diff --git a/README.md b/README.md
index 9e91efb1..17d06c34 100644
--- a/README.md
+++ b/README.md
@@ -69,7 +69,7 @@ pip install agentUniverse
### Run the first example
Run your first example, and you can quickly experience the performance of the agents (or agent groups) built by agentUniverse through the tutorial.
-Please refer to the document for detail steps: [Run the first example](./docs/guidebook/en/1_Run_the_first_example.md) 。
+Please refer to the document for detail steps: [Run the first example](docs/guidebook/en/Get_Start/Quick_Start.md) 。
****************************************
@@ -79,19 +79,19 @@ Please refer to the document for detail steps: [Run the first example](./docs/gu
setup the standard project: [agentUniverse Standard Project](sample_standard_app)
### Create and use agents
-You can learn about the important components of agents through the [Introduction to Agents](./docs/guidebook/en/2_2_1_Agent.md). For detailed information on creating agents, refer to [Creating and Using Agents](./docs/guidebook/en/2_2_1_Agent_Create_And_Use.md). You can also deepen your understanding of the creation and usage of agents by exploring official examples, such as the [Python Code Generation and Execution Agent](./docs/guidebook/en/7_1_1_Python_Auto_Runner.md).
+You can learn about the important components of agents through the [Introduction to Agents](docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent.md). For detailed information on creating agents, refer to [Creating and Using Agents](docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent_Create_And_Use.md). You can also deepen your understanding of the creation and usage of agents by exploring official examples, such as the [Python Code Generation and Execution Agent](docs/guidebook/en/Examples/Python_Auto_Runner.md).
### Setting and use knowledgeBase
-In the construction of intelligent agent applications, knowledge base construction and recall are indispensable. The agentUniverse framework, based on RAG technology, provides an efficient standard operating procedure for knowledge base construction and the retrieval and recall process of RAG. You can learn about its usage through the [Knowledge Introduction](./docs/guidebook/en/2_2_4_Knowledge.md) and [Knowledge Definition and Usage](./docs/guidebook/en/2_2_4_Knowledge_Define_And_Use.md), and further master how to quickly build a knowledge base and create a recall-capable agent through [How to Build RAG Agents](./docs/guidebook/en/2_2_4_How_To_Build_A_RAG_Agent.md).
+In the construction of intelligent agent applications, knowledge base construction and recall are indispensable. The agentUniverse framework, based on RAG technology, provides an efficient standard operating procedure for knowledge base construction and the retrieval and recall process of RAG. You can learn about its usage through the [Knowledge Introduction](docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge.md) and [Knowledge Definition and Usage](docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge_Define_And_Use.md), and further master how to quickly build a knowledge base and create a recall-capable agent through [How to Build RAG Agents](docs/guidebook/en/How-to/How_To_Build_A_RAG_Agent.md).
### Create and use Tools
-In the construction of agent applications, agents need to connect to a variety of tools. You should specify a range of tools that they can use. You can integrate various proprietary APIs and services as tool plugins through [Tool Creation and Usage](./docs/guidebook/en/2_2_3_Tool_Create_And_Use.md). The framework has already integrated LangChain and some third-party toolkits. For detailed usage, you can refer to [Integrating LangChain Tools](./docs/guidebook/en/2_2_3_Integrated_LangChain_Tools.md) and [Existing Integrated Tools](./docs/guidebook/en/2_2_3_Integrated_Tools.md).
+In the construction of agent applications, agents need to connect to a variety of tools. You should specify a range of tools that they can use. You can integrate various proprietary APIs and services as tool plugins through [Tool Creation and Usage](docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool_Create_And_Use.md). The framework has already integrated LangChain and some third-party toolkits. For detailed usage, you can refer to [Integrating LangChain Tools](docs/guidebook/en/In-Depth_Guides/Components/Tools/Integrated_LangChain_Tools.md) and [Existing Integrated Tools](docs/guidebook/en/In-Depth_Guides/Components/Tools/Integrated_Tools.md).
### Effectiveness evaluation
-The effectiveness evaluation of agents can be conducted through expert assessments on one hand and by leveraging the evaluation capabilities of the agents on the other. agentUniverse has launched DataAgent (Minimum Viable Product version), which aims to empower your agents with self-evaluation and evolution capabilities using agent intelligence. You can also customize the evaluation criteria within it. For more details, see the documentation: [DataAgent - Autonomous Data Agents](./docs/guidebook/en/8_1_1_data_autonomous_agent.md).
+The effectiveness evaluation of agents can be conducted through expert assessments on one hand and by leveraging the evaluation capabilities of the agents on the other. agentUniverse has launched DataAgent (Minimum Viable Product version), which aims to empower your agents with self-evaluation and evolution capabilities using agent intelligence. You can also customize the evaluation criteria within it. For more details, see the documentation: [DataAgent - Autonomous Data Agents](docs/guidebook/en/In-Depth_Guides/Tutorials/Data_Autonomous_Agent.md).
### agentServe
-agentUniverse offers multiple standard web server capabilities, as well as standard HTTP and RPC protocols. You can further explore the documentation on [Service Registration and Usage](./docs/guidebook/en/2_4_1_Service_Registration_and_Usage.md) and the [Web Server](./docs/guidebook/en/2_4_1_Web_Server.md) sections.
+agentUniverse offers multiple standard web server capabilities, as well as standard HTTP and RPC protocols. You can further explore the documentation on [Service Registration and Usage](docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Service_Registration_and_Usage.md) and the [Web Server](docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Web_Server.md) sections.
****************************************
@@ -108,7 +108,7 @@ pip install magent-ui ruamel.yaml
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) and the [Advanced Guide](./docs/guidebook/en/10_1_2_Product_Platform_Advancement_Guide.md).
+For more details, refer to [Quick Start for Product Platform](docs/guidebook/en/How-to/Product_Platform_Quick_Start.md) and the [Advanced Guide](docs/guidebook/en/How-to/Product_Platform_Advancement_Guide.md).
This feature is jointly launched by [difizen](https://github.com/difizen/magent) and agentUniverse.
@@ -137,21 +137,21 @@ Rich and Effective Multi-Agent Collaboration Models: It offers collaborative mod
Easy Integration of Domain Expertise: It offers capabilities for domain prompts, knowledge construction, and management, supporting the orchestration and injection of domain-level SOPs, aligning agents with expert-level domain knowledge.
-💡 For more features, see the [key features of agentUniverse](./docs/guidebook/en/1_Core_Features.md) section.
+💡 For more features, see the [key features of agentUniverse](docs/guidebook/en/Concepts/Core_Features.md) section.
****************************************
## Sample Projects
-🚩 [Legal Consultation Agent v2](./docs/guidebook/en/7_1_1_Legal_Consultation_Case.md)
+🚩 [Legal Consultation Agent v2](docs/guidebook/en/Examples/Legal_Advice.md)
-🚩 [Python Code Generation and Execution Agent](./docs/guidebook/en/7_1_1_Python_Auto_Runner.md)
+🚩 [Python Code Generation and Execution Agent](docs/guidebook/en/Examples/Python_Auto_Runner.md)
-🚩 [Discussion Group Based on Multi-Turn Multi-Agent Mode](./docs/guidebook/en/6_2_1_Discussion_Group.md)
+🚩 [Discussion Group Based on Multi-Turn Multi-Agent Mode](docs/guidebook/en/Examples/Discussion_Group.md)
-🚩 [Financial Event Analysis Based on PEER Multi-Agent Mode](./docs/guidebook/en/6_4_1_Financial_Event_Analysis_Case.md)
+🚩 [Financial Event Analysis Based on PEER Multi-Agent Mode](docs/guidebook/en/Examples/Financial_Event_Analysis.md)
-🚩 [Andrew Ng's Reflexive Workflow Translation Agent Replication](./docs/guidebook/en/7_1_1_Translation_Case.md)
+🚩 [Andrew Ng's Reflexive Workflow Translation Agent Replication](docs/guidebook/en/Examples/Translation_Assistant.md)
****************************************
@@ -170,7 +170,7 @@ https://private-user-images.githubusercontent.com/39180831/355437700-192f712d-1b
## Documents
### User Guide
-💡 For more detailed information, please read the [User Guide](./docs/guidebook/en/0_index.md).
+💡 For more detailed information, please read the [User Guide](./docs/guidebook/en/Contents.md).
### API Reference
💡 Please read the [API Reference](https://agentuniverse.readthedocs.io/en/latest/).
diff --git a/docs/guidebook/en/0_index.md b/docs/guidebook/en/0_index.md
deleted file mode 100644
index 10ab3e04..00000000
--- a/docs/guidebook/en/0_index.md
+++ /dev/null
@@ -1,110 +0,0 @@
-# User Guide
-************************************************
-## Table of Contents
-
-**1. Getting Started**
-* 1.1 [Introduction](1_1_Introduction.md)
-* 1.2 [Installation](1_2_Installation.md)
-* 1.3 [Quick Start](1_3_Quick_Start.md)
-* 1.5 [ApplicationStructure](1_4_Application_Engineering_Structure_Explanation.md)
-
-**2. Principle Introduction**
-
-* 2.1 Framework Principles
-* 2.2 [Domain Components](2_2_Domain_Component_Principles.md)
- * 2.2.1 [Agent](2_2_1_Agent.md)
- * 2.2.1.1 [Create And Use](2_2_1_Agent_Create_And_Use.md)
- * 2.2.1.2 [Related Domain Objects](2_2_1_Agent_Related_Domain_Objects.md)
- * 2.2.2 [LLM](2_2_2_LLM.md)
- * 2.2.2.1 [Define And Use](2_2_2_LLM_component_define_and_usage.md)
- * 2.2.2.2 [Related Domain Objects](2_2_2_LLM_Related_Domain_Objects.md)
- * 2.2.3 [Tool](2_2_3_Tool.md)
- * 2.2.3.1 [Create And Use](2_2_3_Tool_Create_And_Use.md)
- * 2.2.3.2 [Related Domain Objects](2_2_3_Tool_Related_Domain_Objects.md)
- * 2.2.4 [Knowledge](2_2_4_Knowledge.md)
- * 2.2.4.1 [Define And Use](2_2_4_Knowledge_Define_And_Use.md)
- * 2.2.4.2 [Related Domain Objects](2_2_4_Knowledge_Related_Domain_Objects.md)
- * 2.2.5 [Memory](2_2_5_Memory.md)
- * 2.2.5.1 [Define And Use](2_2_5_Memory_Define_And_Use.md)
- * 2.2.5.2 [Related Domain Objects](2_2_5_Memory_Related_Domain_Objects.md)
- * 2.2.6 [Planner](2_2_6_Planner.md)
- * 2.2.5.1 [Define And Use](2_2_6_Planner_Define_And_Use.md)
- * 2.2.5.2 [Related Domain Objects](2_2_6_Planner_Related_Domain_Objects.md)
-* 2.3 Technical Components
- * 2.3.1 [RAG](2_2_4_RAG.md)
- * 2.3.1.1 [How To Build A RAG Agent](2_2_4_How_To_Build_A_RAG_Agent.md)
-* 2.4 Others
- * 2.4.1 Service
- * 2.4.1.1 [Registration and Usage](2_4_1_Service_Registration_and_Usage.md)
- * 2.4.1.2 [Web Server](2_4_1_Web_Server.md)
- * 2.4.1.3 [Web API](2_4_1_Web_Api.md)
- * 2.4.1.4 [Service Information Storage](./2_4_1_Service_Information_Storage.md)
- * 2.4.2 Prompt Management
- * 2.4.3 Multi-turn Dialogue
- * 2.4.4 Logging
- * 2.4.4.1 [Logging Component](2_6_Logging_Utils.md)
- * 2.4.5 Data Collection
- * 2.4.5.1 [Monitor Module](2_5_1_Monitor_Module.md)
