Merge pull request #138 from alipay/dev

 feat: Version 0.0.12 Release

CHANGELOG.md

@@ -24,6 +24,18 @@ Note - Additional remarks regarding the version.
 ***************************************************
 
 # Version Update History
+## [0.0.12] - 2024-08-14
+### Added
+- agentUniverse Product Version Offering
+  - The current version provides basic capabilities for agent construction, modification, and debugging, jointly launched by the difizen project. For more details, please refer to the documentation in the product platform section.
+- Monitor Component: Added knowledge and tool instance collection, supporting full-link trace sequence concatenation and providing token consumption monitoring.
+- New Web Session Module: Provides session and message persistence management capabilities.
+
+### Note
+- Optimized Knowledge Component: Users can configure and specify any number of recall results (similarity_top_k).
+- Fixed Chroma Component: Resolved issues where the embedding module was not specified.
+- Various code optimizations and documentation updates.
+
 ## [0.0.11] - 2024-07-11
 ### Added
 - DataAgent Autonomous Data Agent MVP Version Released

CHANGELOG_zh.md

@@ -24,6 +24,18 @@ Note - 对于版本的额外说明。
 ***************************************************
 
 # 版本更新记录
+## [0.0.12] - 2024-08-14
+### Added
+- agentUniverse产品化版本提供
+  - 当前版本提供智能体构建、修改、调试等基础能力，由difizen项目联合推出，更多详情请见文档产品化平台部分。
+- monitor组件新增对于知识、工具实例采集，支持全链路trace时序串联并提供token消耗监控
+- 新增web会话模块，提供session与message持久化管理能力
+
+### Note
+- 优化知识组件，可由用户配置指定任意召回结果数量（similarity_top_k）
+- 修复chroma组件未指定embedding模块出现异常
+- 其他部分代码优化与文档更新
+
 ## [0.0.11] - 2024-07-11
 ### Added
 - DataAgent数据自治智能体MVP版本发布

README.md

@@ -5,7 +5,7 @@ Language version: [English](./README.md) | [中文](./README_zh.md) | [日本語
 ![](https://img.shields.io/badge/framework-agentUniverse-pink)
 ![](https://img.shields.io/badge/python-3.10%2B-blue?logo=Python)
 [![](https://img.shields.io/badge/%20license-Apache--2.0-yellow)](LICENSE)
-[![Static Badge](https://img.shields.io/badge/pypi-v0.0.11-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
+[![Static Badge](https://img.shields.io/badge/pypi-v0.0.12-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
 
 ![](docs/guidebook/_picture/logo_bar.jpg)
 ****************************************
@@ -55,6 +55,24 @@ We will show you how to:
 For more details, please read the [Quick Start](./docs/guidebook/en/1_3_Quick_Start.md).
 
 ****************************************
+## Using the Product Platform
+agentUniverse provides a local product platform capability. Please follow the steps below for a quick start:
+
+**Install via pip**
+```shell
+pip install magent-ui ruamel.yaml
+```
+
+**One-click Run**
+
+Run the [product_application.py](sample_standard_app/app/bootstrap/product_application.py) file located in sample_standard_app/app/bootstrap for a one-click start.
+
+For more details, refer to [Quick Start for Product Platform](./docs/guidebook/en/10_1_1_Product%20Platform%20Quick%20Start.md).
+
+This feature is jointly launched by [difizen](https://github.com/difizen/magent) and agentUniverse.
+
+****************************************
+
 ## Cases and Example Projects
 ### 🌟 Use Cases
 [Legal Consultation Agent](./docs/guidebook/en/7_1_1_Legal_Consultation_Case.md)

README_zh.md

@@ -5,7 +5,7 @@
 ![](https://img.shields.io/badge/framework-agentUniverse-pink)
 ![](https://img.shields.io/badge/python-3.10%2B-blue?logo=Python)
 [![](https://img.shields.io/badge/%20license-Apache--2.0-yellow)](LICENSE)
-[![Static Badge](https://img.shields.io/badge/pypi-v0.0.11-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
+[![Static Badge](https://img.shields.io/badge/pypi-v0.0.12-blue?logo=pypi)](https://pypi.org/project/agentUniverse/)
 
 ![](docs/guidebook/_picture/logo_bar.jpg)
 ****************************************
@@ -51,6 +51,23 @@ pip install agentUniverse
 * 对agent进行快速服务化
 
