add simple summarizer

experiencemaker/model/base_embedding_model.py

@@ -7,8 +7,6 @@ from pydantic import BaseModel, Field
 from experiencemaker.schema.vector_store_node import VectorStoreNode
 from experiencemaker.utils.registry import Registry
 
-EMBEDDING_MODEL_REGISTRY = Registry("embedding_model")
-
 
 class BaseEmbeddingModel(BaseModel, ABC):
     model_name: str = Field(default=..., description="model name")
@@ -87,3 +85,6 @@ class BaseEmbeddingModel(BaseModel, ABC):
 
         else:
             raise RuntimeError(f"unsupported type={type(nodes)}")
+
+
+EMBEDDING_MODEL_REGISTRY = Registry[BaseEmbeddingModel]("embedding_model")

experiencemaker/model/base_llm.py

@@ -8,7 +8,6 @@ from experiencemaker.schema.trajectory import Message, ActionMessage
 from experiencemaker.tool.base_tool import BaseTool
 from experiencemaker.utils.registry import Registry
 
-LLM_REGISTRY = Registry("llm")
 
 class BaseLLM(BaseModel, ABC):
     model_name: str = Field(...)
@@ -110,3 +109,6 @@ class BaseLLM(BaseModel, ABC):
                     raise e
 
         return None
+
+
+LLM_REGISTRY = Registry[BaseLLM]("llm")

experiencemaker/module/agent_wrapper/agent_wrapper_mixin.py

@@ -9,6 +9,7 @@ from experiencemaker.utils.registry import Registry
 
 class AgentWrapperMixin(BaseModel, ABC):
     context_generator: BaseContextGenerator | None = Field(default=None)
+    workspace_id: str = Field(default="")
 
     def execute(self, query: str, **kwargs) -> Trajectory:
         raise NotImplementedError

experiencemaker/module/context_generator/base_context_generator.py

@@ -3,6 +3,8 @@ from typing import List
 
 from pydantic import Field, BaseModel
 
+from experiencemaker.model.base_embedding_model import BaseEmbeddingModel
+from experiencemaker.model.base_llm import BaseLLM
 from experiencemaker.schema.trajectory import Trajectory, ContextMessage
 from experiencemaker.schema.vector_store_node import VectorStoreNode
 from experiencemaker.storage.base_vector_store import BaseVectorStore
@@ -11,6 +13,9 @@ from experiencemaker.utils.registry import Registry
 
 class BaseContextGenerator(BaseModel, ABC):
     vector_store: BaseVectorStore | None = Field(default=None)
+    llm: BaseLLM | None = Field(default=None)
+    embedding_model: BaseEmbeddingModel | None = Field(default=None)
+    workspace_id: str = Field(default="")
 
     def _build_retrieve_query(self, trajectory: Trajectory, **kwargs) -> str:
         raise NotImplementedError

experiencemaker/module/summarizer/base_summarizer.py

@@ -3,24 +3,33 @@ from typing import List
 
 from pydantic import Field, BaseModel
 
-from experiencemaker.schema.trajectory import Trajectory, Sample
+from experiencemaker.model.base_embedding_model import BaseEmbeddingModel
+from experiencemaker.model.base_llm import BaseLLM
+from experiencemaker.schema.experience import Experience
+from experiencemaker.schema.trajectory import Trajectory
+from experiencemaker.schema.vector_store_node import VectorStoreNode
 from experiencemaker.storage.base_vector_store import BaseVectorStore
+from experiencemaker.utils.registry import Registry
 
 
 class BaseSummarizer(BaseModel, ABC):
     vector_store: BaseVectorStore | None = Field(default=None)
+    llm: BaseLLM | None = Field(default=None)
+    embedding_model: BaseEmbeddingModel | None = Field(default=None)
+    workspace_id: str = Field(default="")
 
-    def _extract_samples(self, trajectories: List[Trajectory], **kwargs) -> List[Sample]:
+    def _extract_experiences(self, trajectories: List[Trajectory], **kwargs) -> List[Experience]:
         raise NotImplementedError
 