- * 2.4.6 Data Autonomous
- * 2.4.6.1 [Data Autonomous Agent](8_1_1_data_autonomous_agent.md)
-
-**3. Component Reference Manual**
-* 3.1 Domain Components
- * 3.1.1 List of Agents
- * 3.1.2 [List of LLMs](3_1_2_0_List_Of_LLMs.md)
- * 3.1.2.1 [OpenAI Usage Instructions](3_1_2_OpenAI_LLM_Use.md)
- * 3.1.2.2 [Qwen Usage Instructions](3_1_2_Qwen_LLM_Use.md)
- * 3.1.2.3 [WenXin Usage Instructions](3_1_2_WenXin_LLM_Use.md)
- * 3.1.2.4 [Kimi Usage Instructions](3_1_2_Kimi_LLM_Use.md)
- * 3.1.2.5 [BaiChuan Usage Instructions](3_1_2_BaiChuan_LLM_Use.md)
- * 3.1.2.6 [Claude Usage Instructions](3_1_2_Claude_LLM_Use.md)
- * 3.1.2.7 [Ollama Usage Instructions](3_1_2_Ollama_LLM_Use.md)
- * 3.1.2.8 [DeepSeek Usage Instructions](3_1_2_DeepSeek_LLM_Use.md)
- * 3.1.2.9 [GLM Usage Instructions](3_1_2_GLM_LLM_Use.md)
- * 3.1.2.10 [General OpenAI Protocol Style Wrapper](3_1_2_OpenAIStyleLLM_Use.md)
- * 3.1.3 List of Tools
- * 3.1.3.1 [Integration Tool Details](2_2_3_Integrated_Tools.md)
- * 3.1.3.2 [LangChain Tool Wrapper](2_2_3_Integrated_LangChain_Tools.md)
- * 3.1.4 List of Knowledge
- * 3.1.5 List of Memories
- * 3.1.6 List of Planners
-* 3.2 Technical Components
- * 3.2.1 RPC
- * 3.2.1.1 [gRPC](3_2_1_gRPC.md)
- * 3.2.2 Store
- * 3.2.2.1 [SQLDBWrapper](2_3_1_SQLDB_WRAPPER.md)
- * 3.2.2.2 [Milvus](3_3_1_Milvus.md)
- * 3.2.2.3 [ChromaDB](3_3_2_ChromaDB.md)
- * 3.2.2.4 [Sqlite](3_3_3_Sqlite.md)
- * 3.2.3 Msg
- * 3.2.4 Logging
- * 3.2.4.1 [Alibaba Cloud SLS](3_2_4_Alibaba_Cloud_SLS.md)
-
-**[4. API Reference Manual](4_1_API_Reference.md)**
-
-**5. Best Practices**
-* 5.1 Operations and Deployment
- * 5.1.1 [Docker Containerization Solution](5_1_1_Docker_Container_Deployment.md)
- * 5.1.2 [K8S Solution](5_1_2_K8S_Deployment.md)
-
-**6. Use Cases**
-* 6.1 RAG-Type Agent Examples
- * 6.1.1 [Legal Consultation Agent v2](7_1_1_Legal_Consultation_Case.md)
-* 6.2 ReAct-Type Agent Examples
- * 6.2.1 [Python Code Generation and Execution Agent](7_1_1_Python_Auto_Runner.md)
-* 6.3 [Discussion Group Based on Multi-Turn Multi-Agent Mode](6_2_1_Discussion_Group.md)
-* 6.4 PEER Multi-Agent Cooperation Examples
- * 6.4.1 [Financial Event Analysis Case](./6_4_1_Financial_Event_Analysis_Case.md)
-* 6.5 [Andrew Ng's Reflexive Workflow Translation Agent Replication](./7_1_1_Translation_Case.md)
-
-**7.Product Platform**
-* 7.1 [Quick Use](./10_1_1_Product Platform Quick Start.md)
-* 7.2 [Advancement Guide](./10_1_2_Product_Platform_Advancement_Guide.md)
-
-**8. Series of Articles**
-
-**9. Frequently Asked Questions (FAQ)**
-
-**[10.Citation](9_1_Citation.md)**
-
-**[11. Contact Us](6_1_Contact_Us.md)**
diff --git a/docs/guidebook/en/9_1_Citation.md b/docs/guidebook/en/Concepts/Citation_PEER.md
similarity index 100%
rename from docs/guidebook/en/9_1_Citation.md
rename to docs/guidebook/en/Concepts/Citation_PEER.md
diff --git a/docs/guidebook/en/1_Core_Features.md b/docs/guidebook/en/Concepts/Core_Features.md
similarity index 100%
rename from docs/guidebook/en/1_Core_Features.md
rename to docs/guidebook/en/Concepts/Core_Features.md
diff --git a/docs/guidebook/en/1_Why_Use_agentUniverse.md b/docs/guidebook/en/Concepts/Why_Use_agentUniverse.md
similarity index 100%
rename from docs/guidebook/en/1_Why_Use_agentUniverse.md
rename to docs/guidebook/en/Concepts/Why_Use_agentUniverse.md
diff --git a/docs/guidebook/en/6_1_Contact_Us.md b/docs/guidebook/en/Contact_Us.md
similarity index 100%
rename from docs/guidebook/en/6_1_Contact_Us.md
rename to docs/guidebook/en/Contact_Us.md
diff --git a/docs/guidebook/en/Contents.md b/docs/guidebook/en/Contents.md
new file mode 100644
index 00000000..c1ae2411
--- /dev/null
+++ b/docs/guidebook/en/Contents.md
@@ -0,0 +1,110 @@
+# User Guide
+************************************************
+## Table of Contents
+
+**1. Getting Started**
+* 1.1 [Introduction](Get_Start/Introduction.md)
+* 1.2 [Installation](Get_Start/Installation.md)
+* 1.3 [Quick Start](Get_Start/Quick_Start.md)
+* 1.5 [ApplicationStructure](Get_Start/Application_Project_Structure_and_Explanation.md)
+
+**2. Principle Introduction**
+
+* 2.1 Framework Principles
+* 2.2 [Domain Components](In-Depth_Guides/Tutorials/Domain_Component_Principles.md)
+ * 2.2.1 [Agent](In-Depth_Guides/Tutorials/Agent/Agent.md)
+ * 2.2.1.1 [Create And Use](In-Depth_Guides/Tutorials/Agent/Agent_Create_And_Use.md)
+ * 2.2.1.2 [Related Domain Objects](In-Depth_Guides/Tutorials/Agent/Agent_Related_Domain_Objects.md)
+ * 2.2.2 [LLM](In-Depth_Guides/Tutorials/LLM/LLM.md)
+ * 2.2.2.1 [Define And Use](In-Depth_Guides/Tutorials/LLM/LLM_component_define_and_usage.md)
+ * 2.2.2.2 [Related Domain Objects](In-Depth_Guides/Tutorials/LLM/LLM_Related_Domain_Objects.md)
+ * 2.2.3 [Tool](In-Depth_Guides/Tutorials/Tool/Tool.md)
+ * 2.2.3.1 [Create And Use](In-Depth_Guides/Tutorials/Tool/Tool_Create_And_Use.md)
+ * 2.2.3.2 [Related Domain Objects](In-Depth_Guides/Tutorials/Tool/Tool_Related_Domain_Objects.md)
+ * 2.2.4 [Knowledge](In-Depth_Guides/Tutorials/Knowledge/Knowledge.md)
+ * 2.2.4.1 [Define And Use](In-Depth_Guides/Tutorials/Knowledge/Knowledge_Define_And_Use.md)
+ * 2.2.4.2 [Related Domain Objects](In-Depth_Guides/Tutorials/Knowledge/Knowledge_Related_Domain_Objects.md)
+ * 2.2.5 [Memory](In-Depth_Guides/Tutorials/Memory/Memory.md)
+ * 2.2.5.1 [Define And Use](In-Depth_Guides/Tutorials/Memory/Memory_Define_And_Use.md)
+ * 2.2.5.2 [Related Domain Objects](In-Depth_Guides/Tutorials/Memory/Memory_Related_Domain_Objects.md)
+ * 2.2.6 [Planner](In-Depth_Guides/Tutorials/Plan/Planner.md)
+ * 2.2.5.1 [Define And Use](In-Depth_Guides/Tutorials/Plan/Planner_Define_And_Use.md)
+ * 2.2.5.2 [Related Domain Objects](In-Depth_Guides/Tutorials/Plan/Planner_Related_Domain_Objects.md)
+* 2.3 Technical Components
+ * 2.3.1 [RAG](In-Depth_Guides/Tutorials/RAG.md)
+ * 2.3.1.1 [How To Build A RAG Agent](How-to/How_To_Build_A_RAG_Agent.md)
+* 2.4 Others
+ * 2.4.1 Service
+ * 2.4.1.1 [Registration and Usage](In-Depth_Guides/Tech_Capabilities/Service/Service_Registration_and_Usage.md)
+ * 2.4.1.2 [Web Server](In-Depth_Guides/Tech_Capabilities/Service/Web_Server.md)
+ * 2.4.1.3 [Web API](In-Depth_Guides/Tech_Capabilities/Service/Web_Api.md)
+ * 2.4.1.4 [Service Information Storage](In-Depth_Guides/Tech_Capabilities/Service/Service_Information_Storage.md)
+ * 2.4.2 Prompt Management
+ * 2.4.3 Multi-turn Dialogue
+ * 2.4.4 Logging
+ * 2.4.4.1 [Logging Component](In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Logging_Utils.md)
+ * 2.4.5 Data Collection
+ * 2.4.5.1 [Monitor Module](In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Monitor_Module.md)
+ * 2.4.6 Data Autonomous
+ * 2.4.6.1 [Data Autonomous Agent](In-Depth_Guides/Tutorials/Data_Autonomous_Agent.md)
+
+**3. Component Reference Manual**
+* 3.1 Domain Components
+ * 3.1.1 List of Agents
+ * 3.1.2 [List of LLMs](In-Depth_Guides/Components/LLMs/0.List_Of_LLMs.md)
+ * 3.1.2.1 [OpenAI Usage Instructions](In-Depth_Guides/Components/LLMs/OpenAI_LLM_Use.md)
+ * 3.1.2.2 [Qwen Usage Instructions](In-Depth_Guides/Components/LLMs/Qwen_LLM_Use.md)
+ * 3.1.2.3 [WenXin Usage Instructions](In-Depth_Guides/Components/LLMs/WenXin_LLM_Use.md)
+ * 3.1.2.4 [Kimi Usage Instructions](In-Depth_Guides/Components/LLMs/Kimi_LLM_Use.md)
+ * 3.1.2.5 [BaiChuan Usage Instructions](In-Depth_Guides/Components/LLMs/BaiChuan_LLM_Use.md)
+ * 3.1.2.6 [Claude Usage Instructions](In-Depth_Guides/Components/LLMs/Claude_LLM_Use.md)
+ * 3.1.2.7 [Ollama Usage Instructions](In-Depth_Guides/Components/LLMs/Ollama_LLM_Use.md)
+ * 3.1.2.8 [DeepSeek Usage Instructions](In-Depth_Guides/Components/LLMs/DeepSeek_LLM_Use.md)
+ * 3.1.2.9 [GLM Usage Instructions](In-Depth_Guides/Components/LLMs/GLM_LLM_Use.md)
+ * 3.1.2.10 [General OpenAI Protocol Style Wrapper](In-Depth_Guides/Components/LLMs/OpenAIStyleLLM_Use.md)
+ * 3.1.3 List of Tools
+ * 3.1.3.1 [Integration Tool Details](In-Depth_Guides/Components/Tools/Integrated_Tools.md)
+ * 3.1.3.2 [LangChain Tool Wrapper](In-Depth_Guides/Components/Tools/Integrated_LangChain_Tools.md)
+ * 3.1.4 List of Knowledge
+ * 3.1.5 List of Memories
+ * 3.1.6 List of Planners
+* 3.2 Technical Components
+ * 3.2.1 RPC
+ * 3.2.1.1 [gRPC](In-Depth_Guides/Tech_Capabilities/Service/gRPC.md)
+ * 3.2.2 Store
+ * 3.2.2.1 [SQLDBWrapper](In-Depth_Guides/Tech_Capabilities/Storage/SQLDB_WRAPPER.md)
+ * 3.2.2.2 [Milvus](In-Depth_Guides/Tech_Capabilities/Storage/Milvus.md)
+ * 3.2.2.3 [ChromaDB](In-Depth_Guides/Tech_Capabilities/Storage/ChromaDB.md)
+ * 3.2.2.4 [Sqlite](In-Depth_Guides/Tech_Capabilities/Storage/Sqlite.md)
+ * 3.2.3 Msg
+ * 3.2.4 Logging
+ * 3.2.4.1 [Alibaba Cloud SLS](In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Alibaba_Cloud_SLS.md)
+
+**[4. API Reference Manual](In-Depth_Guides/Tech_Capabilities/Others/API_Reference.md)**
+
+**5. Best Practices**
+* 5.1 Operations and Deployment
+ * 5.1.1 [Docker Containerization Solution](In-Depth_Guides/Tech_Capabilities/Deployment/Docker_Container_Deployment.md)
+ * 5.1.2 [K8S Solution](In-Depth_Guides/Tech_Capabilities/Deployment/K8S_Deployment.md)
+
+**6. Use Cases**
+* 6.1 RAG-Type Agent Examples
+ * 6.1.1 [Legal Consultation Agent v2](Examples/Legal_Advice.md)
+* 6.2 ReAct-Type Agent Examples
+ * 6.2.1 [Python Code Generation and Execution Agent](Examples/Python_Auto_Runner.md)
+* 6.3 [Discussion Group Based on Multi-Turn Multi-Agent Mode](Examples/Discussion_Group.md)
+* 6.4 PEER Multi-Agent Cooperation Examples
+ * 6.4.1 [Financial Event Analysis Case](Examples/Financial_Event_Analysis.md)
+* 6.5 [Andrew Ng's Reflexive Workflow Translation Agent Replication](Examples/Translation_Assistant.md)
+
+**7.Product Platform**
+* 7.1 [Quick Use](How-to/Product_Platform_Quick_Start.md)
+* 7.2 [Advancement Guide](How-to/Product_Platform_Advancement_Guide.md)
+
+**8. Series of Articles**
+
+**9. Frequently Asked Questions (FAQ)**
+
+**[10.Citation](Concepts/Citation_PEER.md)**
+
+**[11. Contact Us](Contact_Us.md)**
diff --git a/docs/guidebook/en/6_2_1_Discussion_Group.md b/docs/guidebook/en/Examples/Discussion_Group.md
similarity index 99%
rename from docs/guidebook/en/6_2_1_Discussion_Group.md
rename to docs/guidebook/en/Examples/Discussion_Group.md
index bf8ee3c7..44f327c5 100644
--- a/docs/guidebook/en/6_2_1_Discussion_Group.md
+++ b/docs/guidebook/en/Examples/Discussion_Group.md
@@ -69,7 +69,7 @@ if __name__ == '__main__':
### Result Demonstration
Which tastes better, Coca-Cola or Pepsi：
-
+
## More Details
### Agent Configuration
diff --git a/docs/guidebook/en/6_4_1_Financial_Event_Analysis_Case.md b/docs/guidebook/en/Examples/Financial_Event_Analysis.md
similarity index 62%
rename from docs/guidebook/en/6_4_1_Financial_Event_Analysis_Case.md
rename to docs/guidebook/en/Examples/Financial_Event_Analysis.md
index a3dc6d1d..a2299750 100644
--- a/docs/guidebook/en/6_4_1_Financial_Event_Analysis_Case.md
+++ b/docs/guidebook/en/Examples/Financial_Event_Analysis.md
@@ -1,4 +1,4 @@
-# Financial Event Analysis Case
+# Financial Event Analysis
## Case Description
This case is based on PeerPlanner and showcases a multi-agent collaborative example for analyzing financial events. Regarding the topic of "Buffett's 2023 Reduction in BYD Shares"， it demonstrates how to use the PEER multi-agent collaboration model in agentUniverse and details the configuration and output examples for each agent in PEER.