 详情请阅读[快速开始](docs/guidebook/zh/1_3_%E5%BF%AB%E9%80%9F%E5%BC%80%E5%A7%8B.md) 。
+****************************************
+## 产品化平台使用
+agentUniverse提供基于本地的产品化平台能力，请按照如下步骤快速启动
+
+**通过pip安装**
+```shell
+pip install magent-ui ruamel.yaml
+```
+
+**一键运行**
+
+运行sample_standard_app/app/boostrap下的[product_application.py](sample_standard_app/app/bootstrap/product_application.py)文件，一键启动。
+
+更多详情参考 [产品化平台快速开始](./docs/guidebook/zh/10_1_1_产品化平台快速开始.md)
+
+本功能由 [difizen](https://github.com/difizen/magent) X agentUniverse联合推出。
+
 ****************************************
 ## 案例与样例工程
 ### 🌟 使用案例

agentuniverse/agent/action/knowledge/knowledge.py

@@ -14,6 +14,7 @@
 from agentuniverse.agent.action.knowledge.store.document import Document
 from agentuniverse.agent.action.knowledge.store.query import Query
 from agentuniverse.agent.action.knowledge.store.store import Store
+from agentuniverse.base.annotation.trace import trace_knowledge
 from agentuniverse.base.component.component_base import ComponentBase
 from agentuniverse.base.component.component_enum import ComponentEnum
 from agentuniverse.base.config.application_configer.application_config_manager import ApplicationConfigManager
@@ -53,6 +54,7 @@ def insert_knowledge(self, **kwargs) -> None:
         document_list: List[Document] = self.reader.load_data()
         self.store.insert_documents(document_list, **kwargs)
 
+    @trace_knowledge
     def query_knowledge(self, **kwargs) -> List[Document]:
         """Query the knowledge.
 

agentuniverse/agent/action/knowledge/store/chroma_store.py

@@ -96,7 +96,7 @@ def insert_documents(self, documents: List[Document], **kwargs: Any):
             self.collection.add(
                 documents=[document.text],
                 metadatas=[document.metadata],
-                embeddings=[embedding] if embedding is not None else None,
+                embeddings=[embedding] if len(embedding) > 0 else None,
                 ids=[document.id]
             )
 

agentuniverse/agent/action/tool/tool.py

@@ -13,6 +13,7 @@
 from langchain.tools import Tool as LangchainTool
 
 from agentuniverse.agent.action.tool.enum import ToolTypeEnum
+from agentuniverse.base.annotation.trace import trace_tool
 from agentuniverse.base.component.component_base import ComponentBase
 from agentuniverse.base.component.component_enum import ComponentEnum
 from agentuniverse.base.config.application_configer.application_config_manager import ApplicationConfigManager
@@ -61,6 +62,7 @@ class Tool(ComponentBase):
     def __init__(self, **kwargs):
         super().__init__(component_type=ComponentEnum.TOOL, **kwargs)
 
+    @trace_tool
     def run(self, **kwargs):
         """The callable method that runs the tool."""
         self.input_check(kwargs)
@@ -73,6 +75,7 @@ def input_check(self, kwargs: dict) -> None:
             if key not in kwargs.keys():
                 raise Exception(f'{self.get_instance_code()} - The input must include key: {key}.')
 
+    @trace_tool
     def langchain_run(self, *args, callbacks=None, **kwargs):
         """The callable method that runs the tool."""
         kwargs["callbacks"] = callbacks

agentuniverse/agent/default/executing_agent/executing_agent.py

@@ -5,21 +5,23 @@
 # @Email   : lc299034@antgroup.com
 # @FileName: executing_agent.py
 """Executing Agent module."""
-import copy
 from concurrent.futures import ThreadPoolExecutor, wait, ALL_COMPLETED
 from typing import Optional, Any
 
 from agentuniverse.agent.action.tool.tool_manager import ToolManager
 from agentuniverse.agent.agent import Agent
+from agentuniverse.agent.agent_model import AgentModel
 from agentuniverse.agent.input_object import InputObject
 from agentuniverse.agent.plan.planner.planner import Planner
 from agentuniverse.agent.plan.planner.planner_manager import PlannerManager
+from agentuniverse.base.context.framework_context_manager import FrameworkContextManager
 
 
 class ExecutingAgent(Agent):
     """Executing Agent class."""
 