-    def _insert_into_database(self, samples: List[Sample], **kwargs):
-        raise NotImplementedError
+    def execute(self, trajectories: List[Trajectory], return_experience: bool = True, **kwargs) -> List[Experience]:
+        experiences: List[Experience] = self._extract_experiences(trajectories, **kwargs)
 
-    def execute(self, trajectories: List[Trajectory], return_samples: bool = True, **kwargs) -> List[Sample]:
-        samples: List[Sample] = self._extract_samples(trajectories, **kwargs)
-        self._insert_into_database(samples, **kwargs)
+        nodes: List[VectorStoreNode] = [x.to_vector_store_node() for x in experiences]
+        self.vector_store.insert(nodes, **kwargs)
 
-        if return_samples:
-            return samples
+        if return_experience:
+            return experiences
+        return []
 
-        return []
+
+SUMMARIZER_REGISTRY = Registry[BaseSummarizer]("summarizer")

experiencemaker/module/summarizer/simple_summarizer.py

@@ -0,0 +1,68 @@
+from pathlib import Path
+from typing import List
+
+from loguru import logger
+from pydantic import Field
+
+from experiencemaker.enumeration.role import Role
+from experiencemaker.module.prompt.prompt_mixin import PromptMixin
+from experiencemaker.module.summarizer.base_summarizer import BaseSummarizer, SUMMARIZER_REGISTRY
+from experiencemaker.schema.experience import Experience
+from experiencemaker.schema.trajectory import Trajectory, Message, ActionMessage
+from experiencemaker.utils.util_function import get_html_match_content
+
+
+class SimpleSummarizer(BaseSummarizer, PromptMixin):
+    max_retries: int = Field(default=5, description="max retries")
+    prompt_file_path: Path = Path(__file__).parent / "simple_summarizer_prompt.yaml"
+
+    def _extract_trajectory_experience(self, trajectory: Trajectory) -> Experience | None:
+        step_content_collector: List[str] = []
+
+        for step in trajectory.steps:
+            step_index = len(step_content_collector)
+
+            if step.role is Role.ASSISTANT:
+                line = f"### step.{step_index} role={step.role.value} content=\n{step.content}\n{step.reasoning_content}\n"
+                if step.tool_calls:
+                    for tool_call in step.tool_calls:
+                        line += f" - tool call={tool_call.name}\n   params={tool_call.arguments}\n"
+                step_content_collector.append(line)
+
+            elif step.role is Role.USER:
+                line = f"### step.{step_index} role={step.role.value} content=\n{step.content}\n"
+                step_content_collector.append(line)
+
+            elif step.role is Role.TOOL:
+                line = f"### step.{step_index} role={step.role.value} tool call result=\n{step.content}\n"
+                step_content_collector.append(line)
+
+        prompt = self.prompt_format(prompt_name="summary_prompt",
+                                    query=trajectory.query,
+                                    execution_process="\n".join(step_content_collector).strip(),
+                                    answer=trajectory.answer)
+
+        for i in range(self.max_retries):
+            action_message: ActionMessage = self.llm.chat(messages=[Message(content=prompt)])
+            experience_str = get_html_match_content(action_message.content, key="experience")
+            condition_str = get_html_match_content(action_message.content, key="condition")
+            if experience_str and condition_str:
+                return Experience(experience_workspace_id=self.workspace_id,
+                                  experience_role=self.llm.model_name,
+                                  experience_desc=condition_str,
+                                  experience_content=experience_str)
+            else:
+                logger.warning(f"action_message.content={action_message.content} re.search failed.")
+
+        return None
+
+    def _extract_experiences(self, trajectories: List[Trajectory], **kwargs) -> List[Experience]:
+        experiences: List[Experience] = []
+        for trajectory in trajectories:
+            experience: Experience = self._extract_trajectory_experience(trajectory)
+            if experience:
+                experiences.append(experience)
+        return experiences
+
+
+SUMMARIZER_REGISTRY.register(SimpleSummarizer, "simple")