@@ -7,41 +7,41 @@ This case study utilizes the GPT-4o model by OPENAI. Before using it, you need t
## Agents
### Planning Agent
Reference the original code files:
-- [Configuration file](../../../sample_standard_app/app/core/agent/peer_agent_case/demo_planning_agent.yaml)
-- [Prompt file](../../../sample_standard_app/app/core/prompt/planning_agent_cn.yaml)
+- [Configuration file](../../../../sample_standard_app/app/core/agent/peer_agent_case/demo_planning_agent.yaml)
+- [Prompt file](../../../../sample_standard_app/app/core/prompt/planning_agent_cn.yaml)
The Planning Agent is responsible for breaking down the original financial problem into multiple sub-problems that can be individually solved and provided to the subsequent Executing Agent. In this case, the original question "Analyze the reasons for Buffett's reduction in BYD shares" can be decomposed into several sub-questions as shown in the diagram below:
-
-You can debug the Planning Agent individually in the [test file](../../../sample_standard_app/app/test/test_planning_agent.py).
+
+You can debug the Planning Agent individually in the [test file](../../../../sample_standard_app/app/test/test_planning_agent.py).
### Executing Agent
Reference the original code files:
-- [Configuration file](../../../sample_standard_app/app/core/agent/peer_agent_case/demo_executing_agent.yaml)
-- [Prompt file](../../../sample_standard_app/app/core/prompt/executing_agent_cn.yaml)
+- [Configuration file](../../../../sample_standard_app/app/core/agent/peer_agent_case/demo_executing_agent.yaml)
+- [Prompt file](../../../../sample_standard_app/app/core/prompt/executing_agent_cn.yaml)
-In this Agent, we provide a tool [google_search_tool](../../../sample_standard_app/app/core/tool/google_search_tool.py) for searching information on Google. To use this tool, you should configure `SERPER_API_KEY` in your environment. For convenience, if `SERPER_API_KEY ` is not configured, this tool will return a pre-set query result related to this case, which you can find in the [mock_search_tool](../../../sample_standard_app/app/core/tool/mock_search_tool.py).
+In this Agent, we provide a tool [google_search_tool](../../../../sample_standard_app/app/core/tool/google_search_tool.py) for searching information on Google. To use this tool, you should configure `SERPER_API_KEY` in your environment. For convenience, if `SERPER_API_KEY ` is not configured, this tool will return a pre-set query result related to this case, which you can find in the [mock_search_tool](../../../../sample_standard_app/app/core/tool/mock_search_tool.py).
The Executing Agent is responsible for solving the sub-problems broken down by the Planning Agent. In this case, the execution results of the Executing Agent are as follows:
-
-The result is lengthy, so only the execution results of the first two questions are shown here. You can debug the Executing Agent individually in the [test file](../../../sample_standard_app/app/test/test_executing_agent.py) to obtain the complete results.
+
+The result is lengthy, so only the execution results of the first two questions are shown here. You can debug the Executing Agent individually in the [test file](../../../../sample_standard_app/app/test/test_executing_agent.py) to obtain the complete results.
### Expressing Agent
Reference the original code files:
-- [Configuration file](../../../sample_standard_app/app/core/agent/peer_agent_case/demo_expressing_agent.yaml)
-- [Prompt file](../../../sample_standard_app/app/core/prompt/expressing_agent_cn.yaml)
+- [Configuration file](../../../../sample_standard_app/app/core/agent/peer_agent_case/demo_expressing_agent.yaml)
+- [Prompt file](../../../../sample_standard_app/app/core/prompt/expressing_agent_cn.yaml)
The Expressing Agent is responsible for summarizing all the results output by the Executing Agent and formulating them into an answer to the original question according to the requirements in the prompt file. In this case, the output result of the Expressing Agent is as follows:
-
-You can debug the Expressing Agent individually in the [test file](../../../sample_standard_app/app/test/test_expressing_agent.py).
+
+You can debug the Expressing Agent individually in the [test file](../../../../sample_standard_app/app/test/test_expressing_agent.py).
### Reviewing Agent
Reference the original code files:
-- [Configuration file](../../../sample_standard_app/app/core/agent/peer_agent_case/demo_reviewing_agent.yaml)
+- [Configuration file](../../../../sample_standard_app/app/core/agent/peer_agent_case/demo_reviewing_agent.yaml)
The Reviewing Agent is responsible for evaluating whether the result produced by the Expressing Agent is an effective answer to the original question. In this case, the Reviewing Agent accepted the answer from the Expressing Agent:
-
-You can debug the Reviewing Agent individually in the [test file](../../../sample_standard_app/app/test/test_reviewing_agent.py).
+
+You can debug the Reviewing Agent individually in the [test file](../../../../sample_standard_app/app/test/test_reviewing_agent.py).
### PEER Agent
```yaml
@@ -71,5 +71,5 @@ Users can configure the four Agents mentioned above into a complete PEER Agent t
- expressing：The Agent responsible for the Express part.
- reviewing：The Agent responsible for the Review part.
-You can run the complete case in the [example file](../../../sample_standard_app/app/examples/peer_chat_bot.py).
+You can run the complete case in the [example file](../../../../sample_standard_app/app/examples/peer_chat_bot.py).
diff --git a/docs/guidebook/en/7_1_1_Legal_Consultation_Case.md b/docs/guidebook/en/Examples/Legal_Advice.md
similarity index 50%
rename from docs/guidebook/en/7_1_1_Legal_Consultation_Case.md
rename to docs/guidebook/en/Examples/Legal_Advice.md
index 7cca9dd8..cfb271a6 100644
--- a/docs/guidebook/en/7_1_1_Legal_Consultation_Case.md
+++ b/docs/guidebook/en/Examples/Legal_Advice.md
@@ -1,4 +1,4 @@
-# Legal Consultation Case
+# Legal Advice
## Case Description
This case demonstrates a simple legal consultation agent built using `RagPlanner`. The agent provides legal advice by retrieving relevant provisions from the Civil Law and the Criminal Law, and combining them with the case background.
@@ -6,12 +6,12 @@ The case leverages the DashScope embedding and rerank features with the Qwen llm
## Components
### Legal Knowledge Base
-The legal knowledge base is constructed using [Knowledge Components](2_2_4_Knowledge_Related_Domain_Objects.md) from agentUniverse. By storing the original legal provisions in the ChromaDB and Sqlite database, the knowledge base facilitates efficient retrieval and consultation for the agent.
+The legal knowledge base is constructed using [Knowledge Components](../In-Depth_Guides/Tutorials/Knowledge/Knowledge_Related_Domain_Objects.md) from agentUniverse. By storing the original legal provisions in the ChromaDB and Sqlite database, the knowledge base facilitates efficient retrieval and consultation for the agent.
Original legal documents:
-- [民法典.pdf](../../../sample_standard_app/app/resources/民法典.pdf)
-- [刑法.pdf](../../../sample_standard_app/app/resources/刑法.pdf)
+- [民法典.pdf](../../../../sample_standard_app/app/resources/民法典.pdf)
+- [刑法.pdf](../../../../sample_standard_app/app/resources/刑法.pdf)
-### [Knowledge Definition](../../../sample_standard_app/app/core/knowledge/law_knowledge.yaml)
+### [Knowledge Definition](../../../../sample_standard_app/app/core/knowledge/law_knowledge.yaml)
```yaml
name: "law_knowledge"
description: "中国民法与刑法相关的知识库"
@@ -37,25 +37,25 @@ metadata:
```
### Reader Component
-- [default_pdf_reader](../../../agentuniverse/agent/action/knowledge/reader/file/pdf_reader.yaml)
+- [default_pdf_reader](../../../../agentuniverse/agent/action/knowledge/reader/file/pdf_reader.yaml)
### DocProcessor Component
-- [custom_query_keyword_extractor](../../../sample_standard_app/app/core/doc_processor/query_keyword_extractor.yaml)
-- [recursive_character_text_splitter](../../../agentuniverse/agent/action/knowledge/doc_processor/recursive_character_text_splitter.yaml)
+- [custom_query_keyword_extractor](../../../../sample_standard_app/app/core/doc_processor/query_keyword_extractor.yaml)
+- [recursive_character_text_splitter](../../../../agentuniverse/agent/action/knowledge/doc_processor/recursive_character_text_splitter.yaml)
### QueryParaphraser Component
-- [custom_query_keyword_extractor](../../../sample_standard_app/app/core/query_paraphraser/custom_query_keyword_extractor.yaml)
+- [custom_query_keyword_extractor](../../../../sample_standard_app/app/core/query_paraphraser/custom_query_keyword_extractor.yaml)
### RagRouter Component
-- [nlu_rag_router](../../../sample_standard_app/app/core/rag_router/nlu_rag_router.yaml)
+- [nlu_rag_router](../../../../sample_standard_app/app/core/rag_router/nlu_rag_router.yaml)
### Store Component
-- [civil_law_chroma_store](../../../sample_standard_app/app/core/store/civil_law_chroma_store.yaml)
-- [criminal_law_chroma_store](../../../sample_standard_app/app/core/store/criminal_law_chroma_store.yaml)
-- [civil_law_sqlite_store](../../../sample_standard_app/app/core/store/civil_law_sqlite_store.yaml)
-- [criminal_law_sqlite_store](../../../sample_standard_app/app/core/store/criminal_law_sqlite_store.yaml)
+- [civil_law_chroma_store](../../../../sample_standard_app/app/core/store/civil_law_chroma_store.yaml)
+- [criminal_law_chroma_store](../../../../sample_standard_app/app/core/store/criminal_law_chroma_store.yaml)
+- [civil_law_sqlite_store](../../../../sample_standard_app/app/core/store/civil_law_sqlite_store.yaml)
+- [criminal_law_sqlite_store](../../../../sample_standard_app/app/core/store/criminal_law_sqlite_store.yaml)
-For your convenience, we have placed the databases containing the relevant information in [this directory](../../../sample_standard_app/DB/). If you want to build the knowledge base from scratch, you can run the following code:
+For your convenience, we have placed the databases containing the relevant information in [this directory](../../../../sample_standard_app/db). If you want to build the knowledge base from scratch, you can run the following code:
```python
from agentuniverse.base.agentuniverse import AgentUniverse
from agentuniverse.agent.action.knowledge.knowledge_manager import KnowledgeManager
@@ -78,12 +78,12 @@ if __name__ == '__main__':
### Law Agent
This agent involves the following two files:
-- [law_rag_agent.py](../../../sample_standard_app/app/core/agent/rag_agent_case/law_rag_agent.py): Defines the agent's input and output
-- [law_rag_agent.yaml](../../../sample_standard_app/app/core/agent/rag_agent_case/law_rag_agent.yaml): Defines the agent's related prompts
+- [law_rag_agent.py](../../../../sample_standard_app/app/core/agent/rag_agent_case/law_rag_agent.py): Defines the agent's input and output
+- [law_rag_agent.yaml](../../../../sample_standard_app/app/core/agent/rag_agent_case/law_rag_agent.yaml): Defines the agent's related prompts
### Demonstration Code
-[CodeLink](../../../sample_standard_app/app/examples/law_chat_bot.py)
+[CodeLink](../../../../sample_standard_app/app/examples/law_chat_bot.py)
## Demonstration
-
\ No newline at end of file
+
\ No newline at end of file
diff --git a/docs/guidebook/en/7_1_1_Python_Auto_Runner.md b/docs/guidebook/en/Examples/Python_Auto_Runner.md
similarity index 86%
rename from docs/guidebook/en/7_1_1_Python_Auto_Runner.md
rename to docs/guidebook/en/Examples/Python_Auto_Runner.md
index 1832cf62..57bfff3c 100644
--- a/docs/guidebook/en/7_1_1_Python_Auto_Runner.md
+++ b/docs/guidebook/en/Examples/Python_Auto_Runner.md
@@ -39,13 +39,13 @@ metadata:
```
Here we used two tools: google_search_tool and python_runner. The relevant tool code links are as follows:
-- [google_search_tool](../../../sample_standard_app/app/core/tool/google_search_tool.yaml)
-- [python_runner](../../../sample_standard_app/app/core/tool/python_repl_tool.yaml)
+- [google_search_tool](../../../../sample_standard_app/app/core/tool/google_search_tool.yaml)
+- [python_runner](../../../../sample_standard_app/app/core/tool/python_repl_tool.yaml)
### Case Run
1. Test Case Run
-Directly run with test code[test_case](../../../sample_standard_app/app/test/test_react_agent.py)
+Directly run with test code[test_case](../../../../sample_standard_app/app/test/test_react_agent.py)
2. Interface Run
After configuring the related keys, start the web service and use the following curl for testing.