     executor: Optional[Any] = ThreadPoolExecutor(max_workers=10, thread_name_prefix="executing_agent")
+    _context_values: Optional[dict] = {}
 
     def input_keys(self) -> list[str]:
         """Return the input keys of the Agent."""
@@ -54,12 +56,16 @@ def parse_result(self, planner_result: dict) -> dict:
         llm_result = []
         executing_result = []
         futures = planner_result.get('futures')
+        index = 1
+        # assemble results of the execution process.
         for future in futures:
             task_result = future.result()
             llm_result.append(task_result)
             executing_result.append({
-                'input': task_result['input'], 'output': task_result['output']
+                'input': f"Question {index}: " + task_result.get('input', ''),
+                'output': f"Answer {index}: " + task_result.get('output', '')
             })
+            index += 1
 
         return {'executing_result': executing_result, 'llm_result': llm_result}
 
@@ -73,6 +79,7 @@ def execute(self, input_object: InputObject, agent_input: dict) -> dict:
         Returns:
             dict: Agent result object.
         """
+        self._context_values: dict = FrameworkContextManager().get_all_contexts()
         framework = agent_input.get('framework', [])
         futures = []
         for task in framework:
@@ -81,11 +88,37 @@ def execute(self, input_object: InputObject, agent_input: dict) -> dict:
             agent_input_copy['input'] = task
             planner: Planner = PlannerManager().get_instance_obj(self.agent_model.plan.get('planner').get('name'))
             futures.append(
-                self.executor.submit(planner.invoke, self.agent_model, agent_input_copy,
+                self.executor.submit(self.run_in_executor, planner, self.agent_model, agent_input_copy,
                                      self.process_intput_object(input_object, task, planner.input_key)))
         wait(futures, return_when=ALL_COMPLETED)
         return {'futures': futures}
 
+    def run_in_executor(self, planner: Planner, agent_model: AgentModel, planner_input: dict,
+                        input_object: InputObject) -> dict:
+        """The execution function of the thread pool.
+
+        Args:
+            planner(Planner): The planner object.
+            agent_model (AgentModel): The agent model object.
+            planner_input (dict): The planner input dict.
+            input_object (InputObject): The input parameters passed by the user.
+        Returns:
+            dict: The planner execution result.
+        """
+        context_tokens = {}
+        try:
+            # pass the framework context into the thread.
+            for var_name, var_value in self._context_values.items():
+                token = FrameworkContextManager().set_context(var_name, var_value)
+                context_tokens[var_name] = token
+            # invoke planner
+            res = planner.invoke(agent_model, planner_input, input_object)
+            return res
+        finally:
+            # clear the framework context.
+            for var_name, token in context_tokens.items():
+                FrameworkContextManager().reset_context(var_name, token)
+
     def process_intput_object(self, input_object: InputObject, subtask: str, planner_input_key: str) -> InputObject:
         """Process input object for the executing agent.
 

agentuniverse/agent/memory/message.py

@@ -24,7 +24,7 @@ class Message(BaseModel):
     """
 
     type: Optional[str] = None
-    content: Union[str, List[Union[str, Dict]]] = None
+    content: Optional[Union[str, List[Union[str, Dict]]]] = None
 
     def as_langchain(self):
         """Convert the agentUniverse(aU) message class to the langchain message class."""

agentuniverse/agent/plan/planner/peer_planner/peer_planner.py

@@ -6,6 +6,7 @@
 # @FileName: peer_planner.py
 """Peer planner module."""
 from agentuniverse.agent.action.tool.tool_manager import ToolManager
+from agentuniverse.agent.agent import Agent
 from agentuniverse.agent.agent_manager import AgentManager
 from agentuniverse.agent.agent_model import AgentModel
 from agentuniverse.agent.input_object import InputObject
@@ -42,7 +43,7 @@ def invoke(self, agent_model: AgentModel, planner_input: dict, input_object: Inp
         """
         planner_config = agent_model.plan.get('planner')
         sub_agents = self.generate_sub_agents(planner_config)
-        return self.agents_run(agent_model, sub_agents, planner_config, planner_input, input_object)
+        return self.agents_run(sub_agents, planner_config, planner_input, input_object)
 
     @staticmethod
     def generate_sub_agents(planner_config: dict) -> dict:
@@ -79,7 +80,7 @@ def build_expert_framework(planner_config: dict, input_object: InputObject):
             elif context:
                 input_object.add_data('expert_framework', context)
 
-    def agents_run(self, agent_mode: AgentModel, agents: dict, planner_config: dict, agent_input: dict,
+    def agents_run(self, agents: dict, planner_config: dict, agent_input: dict,
                    input_object: InputObject) -> dict:
         """Planner agents run.
 