experiencemaker/module/summarizer/simple_summarizer_prompt.yaml

@@ -0,0 +1,22 @@
+summary_prompt: |
+  # Role
+  You are a helpful assistant named BeyondAgent.
+
+  # User Question
+  {query}
+
+  # Execution Process
+  {execution_process}
+
+  # Answer
+  {answer}
+
+  # Task
+  Reflect on the strengths and weaknesses of the **Execution Process** and the **Answer** based on the **User Question**.  
+  Finally, summarize generalized experience from handling such problems to accumulate experience for future similar tasks.  
+  The experience should be broadly applicable, such as how to use tools effectively or approaches to solving certain types of problems.  
+  Also, specify the conditions or scenarios in which these experience are applicable.
+    
+  # Output Format
+  <condition> Output the scenarios or conditions in which applying this experience would be particularly effective... </condition>
+  <experience> Output generalized experience, concise content is required... </experience>

experiencemaker/schema/experience.py

@@ -0,0 +1,83 @@
+import datetime
+from typing import List
+from uuid import uuid4
+
+from pydantic import BaseModel, Field
+
+from experiencemaker.schema.vector_store_node import VectorStoreNode
+
+
+class ExperienceFunctionArg(BaseModel):
+    arg_name: str = Field(default=..., description="argument name")
+    arg_type: str = Field(default=..., description="argument type, like: 'str', 'int', 'bool'")
+    required: bool = Field(default=True, description="whether the argument is required")
+
+
+class ExperienceFunction(BaseModel):
+    func_code: str = Field(default=..., description="function code")
+    func_name: str = Field(default=..., description="function name")
+    func_args: List[ExperienceFunctionArg] = Field(default_factory=list, description="function arguments")
+
+
+class Experience(BaseModel):
+    experience_id: str = Field(default_factory=lambda: uuid4().hex, description="experience unique id")
+    experience_workspace_id: str = Field(default="", description="unique workspace id")
+    experience_role: str = Field(default="", description="experience role")
+    experience_desc: str = Field(default="", description="use condition/purpose. It will be used in vector matching")
+    experience_content: str | bytes = Field(default="", description="content of the experience")
+    experience_function: ExperienceFunction | None = Field(default=None, description="experience function(optional)")
+    experience_score: float = Field(default=0.0, description="score of the experience")
+    experience_created_time: str = Field(default_factory=lambda: datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
+    experience_modified_time: str = Field(default_factory=lambda: datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
+    metadata: dict = Field(default_factory=dict, description="additional metadata")
+
+    def to_vector_store_node(self) -> VectorStoreNode:
+        metadata: dict = {
+            "experience_role": self.experience_role,
+            "experience_content": self.experience_content,
+            "experience_function": self.experience_function.model_dump(),
+            "experience_score": self.experience_score,
+            "experience_created_time": self.experience_created_time,
+            "experience_modified_time": self.experience_modified_time,
+            "metadata": self.metadata,
+        }
+        return VectorStoreNode(
+            unique_id=self.experience_id,
+            workspace_id=self.experience_workspace_id,
+            content=self.experience_desc,
+            metadata=metadata)
+
+    @classmethod
+    def from_vector_store_node(cls, node: VectorStoreNode) -> "Experience":
+        return cls(
+            experience_id=node.unique_id,
+            experience_workspace_id=node.workspace_id,
+            experience_role=node.metadata.get("experience_role", ""),
+            experience_desc=node.content,
+            experience_content=node.metadata.get("experience_content", ""),
+            experience_function=node.metadata.get("experience_function", None),
+            experience_score=node.metadata.get("experience_score", 0.0),
+            experience_created_time=node.metadata.get("experience_created_time", ""),
+            experience_modified_time=node.metadata.get("experience_modified_time", ""),
+            metadata=node.metadata.get("metadata", {}))
+
+
+if __name__ == "__main__":
+    e1 = Experience(
+        experience_workspace_id="w_1024",
+        experience_role="qwen3",
+        experience_desc="test desc",
+        experience_content="test content",
+        experience_function=ExperienceFunction(
+            func_code="def a():\n    return",
+            func_name="a",
+            func_args=[ExperienceFunctionArg(arg_name="x", arg_type="str", required=True)]
+        ),
+        experience_score=0.99,
+        metadata={"haha": 1}
+    )
+    print(e1.model_dump_json(indent=2))
+    v1 = e1.to_vector_store_node()
+    print(v1.model_dump_json(indent=2))
+    e2 = Experience.from_vector_store_node(v1)
+    print(e2.model_dump_json(indent=2))