```shell
@@ -62,7 +62,7 @@ curl --location --request POST 'http://localhost:8888/service_run' \
```
### Result
-
+
In the image, React went through three steps in total:
Step 1: The model provided a piece of Python code and handed it over to the Python Runner tool for execution, but the execution failed due to the failure to use print to output the execution result.
diff --git a/docs/guidebook/en/7_1_1_Translation_Case.md b/docs/guidebook/en/Examples/Translation_Assistant.md
similarity index 56%
rename from docs/guidebook/en/7_1_1_Translation_Case.md
rename to docs/guidebook/en/Examples/Translation_Assistant.md
index 4a34620c..a94e1930 100644
--- a/docs/guidebook/en/7_1_1_Translation_Case.md
+++ b/docs/guidebook/en/Examples/Translation_Assistant.md
@@ -1,4 +1,4 @@
-# Translation Case Study
+# Translation Assistant
Recently, Professor Andrew Ng of Stanford University open-sourced an AI agent for machine translation—an agent that employs a reflective workflow for translation. This project showcases an example of machine translation utilizing the reflective agent workflow. The primary steps of the agent include:
1. Initial translation, utilizing a large model (LLM) to translate text from the source language to the target language;
2. Reflection, wherein the large model identifies deficiencies in the translation and offers constructive improvement suggestions;
@@ -8,43 +8,43 @@ This case is based on the Qianwen large model, and prior to use, you need to con
## Collaborative Working Process of Multi-Agents
During the translation process, the priority is to ascertain whether the model's length surpasses the maximum number of tokens it can accommodate. For instances where the length exceeds the limit, the text is initially segmented, followed by the translation of each segment. Nonetheless, the entire translation process adheres to the initial translation -> reflection -> revision workflow.
-
+
Implementing this translation in aU involves the following steps:
1. Define prompts related to translation, with three for short text and three for long text. Relevant files include:
- - [Short Text Init Prompt](../../../sample_standard_app/app/core/prompt/translation/translation_init_en.yaml)
- - [Short Text Reflection Prompt](../../../sample_standard_app/app/core/prompt/translation/translation_reflection_en.yaml)
- - [Short Text Improve Prompt](../../../sample_standard_app/app/core/prompt/translation/translation_improve_en.yaml)
- - [Long Text Init Prompt](../../../sample_standard_app/app/core/prompt/translation/multi_translation_init_en.yaml)
- - [Long Text Reflection Prompt](../../../sample_standard_app/app/core/prompt/translation/multi_translation_improve_en.yaml)
- - [Long Text Improve Prompt](../../../sample_standard_app/app/core/prompt/translation/multi_translation_improve_en.yaml)
+ - [Short Text Init Prompt](../../../../sample_standard_app/app/core/prompt/translation/translation_init_en.yaml)
+ - [Short Text Reflection Prompt](../../../../sample_standard_app/app/core/prompt/translation/translation_reflection_en.yaml)
+ - [Short Text Improve Prompt](../../../../sample_standard_app/app/core/prompt/translation/translation_improve_en.yaml)
+ - [Long Text Init Prompt](../../../../sample_standard_app/app/core/prompt/translation/multi_translation_init_en.yaml)
+ - [Long Text Reflection Prompt](../../../../sample_standard_app/app/core/prompt/translation/multi_translation_improve_en.yaml)
+ - [Long Text Improve Prompt](../../../../sample_standard_app/app/core/prompt/translation/multi_translation_improve_en.yaml)
2. Define three agents
- - [Short Text Translation Work Agent](../../../sample_standard_app/app/core/agent/translation_agent_case/translation_work_agent.yaml)
- - [Short Text Translation Reflection Agent](../../../sample_standard_app/app/core/agent/translation_agent_case/translation_reflection_agent.yaml)
- - [Short Text Translation Improvement Agent](../../../sample_standard_app/app/core/agent/translation_agent_case/translation_improve_agent.yaml)
- These agents switch their prompts based on whether the task involves translating long or short texts. The specific logic for this switching mechanism is detailed in the [agent file](../../../sample_standard_app/app/core/agent/translation_agent_case/translation_agent.py).
+ - [Short Text Translation Work Agent](../../../../sample_standard_app/app/core/agent/translation_agent_case/translation_work_agent.yaml)
+ - [Short Text Translation Reflection Agent](../../../../sample_standard_app/app/core/agent/translation_agent_case/translation_reflection_agent.yaml)
+ - [Short Text Translation Improvement Agent](../../../../sample_standard_app/app/core/agent/translation_agent_case/translation_improve_agent.yaml)
+ These agents switch their prompts based on whether the task involves translating long or short texts. The specific logic for this switching mechanism is detailed in the [agent file](../../../../sample_standard_app/app/core/agent/translation_agent_case/translation_agent.py).
3. Define the collaborative work process of the three agents
The collaborative process is illustrated in the earlier-mentioned flowchart of multi-agent collaboration.
-
-For a deeper dive into the processes, refer to the [detailed code file](../../../sample_standard_app/app/core/agent/translation_agent_case/translation_by_token_agent.py).
-The [configuration file](../../../sample_standard_app/app/core/agent/translation_agent_case/translation_agent.yaml) for the collaborative agents.
+
+For a deeper dive into the processes, refer to the [detailed code file](../../../../sample_standard_app/app/core/agent/translation_agent_case/translation_by_token_agent.py).
+The [configuration file](../../../../sample_standard_app/app/core/agent/translation_agent_case/translation_agent.yaml) for the collaborative agents.
### Demonstration Code
-[Code Link](../../../sample_standard_app/app/test/test_translation_agent.py)
+[Code Link](../../../../sample_standard_app/app/test/test_translation_agent.py)
-[Long Text](../../../sample_standard_app/app/test/translation_data/long_text.txt)
-[Short Text](../../../sample_standard_app/app/test/translation_data/short_text.txt)
+[Long Text](../../../../sample_standard_app/app/test/translation_data/long_text.txt)
+[Short Text](../../../../sample_standard_app/app/test/translation_data/short_text.txt)
-[Translation Of Long Text](../../../sample_standard_app/app/test/translation_data/short_text_result.txt)
-[Translation Of Short Text](../../../sample_standard_app/app/test/translation_data/long_text_result.txt)
+[Translation Of Long Text](../../../../sample_standard_app/app/test/translation_data/short_text_result.txt)
+[Translation Of Short Text](../../../../sample_standard_app/app/test/translation_data/long_text_result.txt)
### 演示结果
We can see that using aU maintains consistency with the original translation_agent project results, successfully replicated.
aU Results:
-
+
translation_agent Results:
-
+
### Others
In reference to Professor Andrew Ng's code, when managing segmented translations, to ensure the coherence of the translation, each segment is translated with the corresponding context. However, incorporating all translation content into the context within his code can undermine the original intent of segmentation, and in certain cases, it can result in an excess of tokens beyond the model's capacity. I have raised a related issue on the corresponding repository address: [Issue Link](https://github.com/andrewyng/translation-agent/issues/28)## Implementation in aU
diff --git a/docs/guidebook/en/1_4_Application_Engineering_Structure_Explanation.md b/docs/guidebook/en/Get_Start/Application_Project_Structure_and_Explanation.md
similarity index 99%
rename from docs/guidebook/en/1_4_Application_Engineering_Structure_Explanation.md
rename to docs/guidebook/en/Get_Start/Application_Project_Structure_and_Explanation.md
index 07541951..881a20fa 100644
--- a/docs/guidebook/en/1_4_Application_Engineering_Structure_Explanation.md
+++ b/docs/guidebook/en/Get_Start/Application_Project_Structure_and_Explanation.md
@@ -1,4 +1,4 @@
-# Application Engineering Structure and Explanation
+# Application Project Structure and Explanation
As you can see, `agentUniverse` is designed with lightness and integrative capabilities in mind, allowing you to incorporate `agentUniverse` into any of your projects for seamless operation.
## Recommended Project Directory Structure and Explanation
diff --git a/docs/guidebook/en/1_2_Installation.md b/docs/guidebook/en/Get_Start/Installation.md
similarity index 92%
rename from docs/guidebook/en/1_2_Installation.md
rename to docs/guidebook/en/Get_Start/Installation.md
index 3c16bc37..1c347aab 100644
--- a/docs/guidebook/en/1_2_Installation.md
+++ b/docs/guidebook/en/Get_Start/Installation.md
@@ -25,7 +25,7 @@ Or add the following content to your `pyproject.toml` file:
[tool.poetry.dependencies]
agentUniverse = "^0.0.3"
```
-A standard project's `pyproject.toml` can be found [here](../../../sample_standard_app/pyproject.toml).
+A standard project's `pyproject.toml` can be found [here](../../../../sample_standard_app/pyproject.toml).
Use the `poetry update` command to update dependencies:
```shell
@@ -38,4 +38,4 @@ pip list | grep agentUniverse
```
If you see `agentUniverse` and its version number, the installation was successful.
-
\ No newline at end of file
+
\ No newline at end of file
diff --git a/docs/guidebook/en/1_1_Introduction.md b/docs/guidebook/en/Get_Start/Introduction.md
similarity index 95%
rename from docs/guidebook/en/1_1_Introduction.md
rename to docs/guidebook/en/Get_Start/Introduction.md
index 9943e90b..eb428e2d 100644
--- a/docs/guidebook/en/1_1_Introduction.md
+++ b/docs/guidebook/en/Get_Start/Introduction.md
@@ -13,7 +13,7 @@ This pattern consists of three agents: Data-fining agent, which is designed to s
More patterns are coming soon...
