candidate_tool_names]
+
+        return recalled_tools[:topk]
+
+
 class BM25ToolRecommender(ToolRecommender):
     """
     A ToolRecommender using BM25 at the recall stage:

requirements.txt

@@ -71,3 +71,5 @@ Pillow
 imap_tools==1.5.0  # Used by metagpt/tools/libs/email_login.py
 qianfan==0.3.2
 dashscope==1.14.1
+rank-bm25==0.2.2  # for tool recommendation
+jieba==0.42.1  # for tool recommendation