@@ -105,10 +106,10 @@ def agents_run(self, agent_mode: AgentModel, agents: dict, planner_config: dict,
 
         self.build_expert_framework(planner_config, input_object)
 
-        planningAgent = agents.get('planning')
-        executingAgent = agents.get('executing')
-        expressingAgent = agents.get('expressing')
-        reviewingAgent = agents.get('reviewing')
+        planningAgent: Agent = agents.get('planning')
+        executingAgent: Agent = agents.get('executing')
+        expressingAgent: Agent = agents.get('expressing')
+        reviewingAgent: Agent = agents.get('reviewing')
 
         for _ in range(retry_count):
             LOGGER.info(f"Starting peer agents, retry_count is {_ + 1}.")
@@ -126,10 +127,13 @@ def agents_run(self, agent_mode: AgentModel, agents: dict, planner_config: dict,
                 for index, one_framework in enumerate(planning_result.get_data('framework')):
                     logger_info += f"[{index + 1}] {one_framework} \n"
                 LOGGER.info(logger_info)
-                self.stream_output(input_object, {"data": {
-                    'output': planning_result.to_dict(),
-                    "agent_info": agent_mode.info
-                }, "type": "planning"})
+
+                # add planning agent intermediate steps
+                if planningAgent:
+                    self.stream_output(input_object, {"data": {
+                        'output': planning_result.get_data('framework'),
+                        "agent_info": planningAgent.agent_model.info
+                    }, "type": "planning"})
 
             if not executing_result or jump_step in ["planning", "executing"]:
                 if not executingAgent:
@@ -148,10 +152,13 @@ def agents_run(self, agent_mode: AgentModel, agents: dict, planner_config: dict,
                         one_exec_log_info += f"[{index + 1}] output: {one_exec_res['output']}\n"
                         logger_info += one_exec_log_info
                 LOGGER.info(logger_info)
-                self.stream_output(input_object, {"data": {
-                    'output': executing_result.to_dict(),
-                    "agent_info": agent_mode.info
-                }, "type": "executing"})
+
+                # add executing agent intermediate steps
+                if executingAgent:
+                    self.stream_output(input_object, {"data": {
+                        'output': executing_result.get_data('executing_result'),
+                        "agent_info": executingAgent.agent_model.info
+                    }, "type": "executing"})
 
             if not expressing_result or jump_step in ["planning", "executing", "expressing"]:
                 if not expressingAgent:
@@ -166,10 +173,13 @@ def agents_run(self, agent_mode: AgentModel, agents: dict, planner_config: dict,
                 logger_info = f"\nExpressing agent execution result is :\n"
                 logger_info += f"{expressing_result.get_data('output')}"
                 LOGGER.info(logger_info)
-                self.stream_output(input_object, {"data": {
-                    'output': expressing_result.get_data('output'),
-                    "agent_info": agent_mode.info
-                }, "type": "expressing"})
+
+                # add expressing agent intermediate steps
+                if expressingAgent:
+                    self.stream_output(input_object, {"data": {
+                        'output': expressing_result.get_data('output'),
+                        "agent_info": expressingAgent.agent_model.info
+                    }, "type": "expressing"})
 
             if not reviewing_result or jump_step in ["planning", "executing", "expressing", "reviewing"]:
                 if not reviewingAgent:
@@ -193,7 +203,14 @@ def agents_run(self, agent_mode: AgentModel, agents: dict, planner_config: dict,
                     reviewing_info_str = f"review suggestion: {reviewing_result.get_data('suggestion')} \n"
                     reviewing_info_str += f"review score: {reviewing_result.get_data('score')} \n"
                     LOGGER.info(logger_info + reviewing_info_str)
-                    self.stream_output(input_object, {"data": reviewing_result.to_dict(), "type": "reviewing"})
+
+                    # add reviewing agent intermediate steps
+                    self.stream_output(input_object,
+                                       {"data": {
+                                           'output': reviewing_result.get_data('suggestion'),
+                                           "agent_info": reviewingAgent.agent_model.info
+                                       }, "type": "reviewing"})
+
                     if reviewing_result.get_data('score') and reviewing_result.get_data('score') >= eval_threshold:
                         loopResults.append({
                             "planning_result": planning_result,