-
+
In addition to rich collaboration modes, agentUniverse also includes the following main features:
diff --git a/docs/guidebook/en/1_Run_the_first_example.md b/docs/guidebook/en/Get_Start/Quick_Start.md
similarity index 94%
rename from docs/guidebook/en/1_Run_the_first_example.md
rename to docs/guidebook/en/Get_Start/Quick_Start.md
index ef3afbcd..bdb62d88 100644
--- a/docs/guidebook/en/1_Run_the_first_example.md
+++ b/docs/guidebook/en/Get_Start/Quick_Start.md
@@ -1,4 +1,4 @@
-# Run the first example
+# Quick Start
Through this document, you will learn how to quickly run examples of agentUniverse and personally experience its effects.
## 1.Preparation Work
@@ -62,19 +62,19 @@ This framework supports key injection through environment variables, file config
##### step1. Confirm that the config file enables automatic reading of the external key file
Locate the main configuration file in the project (path: agentUniverse/sample_standard_app/config/config.toml). Find the SUB_CONFIG_PATH configuration item, and uncomment the custom_key_path configuration item as shown in the picture below:
-
+
This step will enable the project to automatically read configuration files and batch load keys. We can see that the custom_key_path configuration option already includes one default path. To simplify the tutorial, we will not modify the path here.
##### step2. Create an external key file based on the template
The external key file template is located at the same level as the config path (specifically at sample_standard_app/config/custom_key.toml.sample). We will copy custom_key.toml.sample and create a new file, naming it custom_key.toml in accordance with the default configuration of custom_key_path from step 1, as shown in the image below:
-
+
Tips: The external key file generally contains all of your access keys (AK), which are very private and need to be strictly protected. This file should never be leaked or managed on code platforms like Git. In actual production projects, we typically separate this file from the project and implement strong system-level permission controls. The steps in the key configuration of this framework are mainly for the sake of production security.
##### step3. In the external key file, configure your commonly used model AK
The key file contains dozens of common model service AK formats. You can fill in your own keys according to your needs, and don't forget to uncomment them. In subsequent tutorials, we will use the Qwen and GPT models as the LLM for the tutorial agent, so here we will configure the corresponding AK for Qianwen and GPT as shown in the image below:
-
+
## 2. Run the first example
The agentUniverse currently includes 5 official tutorial cases, located at agentUniverse/sample_standard_app/app/examples.
@@ -83,10 +83,10 @@ In this section, we will run the first example, choosing the law_chat_bot as our
### 2.1 Determine the agent used behind the example and its configuration
For instance, in the case of law_chat_bot (path: agentUniverse/sample_standard_app/app/examples/law_chat_bot.py), we first identify the corresponding agent_name in the script. For the law_chat_bot, it is law_rag_agent:
-
+
After determining the agent used in the example, we go to the project agent directory (the directory path is: agentUniverse/sample_standard_app/app/core/agent) and find the corresponding agent configuration file law_rag_agent.yaml. Note that the name field in the agent configuration corresponds to the agent name in law_chat_bot.
-
+
Let's further examine the other configuration details in the law_rag_agent.yaml file, focusing on the llm_model configuration item. This item specifies the LLM used by the agent. By default, law_rag_agent uses the qwen series, specifically qwen-max, as the model core. If you configured a different series model type during the key configuration stage, you'll need to replace it here. You can refer to the following common model replacements. You can copy the default settings, and if needed, you can replace the model_name according to the official model codes of the service provider.
@@ -138,11 +138,11 @@ Tips: To simplify the configuration process, we only list a selection of commonl
### 2.2 Run the Example
By following the steps above, you have completed all the preparatory work. Now, let's run it and see the results. Locate the agentUniverse/sample_standard_app/app/examples/law_chat_bot.py file and run it in your IDE or in the shell.
-
+
When you see the following results, it indicates that the case has run successfully.
-
+
## 3. Run the other example
diff --git a/docs/guidebook/en/1_3_Quick_Start.md b/docs/guidebook/en/Get_Start/Start_Tutorial.md
similarity index 98%
rename from docs/guidebook/en/1_3_Quick_Start.md
rename to docs/guidebook/en/Get_Start/Start_Tutorial.md
index 8cf09be2..3d851b77 100644
--- a/docs/guidebook/en/1_3_Quick_Start.md
+++ b/docs/guidebook/en/Get_Start/Start_Tutorial.md
@@ -1,4 +1,4 @@
-# Quick Start
+# Start Tutorial
we will show you how to:
* Prepare the environment and application engineering
@@ -12,7 +12,7 @@ we will show you how to:
- python 3.10+
### Application Preparation
-We provide a standard project template which you can access [here](../../../sample_standard_app) .
+We provide a standard project template which you can access [here](../../../../sample_standard_app) .
The "sample_standard_app" folder contains a standard project template that you can modify according to your own needs. You can also copy the "sample_standard_app" folder to use as the root directory of your application project.
@@ -226,7 +226,7 @@ python server_application.py
```
When the command line shows that the service is listening successfully, the service is started. By default, the service listens on the address `127.0.0.1` and port `8000`, with 5 workers. You can modify the configuration in `config/gunicorn_config.toml`.(Note that on Windows systems and when directly using Flask to start, the default listening port is currently 8888.)
-
+
### Access the Service
#### Local Access
diff --git a/docs/guidebook/en/2_2_4_How_To_Build_A_RAG_Agent.md b/docs/guidebook/en/How-to/How_To_Build_A_RAG_Agent.md
similarity index 87%
rename from docs/guidebook/en/2_2_4_How_To_Build_A_RAG_Agent.md
rename to docs/guidebook/en/How-to/How_To_Build_A_RAG_Agent.md
index b8617abe..277d5199 100644
--- a/docs/guidebook/en/2_2_4_How_To_Build_A_RAG_Agent.md
+++ b/docs/guidebook/en/How-to/How_To_Build_A_RAG_Agent.md
@@ -1,6 +1,6 @@
# How to Build a RAG Agent
-This tutorial provides a quick guide to building a RAG (Retrieval-Augmented Generation) agent within agentUniverse. The full structure and content of the case can be found in [this document](7_1_1_Legal_Consultation_Case.md). This document focuses on the construction process, so some non-essential content has been omitted.
+This tutorial provides a quick guide to building a RAG (Retrieval-Augmented Generation) agent within agentUniverse. The full structure and content of the case can be found in [this document](../Examples/Legal_Advice.md). This document focuses on the construction process, so some non-essential content has been omitted.
## Case Description
This case is based on RagPlanner and sets up a simple legal consultation agent that provides relevant legal advice by retrieving applicable articles from the Civil Code and Criminal Code and considering the case background.
@@ -31,8 +31,8 @@ metadata:
## Building the Knowledge Index
Origin docs：
-- [民法典.pdf](../../../sample_standard_app/app/resources/民法典.pdf)
-- [刑法.pdf](../../../sample_standard_app/app/resources/刑法.pdf)
+- [民法典.pdf](../../../../sample_standard_app/app/resources/民法典.pdf)
+- [刑法.pdf](../../../../sample_standard_app/app/resources/刑法.pdf)
### Extracting Text from PDFs
Since the original documents in this case are in PDF format, we configured the Knowledge component as follows:
@@ -40,7 +40,7 @@ Since the original documents in this case are in PDF format, we configured the K
readers:
pdf: "default_pdf_reader"
```
-This allows the extraction of text from the PDF. If you want to read more file formats, you can refer to the [Reader component](2_2_4_Reader.md).
+This allows the extraction of text from the PDF. If you want to read more file formats, you can refer to the [Reader component](../In-Depth_Guides/Tutorials/Knowledge/Reader.md).
### Splitting Long Text
Since the text content in the original documents is very long, we need to split it into smaller chunks. Here we use `recursive_character_text_splitter` for splitting, configured as follows:：
@@ -48,7 +48,7 @@ Since the text content in the original documents is very long, we need to split
insert_processors:
- "recursive_character_text_splitter"
```
-This configuration is a list format, allowing multiple document processors to be configured. The only specified processor in this case, recursive_character_text_splitter, recursively splits the original document according to a specified delimiter until it meets the required length. For more details, refer to [DocProcessor](2_2_4_DocProcessor.md). This document also includes other document processors that you can use or customize.
+This configuration is a list format, allowing multiple document processors to be configured. The only specified processor in this case, recursive_character_text_splitter, recursively splits the original document according to a specified delimiter until it meets the required length. For more details, refer to [DocProcessor](../In-Depth_Guides/Tutorials/Knowledge/DocProcessor.md). This document also includes other document processors that you can use or customize.
### Configuring the Store
This case includes four Stores: the Civil Law and Criminal Law are stored separately in SQLite and ChromaDB. We will take `civil_law_chroma_store` as an example, with other Stores being similar.
@@ -64,7 +64,7 @@ metadata:
class: 'ChromaStore'
```
-The `persist_path` specifies the local storage location of the database file and designates `dashscope_embedding` as the component for vectorizing the text in the database. `similarity_top_k` indicates the number of documents to be retrieved. For more details on Store, refer to [this document](2_2_4_Store.md).
+The `persist_path` specifies the local storage location of the database file and designates `dashscope_embedding` as the component for vectorizing the text in the database. `similarity_top_k` indicates the number of documents to be retrieved. For more details on Store, refer to [this document](../In-Depth_Guides/Tutorials/Knowledge/Store.md).
### Executing the Insertion Process
@@ -107,4 +107,4 @@ action:
```
We configure the knowledge like this in the YAML file of the Agent.
-For the complete case and how to invoke it, please refer to [this document](7_1_1_Legal_Consultation_Case.md).
\ No newline at end of file
+For the complete case and how to invoke it, please refer to [this document](../Examples/Legal_Advice.md).
\ No newline at end of file
diff --git a/docs/guidebook/en/10_1_2_Product_Platform_Advancement_Guide.md b/docs/guidebook/en/How-to/Product_Platform_Advancement_Guide.md
similarity index 85%
rename from docs/guidebook/en/10_1_2_Product_Platform_Advancement_Guide.md
rename to docs/guidebook/en/How-to/Product_Platform_Advancement_Guide.md
index e804fa50..ef714caa 100644
--- a/docs/guidebook/en/10_1_2_Product_Platform_Advancement_Guide.md
+++ b/docs/guidebook/en/How-to/Product_Platform_Advancement_Guide.md
@@ -13,7 +13,7 @@ pip install magent-ui==0.1.17 ruamel.yaml --force-reinstall
```
### Create Workflow Agent
On the aU-product homepage, click the "Create Agent" button to the right of the agent tab, and select the workflow type agent.
-
+
### Workflow Node Type
The current aU product platform supports 7 types of nodes, which are:
@@ -35,16 +35,16 @@ Note: Please ensure that the logic for passing parameters between nodes is corre
```
The complete workflow process is shown in the following figure:
-
+
The configuration file for the agent generated by aU is shown in the following figure:
-
+
### Run Workflow Agent
After clicking the save button, start attempting to run the workflow agent.
The operation process is as shown in the figure:
-
+
## Table Form Agent Creation Feature
@@ -53,13 +53,13 @@ On the product homepage, click the 'Create Agent' button to the right of the age
aU will automatically generate the corresponding agent yaml file locally, assisting users in completing their development work.
-
+
### Run Agent
After clicking the save button, start attempting to run the created example RAG agent.
The operation process is as shown in the figure:
-
+
## Custom Knowledge Insertion Feature
### Create Custom Knowledge
@@ -67,7 +67,7 @@ On the product homepage, switch to the Knowledge tab, and click the 'Add Knowled
aU will automatically generate the corresponding knowledge and store yaml files locally, assisting users in completing their development work.
-
+
### Upload Knowledge
Specify the knowledge base, click the upload button, and upload the local knowledge file.
@@ -78,12 +78,12 @@ After the upload is successful, you can use the corresponding knowledge base in
Currently supported knowledge types are: pdf/docx/pptx/txt
```
The upload operation is as shown in the figure:
-
+
## Custom Plugin Insertion Feature
### Create Custom Plugin
On the product homepage, switch to the Plugin tab, and click the 'Create Plugin' button to the right to create a custom plugin.
-
+
After successful creation, you can use the corresponding tools in the tool nodes of the workflow agent or the tool modules of the table form agent, providing powerful third-party plugin capabilities to support the agent.
diff --git a/docs/guidebook/en/10_1_1_Product Platform Quick Start.md b/docs/guidebook/en/How-to/Product_Platform_Quick_Start.md
similarity index 83%
rename from docs/guidebook/en/10_1_1_Product Platform Quick Start.md
rename to docs/guidebook/en/How-to/Product_Platform_Quick_Start.md
index 803d54b7..424bf8a1 100644
--- a/docs/guidebook/en/10_1_1_Product Platform Quick Start.md
+++ b/docs/guidebook/en/How-to/Product_Platform_Quick_Start.md
@@ -8,7 +8,7 @@ In this section, we will show you how to:
## Environment and Application Engineering Preparation
### Application Engineering Preparation
-We have placed the **product module samples** in the agentUniverse’s sample_standard_app project. You can view them [here](../../../sample_standard_app/app/core/product). This part can be configured in the background through YAML, and of course, these functions can be automatically created and managed through the product page.