experiencemaker/schema/trajectory.py

@@ -118,11 +118,3 @@ class Trajectory(BaseModel):
         self.query = ""
         self.answer = ""
         self.metadata.clear()
-
-
-class Experience(BaseModel):
-    experience_id: str = Field(default_factory=lambda: uuid4().hex, description="experience unique id")
-    experience_desc: str = Field(default="", description="use condition or use purpose for vector matching")
-    experience_content: str | bytes = Field(default="", description="content of the experience")
-    experience_score: float = Field(default=0.0, description="score of the experience")
-    metadata: dict = Field(default_factory=dict, description="additional metadata")

experiencemaker/storage/__init__.py

@@ -1,3 +0,0 @@
-from experiencemaker.utils.registry import Registry
-
-VECTOR_STORE_REGISTRY = Registry("vector_store")

experiencemaker/storage/base_vector_store.py

@@ -5,6 +5,7 @@ from pydantic import BaseModel, Field
 
 from experiencemaker.model.base_embedding_model import BaseEmbeddingModel
 from experiencemaker.schema.vector_store_node import VectorStoreNode
+from experiencemaker.utils.registry import Registry
 
 
 class BaseVectorStore(BaseModel, ABC):
@@ -24,3 +25,6 @@ class BaseVectorStore(BaseModel, ABC):
 
     def retrieve_by_query(self, query: str, top_k: int = 3, **kwargs) -> List[VectorStoreNode]:
         raise NotImplementedError
+
+
+VECTOR_STORE_REGISTRY = Registry[BaseVectorStore]("vector_store")

experiencemaker/storage/es_vector_store.py

@@ -7,8 +7,7 @@ from loguru import logger
 from pydantic import Field, PrivateAttr, model_validator
 
 from experiencemaker.schema.vector_store_node import VectorStoreNode
-from experiencemaker.storage import VECTOR_STORE_REGISTRY
-from experiencemaker.storage.base_vector_store import BaseVectorStore
+from experiencemaker.storage.base_vector_store import BaseVectorStore, VECTOR_STORE_REGISTRY
 
 
 class EsVectorStore(BaseVectorStore):
@@ -104,7 +103,7 @@ class EsVectorStore(BaseVectorStore):
         self.retrieve_filters.clear()
         return self
 
-    def insert(self, nodes: VectorStoreNode | List[VectorStoreNode], refresh_index: bool = False, **kwargs):
+    def insert(self, nodes: VectorStoreNode | List[VectorStoreNode], refresh_index: bool = True, **kwargs):
         if isinstance(nodes, VectorStoreNode):
             nodes = [nodes]
 
@@ -119,7 +118,7 @@ class EsVectorStore(BaseVectorStore):
         if refresh_index:
             self.refresh_index()
 
-    def update(self, nodes: VectorStoreNode | List[VectorStoreNode], refresh_index: bool = False, **kwargs):
+    def update(self, nodes: VectorStoreNode | List[VectorStoreNode], refresh_index: bool = True, **kwargs):
         if isinstance(nodes, VectorStoreNode):
             nodes = [nodes]
 

experiencemaker/storage/file_vector_store.py

@@ -8,8 +8,7 @@ from loguru import logger
 from pydantic import Field, model_validator, PrivateAttr
 
 from experiencemaker.schema.vector_store_node import VectorStoreNode
-from experiencemaker.storage import VECTOR_STORE_REGISTRY
-from experiencemaker.storage.base_vector_store import BaseVectorStore
+from experiencemaker.storage.base_vector_store import BaseVectorStore, VECTOR_STORE_REGISTRY
 
 
 class FileVectorStore(BaseVectorStore):