+We have placed the **product module samples** in the agentUniverse’s sample_standard_app project. You can view them [here](../../../../sample_standard_app/app/core/product). This part can be configured in the background through YAML, and of course, these functions can be automatically created and managed through the product page.
### Installing Dependencies
**Using pip**
@@ -33,27 +33,27 @@ Of course, when using the agent, you need to pre-configure the various LLM model
## Using the agentUniverse Product Platform
### Starting the Product Service
-Run the [product_application](../../../sample_standard_app/app/bootstrap/product_application.py) file located in `sample_standard_app/app/bootstrap` to start with one click.
+Run the [product_application](../../../../sample_standard_app/app/bootstrap/product_application.py) file located in `sample_standard_app/app/bootstrap` to start with one click.
-
+
After a successful start, it will automatically redirect to the product homepage, which includes system presets and your custom Agent/Tool/Knowledge product modules.
-
+
### Experience the Agent
As shown in the image above, click the chat button on the right of the peer multi-agent group to enter the conversation page.
The conversation management system includes the last 10 agent conversation history records, allowing you to directly engage in multi-turn dialogues and experience the capabilities of the peer multi-agent group (default is streaming dialogue, and the multi-agent group includes the intermediate thinking process).
-
+
### Debugging the Agent
On the product homepage, click the edit button on the left of the agent to enter the online debugging page.
You can debug the agent’s Prompt/Tool/Knowledge/LLM online. Click the save button, and aU-product will automatically save the configuration to the corresponding yaml file.
-
+
Click the debug button in the upper right corner of the image above to view the Trace information, including token consumption, call chain, and latency of the agent’s specific invocation process.
-
+
## Configuring agentUniverse Product Modules
### Creating Product Modules
diff --git a/docs/guidebook/en/3_1_2_0_List_Of_LLMs.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/0.List_Of_LLMs.md
similarity index 54%
rename from docs/guidebook/en/3_1_2_0_List_Of_LLMs.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/0.List_Of_LLMs.md
index c716e927..0d6d0c05 100644
--- a/docs/guidebook/en/3_1_2_0_List_Of_LLMs.md
+++ b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/0.List_Of_LLMs.md
@@ -1,20 +1,20 @@
# List of LLMs
The platform has currently integrated the following list of models; please refer to this section for detailed usage instructions for each LLM.
-| LLM (Series) Name |
-|---------------------------------------|
-| [OpenAI](3_1_2_OpenAI_LLM_Use.md) |
-| [Qwen](3_1_2_Qwen_LLM_Use.md) |
-| [WenXin](3_1_2_WenXin_LLM_Use.md) |
-| [Kimi](3_1_2_Kimi_LLM_Use.md) |
-| [BaiChuan](3_1_2_BaiChuan_LLM_Use.md) |
-| [Claude](3_1_2_Claude_LLM_Use.md) |
-| [ollama](3_1_2_Ollama_LLM_Use.md) |
-| [DeepSeek](3_1_2_DeepSeek_LLM_Use.md) |
-| [GLM](3_1_2_GLM_LLM_Use.md) |
+| LLM (Series) Name |
+|---------------------------|
+| [OpenAI](OpenAI_LLM_Use.md) |
+| [Qwen](Qwen_LLM_Use.md) |
+| [WenXin](WenXin_LLM_Use.md) |
+| [Kimi](Kimi_LLM_Use.md) |
+| [BaiChuan](BaiChuan_LLM_Use.md) |
+| [Claude](Claude_LLM_Use.md) |
+| [ollama](Ollama_LLM_Use.md) |
+| [DeepSeek](DeepSeek_LLM_Use.md) |
+| [GLM](GLM_LLM_Use.md) |
-To facilitate the integration of models with OpenAI-style protocols, we offer a wrapper object based on the OpenAI general protocol. See [OpenAIStyleLLM](3_1_2_OpenAIStyleLLM_Use.md).
+To facilitate the integration of models with OpenAI-style protocols, we offer a wrapper object based on the OpenAI general protocol. See [OpenAIStyleLLM](OpenAIStyleLLM_Use.md).
-For LLM not included in the list, you can customize the integration of any LLM according to the steps provided in the [LLM definition](2_2_3_Tool_Create_And_Use.md).
+For LLM not included in the list, you can customize the integration of any LLM according to the steps provided in the [LLM definition](../../Tutorials/LLM/LLM_component_define_and_usage.md).
At the same time, we are adding the integration methods for common LLMs such as Gemini, Llama, ZhipuAI, etc. If you have used these LLMs in your projects and have created your own instances, we welcome you to submit a PR to become a contributor to agentUniverse.
\ No newline at end of file
diff --git a/docs/guidebook/en/3_1_2_BaiChuan_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/BaiChuan_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_BaiChuan_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/BaiChuan_LLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_Claude_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/Claude_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_Claude_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/Claude_LLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_DeepSeek_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/DeepSeek_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_DeepSeek_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/DeepSeek_LLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_GLM_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/GLM_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_GLM_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/GLM_LLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_Kimi_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/Kimi_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_Kimi_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/Kimi_LLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_Ollama_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/Ollama_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_Ollama_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/Ollama_LLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_OpenAIStyleLLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/OpenAIStyleLLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_OpenAIStyleLLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/OpenAIStyleLLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_OpenAI_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/OpenAI_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_OpenAI_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/OpenAI_LLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_Qwen_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/Qwen_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_Qwen_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/Qwen_LLM_Use.md
diff --git a/docs/guidebook/en/3_1_2_WenXin_LLM_Use.md b/docs/guidebook/en/In-Depth_Guides/Components/LLMs/WenXin_LLM_Use.md
similarity index 100%
rename from docs/guidebook/en/3_1_2_WenXin_LLM_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Components/LLMs/WenXin_LLM_Use.md
diff --git a/docs/guidebook/en/2_2_3_Integrated_LangChain_Tools.md b/docs/guidebook/en/In-Depth_Guides/Components/Tools/Integrated_LangChain_Tools.md
similarity index 93%
rename from docs/guidebook/en/2_2_3_Integrated_LangChain_Tools.md
rename to docs/guidebook/en/In-Depth_Guides/Components/Tools/Integrated_LangChain_Tools.md
index fcaba8f4..642bcb24 100644
--- a/docs/guidebook/en/2_2_3_Integrated_LangChain_Tools.md
+++ b/docs/guidebook/en/In-Depth_Guides/Components/Tools/Integrated_LangChain_Tools.md
@@ -9,7 +9,7 @@ For the second category of tools, we have implemented a LangChainTool base class
Note: If you want to directly use the description from LangChain, the description in the configuration file must be set to empty.
An Example of Tool Initialization:
-[Tool Address](../../../sample_standard_app/app/core/tool/langchain_tool/human_input_run.yaml)
+[Tool Address](../../../../../../sample_standard_app/app/core/tool/langchain_tool/human_input_run.yaml)
```yaml
name: 'human_input_run'
description: ''
@@ -38,7 +38,7 @@ Parameter Description:
If you completely override the `init_langchain_tool` method, then you do not need to configure this part.
## 1. Integrate the DuckDuckGo Tool from LangChain
-[Tool Address](../../../sample_standard_app/app/core/tool/langchain_tool/duckduckgo_search.yaml)
+[Tool Address](../../../../../../sample_standard_app/app/core/tool/langchain_tool/duckduckgo_search.yaml)
```yaml
name: 'duckduckgo_search'
description: 'DuckDuckGo Search tool'
diff --git a/docs/guidebook/en/2_2_3_Integrated_Tools.md b/docs/guidebook/en/In-Depth_Guides/Components/Tools/Integrated_Tools.md
similarity index 92%
rename from docs/guidebook/en/2_2_3_Integrated_Tools.md
rename to docs/guidebook/en/In-Depth_Guides/Components/Tools/Integrated_Tools.md
index 7544fe9e..84ce22ab 100644
--- a/docs/guidebook/en/2_2_3_Integrated_Tools.md
+++ b/docs/guidebook/en/In-Depth_Guides/Components/Tools/Integrated_Tools.md
@@ -5,7 +5,7 @@ In the current au's sample project, the following tools are integrated.
## 1. Search Tools
### 1.1 Google Search
-[Tool path](../../../sample_standard_app/app/core/tool/google_search_tool.yaml)
+[Tool path](../../../../../../sample_standard_app/app/core/tool/google_search_tool.yaml)
Detailed Configuration Information:
```yaml
@@ -37,7 +37,7 @@ SERPER_API_KEY="xxxx"
### 1.2 Bing Search
Currently, it integrates with the official Bing search.
-[Tool path](../../../sample_standard_app/app/core/tool/bing_search_tool.yaml)
+[Tool path](../../../../../../sample_standard_app/app/core/tool/bing_search_tool.yaml)
Tool configuration:
```yaml
name: 'bing_search_tool'
@@ -67,8 +67,8 @@ BING_SUBSCRIPTION_KEY="xxxx"
### 1.3 Search API
Supports multiple search tools, such as:
-- [Baidu search](../../../sample_standard_app/app/core/tool/search_api_baidu_tool.yaml)
-- [Bing search](../../../sample_standard_app/app/core/tool/search_api_bing_tool.yaml)
+- [Baidu search](../../../../../../sample_standard_app/app/core/tool/search_api_baidu_tool.yaml)
+- [Bing search](../../../../../../sample_standard_app/app/core/tool/search_api_bing_tool.yaml)
Other search engines also include: Google search, Amazon search, YouTube search, etc. For more information, please refer to: https://www.searchapi.io/
Tool configuration:
```yaml
@@ -107,7 +107,7 @@ SEARCHAPI_API_KEY="xxxxxx"
## 2. Code Tool
### 2.1 PythonRepl
-[Tool path](../../../sample_standard_app/app/core/tool/python_repl_tool.yaml)
+[Tool path](../../../../../../sample_standard_app/app/core/tool/python_repl_tool.yaml)
This tool can execute a piece of Python code, the configuration information of the tool:
```yaml
name: 'python_runner'
@@ -137,7 +137,7 @@ This tool can be used directly without any key, but for system security, please
## 3.HTTP Tool
### 3.1 HTTP GET
-[Tool path](../../../sample_standard_app/app/core/tool/request_get_tool.yaml)
+[Tool path](../../../../../../sample_standard_app/app/core/tool/request_get_tool.yaml)
The tool can send a GET request, with its configuration information being:
```yaml
name: 'requests_get'
diff --git a/docs/guidebook/en/5_1_1_Docker_Container_Deployment.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Deployment/Docker_Container_Deployment.md
similarity index 94%
rename from docs/guidebook/en/5_1_1_Docker_Container_Deployment.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Deployment/Docker_Container_Deployment.md
index ec2aec02..b92e960f 100644
--- a/docs/guidebook/en/5_1_1_Docker_Container_Deployment.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Deployment/Docker_Container_Deployment.md
@@ -3,7 +3,7 @@
AgentUniverse provides standard work environment images for containerized deployment of AgentUniverse projects. This document will explain how to deploy your own project based on the such images. You can get full tag list in [this site](https://cr.console.aliyun.com/repository/cn-hangzhou/agent_universe/agent_universe/images).
## Preparations
-1. Build your own project according to the standard directory structure of AgentUniverse, referring to [Application_Engineering_Structure_Explanation](1_4_Application_Engineering_Structure_Explanation.md)。For ease of explanation, this document assumes the project name and project directory are `sample_standard_app`.
+1. Build your own project according to the standard directory structure of AgentUniverse, referring to [Application_Engineering_Structure_Explanation](../../../Get_Start/Application_Project_Structure_and_Explanation.md)。For ease of explanation, this document assumes the project name and project directory are `sample_standard_app`.
2. Get the required version of the AgentUniverse image.
```shell
docker pull registry.cn-hangzhou.aliyuncs.com/agent_universe/agent_universe:0.0.9_centos8
diff --git a/docs/guidebook/en/5_1_2_K8S_Deployment.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Deployment/K8S_Deployment.md
similarity index 92%
rename from docs/guidebook/en/5_1_2_K8S_Deployment.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Deployment/K8S_Deployment.md
index 3d6c08ff..e5b28d5d 100644
--- a/docs/guidebook/en/5_1_2_K8S_Deployment.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Deployment/K8S_Deployment.md
@@ -62,7 +62,7 @@ In the resource configuration file, uncomment the `env` section and replace `val
#### Method 2
-Please refer to the description at the beginning of the configuration file: [Quick Start Guide](https://github.com/antgroup/agentUniverse/blob/master/docs/guidebook/zh/1_3_快速开始.md)
+Please refer to the description at the beginning of the configuration file: [Quick Start Guide](../../../Get_Start/Quick_Start.md)
## 2. Building Resources
@@ -80,7 +80,7 @@ Verify that all resources have been correctly deployed:
kubectl get all -n agent-namespace
```
-
+
## 4. Accessing AgentUniverse Services from Inside the Cluster
@@ -98,7 +98,7 @@ kubectl exec -it [Pod Name] -n agent-namespace -- curl http://agentuniverse-serv
kubectl exec -it agentuniverse-deployment-55cfd778d-g7d9d -n agent-namespace -- curl http://agentuniverse-service:9999/echo
```
-
+
#### 4.1.2 Q&A Test
@@ -106,4 +106,4 @@ kubectl exec -it agentuniverse-deployment-55cfd778d-g7d9d -n agent-namespace --
kubectl exec -it agentuniverse-deployment-55cfd778d-g7d9d -n agent-namespace -- curl -X POST -H "Content-Type: application/json" -d '{"service_id":"demo_service","params":{"input":"(18+3-5)/2*4=?"}}' http://agentuniverse-service:9999/service_run
```
-
+
diff --git a/docs/guidebook/en/3_2_4_Alibaba_Cloud_SLS.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Alibaba_Cloud_SLS.md
similarity index 100%
rename from docs/guidebook/en/3_2_4_Alibaba_Cloud_SLS.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Alibaba_Cloud_SLS.md
diff --git a/docs/guidebook/en/2_6_Logging_Utils.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Logging_Utils.md
similarity index 98%
rename from docs/guidebook/en/2_6_Logging_Utils.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Logging_Utils.md
index 9d22846f..26632c0a 100644
--- a/docs/guidebook/en/2_6_Logging_Utils.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Logging_Utils.md
@@ -45,7 +45,7 @@ log_format: str = ("{time:YYYY-MM-DD HH:mm:ss.SSS} "
":{line} "
"| {message}")
```
-Where `{extra[context_prefix]}` defaults to `default`, When `LOG_CONTEXT` exists in the framework context, its contents will be replaced by the contents of `LOG_CONTEXT`. For more information related to the framework context, please refer to [Framework_Context](2_7_Framework_Context.md)。
+Where `{extra[context_prefix]}` defaults to `default`, When `LOG_CONTEXT` exists in the framework context, its contents will be replaced by the contents of `LOG_CONTEXT`. For more information related to the framework context, please refer to [Framework_Context](../Others/Framework_Context.md)。
## Global Log Component
AgentUniverse provides a directly usable log component `logging_util.Logger`, which you can introduce into your project as follows:
@@ -72,4 +72,4 @@ Logs recorded by this new component will be saved in the log storage path, in a
## External Log Service
-If you want to use more log utils, please refer to [extension logging utils](3_2_4_Alibaba_Cloud_SLS.md).
+If you want to use more log utils, please refer to [extension logging utils](Alibaba_Cloud_SLS.md).
diff --git a/docs/guidebook/en/2_5_1_Monitor_Module.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Monitor_Module.md
similarity index 100%
rename from docs/guidebook/en/2_5_1_Monitor_Module.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Log_And_Monitor/Monitor_Module.md
diff --git a/docs/guidebook/en/4_1_API_Reference.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Others/API_Reference.md
similarity index 100%
rename from docs/guidebook/en/4_1_API_Reference.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Others/API_Reference.md
diff --git a/docs/guidebook/en/2_7_Framework_Context.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Others/Framework_Context.md
similarity index 100%
rename from docs/guidebook/en/2_7_Framework_Context.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Others/Framework_Context.md
diff --git a/docs/guidebook/en/2_4_1_Service_Information_Storage.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Service_Information_Storage.md
similarity index 90%
rename from docs/guidebook/en/2_4_1_Service_Information_Storage.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Service_Information_Storage.md
index 6130e76d..dbbe16c5 100644
--- a/docs/guidebook/en/2_4_1_Service_Information_Storage.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Service_Information_Storage.md
@@ -12,7 +12,7 @@ system_db_uri = ''
```
Please note that this URI should comply with the URI format specification in SQLAlchemy.
When this value is empty, a `DB` folder will be created in the project root directory, and a SQLite DB file named `agent_universe.db` will be created in the folder as the default system database.
-If you wish to obtain more information on how to use the system database, you can refer to the section [SQLDB_WRAPPER](2_3_1_SQLDB_WRAPPER.md), where the name of the system database is registered as `__system_db__`.
+If you wish to obtain more information on how to use the system database, you can refer to the section [SQLDB_WRAPPER](../Storage/SQLDB_WRAPPER.md), where the name of the system database is registered as `__system_db__`.
diff --git a/docs/guidebook/en/2_4_1_Service_Registration_and_Usage.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Service_Registration_and_Usage.md
similarity index 93%
rename from docs/guidebook/en/2_4_1_Service_Registration_and_Usage.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Service_Registration_and_Usage.md
index cb2462fc..299df8cb 100644
--- a/docs/guidebook/en/2_4_1_Service_Registration_and_Usage.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Service_Registration_and_Usage.md
@@ -24,8 +24,8 @@ metadata:
```
- **`name`**: The name of the Service, which needs to be provided when calling the service through the Web API.
- **`description`**: Description of the Service's functionality.
-- **`agent`**: The name of the Agent. For more information about Agents, please refer to [Agent]().
+- **`agent`**: The name of the Agent. For more information about Agents, please refer to Agent.
- **`metadata`**: Indicates that this configuration is for a Service; no changes are needed.
## Usage
-Please refer to [Web API](2_4_1_Web_Api.md).
\ No newline at end of file
+Please refer to [Web API](Web_Api.md).
\ No newline at end of file
diff --git a/docs/guidebook/en/2_4_1_Web_Api.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Web_Api.md
similarity index 95%
rename from docs/guidebook/en/2_4_1_Web_Api.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Web_Api.md
index 2864a63b..cdc5950d 100644
--- a/docs/guidebook/en/2_4_1_Web_Api.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Web_Api.md
@@ -31,7 +31,7 @@ The expected return value example is as follows:
- **`success`**: Indicates whether the Agent call was successful or not, with values `true` and `false`.。
- **`message`**: When the `success` value is `false`, this value represents the error message, and it is `null` when successful.
- **`result`**: Represents the result of the execution when the Agent call is successful.
-- **`request_id`**: A random string, used for a unique request. It can be used in the [/service_run_result](#servicerunresult) interface to query the result of the corresponding request.
+- **`request_id`**: A random string, used for a unique request. It can be used in the [/service_run_result](#service_run_result) interface to query the result of the corresponding request.
## /service_run_stream
@@ -63,7 +63,7 @@ The interface will return immediately:
}
```
The return result will only contain the success indicating whether the call was successful or not, and the request_id indicating this call.
-For the result of the call, you need to use the request_id to query in the [/service_run_result](#servicerunresult) interface.
+For the result of the call, you need to use the request_id to query in the [/service_run_result](#service_run_result) interface.
## /service_run_result
This GET interface allows users to check the request status with request_id, an example call is as follows:
diff --git a/docs/guidebook/en/2_4_1_Web_Server.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Web_Server.md
similarity index 100%
rename from docs/guidebook/en/2_4_1_Web_Server.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/Web_Server.md
diff --git a/docs/guidebook/en/3_2_1_gRPC.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/gRPC.md
similarity index 97%
rename from docs/guidebook/en/3_2_1_gRPC.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/gRPC.md
index 68f2d20d..a7c6a9e5 100644
--- a/docs/guidebook/en/3_2_1_gRPC.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Service/gRPC.md
@@ -56,7 +56,7 @@ message AgentResultRequest {
}
```
\
-Similar to the [Web API](2_4_1_Web_Api.md), the gRPC service includes three interfaces:
+Similar to the [Web API](Web_Api.md), the gRPC service includes three interfaces:
```text
service AgentUniverseService {
rpc service_run(AgentServiceRequest) returns (AgentServiceResponse);
diff --git a/docs/guidebook/en/3_3_2_ChromaDB.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/ChromaDB.md
similarity index 90%
rename from docs/guidebook/en/3_3_2_ChromaDB.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/ChromaDB.md
index 44526af0..5820c1c2 100644
--- a/docs/guidebook/en/3_3_2_ChromaDB.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/ChromaDB.md
@@ -20,4 +20,4 @@ metadata:
- similarity_top_k: The number of most similar results returned in similarity search.
### Usage
-[Knowledge_Define_And_Use](2_2_4_Knowledge_Define_And_Use.md)
\ No newline at end of file
+[Knowledge_Define_And_Use](../../../In-Depth_Guides/Tutorials/Knowledge/Knowledge_Define_And_Use.md)
\ No newline at end of file
diff --git a/docs/guidebook/en/3_3_1_Milvus.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/Milvus.md
similarity index 95%
rename from docs/guidebook/en/3_3_1_Milvus.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/Milvus.md
index 1bb8bee9..76e78026 100644
--- a/docs/guidebook/en/3_3_1_Milvus.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/Milvus.md
@@ -47,5 +47,5 @@ metadata:
- embedding_model: The model used to generate embedding vectors, specified here as dashscope_embedding.
- similarity_top_k: The number of most similar results returned in similarity search.
### Usage
-[Knowledge_Define_And_Use](2_2_4_Knowledge_Define_And_Use.md)
+[Knowledge_Define_And_Use](../../../In-Depth_Guides/Tutorials/Knowledge/Knowledge_Define_And_Use.md)
diff --git a/docs/guidebook/en/2_3_1_SQLDB_WRAPPER.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/SQLDB_WRAPPER.md
similarity index 100%
rename from docs/guidebook/en/2_3_1_SQLDB_WRAPPER.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/SQLDB_WRAPPER.md
diff --git a/docs/guidebook/en/3_3_3_Sqlite.md b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/Sqlite.md
similarity index 83%
rename from docs/guidebook/en/3_3_3_Sqlite.md
rename to docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/Sqlite.md
index 9007a574..ba4924b7 100644
--- a/docs/guidebook/en/3_3_3_Sqlite.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tech_Capabilities/Storage/Sqlite.md
@@ -4,7 +4,7 @@ The SQLite component in the Store module is used to store the text content of Do
### How to Configure the SQLite Component
-You can use ChromaDB to store and query knowledge in the [Knowledge Components](2_2_4_Knowledge.md). You can create a storage component using SQLite with the following configuration:
+You can use ChromaDB to store and query knowledge in the [Knowledge Components](../../../In-Depth_Guides/Tutorials/Knowledge/Knowledge.md). You can create a storage component using SQLite with the following configuration:
```yaml
name: 'sqlite_store'
description: 'a store based on sqlite'
@@ -25,4 +25,4 @@ metadata:
- similarity_top_k: Return top k similar documents based on bm25 score.
### Usage
-[Knowledge_Define_And_Use](2_2_4_Knowledge_Define_And_Use.md)
\ No newline at end of file
+[Knowledge_Define_And_Use](../../../In-Depth_Guides/Tutorials/Knowledge/Knowledge_Define_And_Use.md)
\ No newline at end of file
diff --git a/docs/guidebook/en/2_2_1_Agent.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent.md
similarity index 99%
rename from docs/guidebook/en/2_2_1_Agent.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent.md
index 8f8f0374..0b6eb245 100644
--- a/docs/guidebook/en/2_2_1_Agent.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent.md
@@ -2,7 +2,7 @@
An agent is capable of autonomously acting to achieve goals set by humans, with abilities in learning, reasoning, decision-making, and execution. It accomplishes objectives through steps such as task decomposition, using tools and knowledge, and progress control, and then independently concludes its work. Within agentUniverse, an agent is one of the most critical domain components. It integrates a series of other domain components, including tools, knowledge, and plans, into a cohesive whole, ultimately completing the tasks assigned to it by people.
The performance of an agent directly impacts the strength of application service capabilities. In complex service scenarios, often one or multiple outstanding agents are required to complete tasks. In agentUniverse, drawing from the achievements of industry and academia as well as practical experience in industry implementation, the following definition for agents is established, as shown in the figure.
-
+
Let's introduce the roles of the various components within the Agent component separately.
diff --git a/docs/guidebook/en/2_2_1_Agent_Create_And_Use.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent_Create_And_Use.md
similarity index 97%
rename from docs/guidebook/en/2_2_1_Agent_Create_And_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent_Create_And_Use.md
index 9bfc764f..5b833d27 100644
--- a/docs/guidebook/en/2_2_1_Agent_Create_And_Use.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent_Create_And_Use.md
@@ -1,5 +1,5 @@
# How to create agents.
-You might have already learned how to quickly create an agent in the [Quick Start](1_3_Quick_Start.md) chapter, or grasped the important components of an agent in the [Principles of Agents](2_2_1_Agent.md). In this section, we will further elaborate on how to create an agent in detail.
+You might have already learned how to quickly create an agent in the [Quick Start](../../../Get_Start/Quick_Start.md) chapter, or grasped the important components of an agent in the [Principles of Agents](../../../In-Depth_Guides/Tutorials/Agent/Agent.md). In this section, we will further elaborate on how to create an agent in detail.
Based on the design features of the agentUniverse domain components, creating an agent consists of two parts during the creation process.
* agent_xx.yaml
@@ -24,7 +24,7 @@ We will provide detailed descriptions of each component in the configuration.
* `name`: name of LLM
* `model_name`: model_name of LLM
- You can choose any existing LLM or connect to any LLM of your choice. We will not elaborate on this part here; you can refer to the [LLM section](2_2_2_LLM.md) for more details.
+ You can choose any existing LLM or connect to any LLM of your choice. We will not elaborate on this part here; you can refer to the [LLM section](../../../In-Depth_Guides/Tutorials/LLM/LLM.md) for more details.
### Setting the agent's plan
**`plan` - plan of agent**
@@ -41,7 +41,7 @@ We will provide detailed descriptions of each component in the configuration.
\- tool_name_b
\- tool_name_c
- You can choose any existing Tool or connect to any Tool of your choice. We will not elaborate on this part here; you can refer to the [Tool section](2_2_3_Tool.md) for more details.
+ You can choose any existing Tool or connect to any Tool of your choice. We will not elaborate on this part here; you can refer to the [Tool section](../../../In-Depth_Guides/Tutorials/Tool/Tool.md) for more details.
* `Knowledge` : Knowledge available for the agent's use.
* knowledge_name_list，list of knowledge names, for example:
@@ -401,7 +401,7 @@ if __name__ == '__main__':
## Solution 2: Utilize the service capabilities of agent_serve
-The agentUniverse offers a variety of standard web serve capabilities, along with standard HTTP and RPC protocols. You can further refer to the documentation sections on [Service Registration and Usage](2_4_1_Service_Registration_and_Usage.md) and [Web_Server](2_4_1_Web_Server.md).
+The agentUniverse offers a variety of standard web serve capabilities, along with standard HTTP and RPC protocols. You can further refer to the documentation sections on [Service Registration and Usage](../../../In-Depth_Guides/Tech_Capabilities/Service/Service_Registration_and_Usage.md) and [Web_Server](../../../In-Depth_Guides/Tech_Capabilities/Service/Web_Server.md).
# Learn more about agents
The agents provided by the framework can be found under the `agentuniverse.agent.default` package path. You can further explore the corresponding code or learn more about them in our extension component introduction section.
diff --git a/docs/guidebook/en/2_2_1_Agent_Related_Domain_Objects.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent_Related_Domain_Objects.md
similarity index 81%
rename from docs/guidebook/en/2_2_1_Agent_Related_Domain_Objects.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent_Related_Domain_Objects.md
index 60f3aeae..8fad2df4 100644
--- a/docs/guidebook/en/2_2_1_Agent_Related_Domain_Objects.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Agent/Agent_Related_Domain_Objects.md
@@ -1,5 +1,5 @@
# Agent and Related Domain Objects
-In this chapter, we will highlight agent and related core domain objects. We have omitted their corresponding code parts. If you wish to learn more, please read the [API Reference](4_1_API_Reference.md) Section.
+In this chapter, we will highlight agent and related core domain objects. We have omitted their corresponding code parts. If you wish to learn more, please read the [API Reference](../../../In-Depth_Guides/Tech_Capabilities/Others/API_Reference.md) Section.
## Agent Base Class
Package path: `agentuniverse.agent.agent.Agent`
diff --git a/docs/guidebook/en/8_1_1_data_autonomous_agent.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Data_Autonomous_Agent.md
similarity index 76%
rename from docs/guidebook/en/8_1_1_data_autonomous_agent.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Data_Autonomous_Agent.md
index 2880a1c7..406697de 100644
--- a/docs/guidebook/en/8_1_1_data_autonomous_agent.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Data_Autonomous_Agent.md
@@ -16,7 +16,7 @@ By utilizing a complete set of data autonomy capabilities, you can easily unders
It needs to be particularly emphasized that the scores in the entire evaluation report are reference values. In the actual production environment, we will conduct a comprehensive comparison of scores from multiple rounds to distinguish the effectiveness of the agent.
## DataAgent Flowchart
-
+
- data_agent consists of two parts. **dataset_build_agent** is responsible for automating batch execution of multiple rounds of agent invocation and producing evaluation datasets.
- **dataset_eval_agent** is responsible for automating the multidimensional evaluation of the dataset and generating evaluation report.
@@ -46,9 +46,9 @@ metadata:
module: 'sample_standard_app.app.core.agent.data_agent_case.data_agent'
class: 'DataAgent'
```
-[data_agent sample configuration file](../../../sample_standard_app/app/core/agent/data_agent_case/data_agent.yaml)
+[data_agent sample configuration file](../../../../../sample_standard_app/app/core/agent/data_agent_case/data_agent.yaml)
-[data_agent sample python file](../../../sample_standard_app/app/core/agent/data_agent_case/data_agent.py)
+[data_agent sample python file](../../../../../sample_standard_app/app/core/agent/data_agent_case/data_agent.py)
### Step3 Configure the agent for producing the evaluation dataset.
Use the **dataset_build_agent** configured in step2 `dataset_builder`, and the following is the configuration file of dataset_build_agent. In addition to the basic configuration of the agent, the configuration file mainly includes two important items: `candidate` configures the name of the agent to be evaluated (for example, to evaluate the effectiveness of demo_rag_agent, candidate is configured as demo_rag_agent), and `concurrency_level` configures the level of concurrency when executing batch agent invocation (for example, setting it to 5 represents calling the candidate agent concurrently with 5).
@@ -66,9 +66,9 @@ metadata:
module: 'sample_standard_app.app.core.agent.data_agent_case.dataset_build_agent'
class: 'DatasetBuildAgent'
```
-[dataset_build_agent sample configuration file](../../../sample_standard_app/app/core/agent/data_agent_case/dataset_build_agent.yaml)
+[dataset_build_agent sample configuration file](../../../../../sample_standard_app/app/core/agent/data_agent_case/dataset_build_agent.yaml)
-[dataset_build_agent sample python file](../../../sample_standard_app/app/core/agent/data_agent_case/dataset_build_agent.py)
+[dataset_build_agent sample python file](../../../../../sample_standard_app/app/core/agent/data_agent_case/dataset_build_agent.py)
### Step4 Configure the agent for dataset evaluation and annotation
Use the **dataset_eval_agent** configured in step2 `dataset_evaluator`, and the following is the configuration file of dataset_eval_agent. In addition to the basic configuration of the agent, the configuration file mainly includes two important items: `llm_model` configures the agent model, and `max_eval_lines` configures the number of evaluation data lines (for example, setting it to 10 means only evaluate the first 10 rows of data, to avoid global evaluation and the consumption of a large number of tokens).
@@ -88,12 +88,12 @@ metadata:
module: 'sample_standard_app.app.core.agent.data_agent_case.dataset_eval_agent'
class: 'DatasetEvalAgent'
```
-[dataset_eval_agent sample configuration file](../../../sample_standard_app/app/core/agent/data_agent_case/dataset_eval_agent.yaml)
+[dataset_eval_agent sample configuration file](../../../../../sample_standard_app/app/core/agent/data_agent_case/dataset_eval_agent.yaml)
-[dataset_eval_agent sample python file](../../../sample_standard_app/app/core/agent/data_agent_case/dataset_eval_agent.py)
+[dataset_eval_agent sample python file](../../../../../sample_standard_app/app/core/agent/data_agent_case/dataset_eval_agent.py)
### step5 Run DataAgent
-Through the [dataAgent code entry](../../../sample_standard_app/app/examples/data_agent.py), configure two parameters: `queryset_path` representing the path to the queryset, and `turn` representing the total number of rounds for the queryset execution, to start the dataAgent with one click.
+Through the [dataAgent code entry](../../../../../sample_standard_app/app/examples/data_agent.py), configure two parameters: `queryset_path` representing the path to the queryset, and `turn` representing the total number of rounds for the queryset execution, to start the dataAgent with one click.
Tips: please configure the queryset and specific evaluation rows reasonably to avoid excessive computational and token consumption.
@@ -106,9 +106,9 @@ As shown in the figure below:
- query: agent question
- answer: agent answer
-
+
-[dataAgent sample evaluation dataset](../../../sample_standard_app/app/examples/data/dataset_turn_1_2024-07-10-15-06-24.jsonl)
+[dataAgent sample evaluation dataset](../../../../../sample_standard_app/app/examples/data/dataset_turn_1_2024-07-10-15-06-24.jsonl)
### Complete Evaluation Results
@@ -122,9 +122,9 @@ As shown in the figure below:
- Relevance Score: represents the relevance of the agent answer to the question, the higher the score, the more relevant (full score is 5, score range 0-5).
- Relevance Suggestion: represents issues and suggestions for improvement in the relevance dimension.
- More dimensions Score/Suggestion: similar to the Relevance dimension.
-
+
-[dataAgent sample eval result](../../../sample_standard_app/app/examples/data/eval_result_turn_1_2024-07-10-15-06-24.xlsx)
+[dataAgent sample eval result](../../../../../sample_standard_app/app/examples/data/eval_result_turn_1_2024-07-10-15-06-24.xlsx)
@@ -137,33 +137,33 @@ As shown in the figure below:
- Relevance Avg Score: The sum of the relevance scores of all data in a single round of the dataset / the amount of data in the dataset (full score is 5, score range 0-5).
- More dimensions Avg Score: similar to the Relevance dimension.
-
+
-[dataAgent sample evaluation report](../../../sample_standard_app/app/examples/data/eval_report_2024-07-10-15-06-24.xlsx)
+[dataAgent sample evaluation report](../../../../../sample_standard_app/app/examples/data/eval_report_2024-07-10-15-06-24.xlsx)
### Comparative Experiment
Adjust the llm model in demo_rag_agent within aU from the previous `qwen1.5-72b-chat` to `qwen1.5-7b-chat`, and after evaluation by dataAgent, the comprehensive evaluation reports are as follows:
The following figure is the comprehensive evaluation report produced by the data autonomous agent when the model is qwen1.5-7b-chat:
-
+
The following figure is the comprehensive evaluation report produced by the data autonomous agent when the model is qwen1.5-72b-chat:
-
+
Comparing the two comprehensive evaluation reports, it can be observed that after the agent llm model was changed from qwen1.5-7b-chat to qwen1.5-72b-chat, there was a significant increase in the scores across all dimensions in multiple rounds. This method can quickly distinguish the difference in agent effects after the agent configuration was changed.
## DataAgent Detailed Description
### data_agent
-- [configuration file](../../../sample_standard_app/app/core/agent/data_agent_case/data_agent.yaml)
-- [agent file](../../../sample_standard_app/app/core/agent/data_agent_case/data_agent.py)
+- [configuration file](../../../../../sample_standard_app/app/core/agent/data_agent_case/data_agent.yaml)
+- [agent file](../../../../../sample_standard_app/app/core/agent/data_agent_case/data_agent.py)
### dataset_build_agent
-- [configuration file](../../../sample_standard_app/app/core/agent/data_agent_case/dataset_build_agent.yaml)
-- [agent file](../../../sample_standard_app/app/core/agent/data_agent_case/dataset_build_agent.py)
+- [configuration file](../../../../../sample_standard_app/app/core/agent/data_agent_case/dataset_build_agent.yaml)
+- [agent file](../../../../../sample_standard_app/app/core/agent/data_agent_case/dataset_build_agent.py)
- The evaluation data produced by dataset_build_agent is stored locally in jsonl format (the jsonl file name is dataset_turn_{i}_{date}, `i` represents the round, and `date` represents the generation time)
### dataset_eval_agent
-- [configuration file](../../../sample_standard_app/app/core/agent/data_agent_case/dataset_eval_agent.yaml)
-- [agent file](../../../sample_standard_app/app/core/agent/data_agent_case/dataset_eval_agent.py)
-- [prompt file](../../../sample_standard_app/app/core/prompt/dataset_eval_agent_en.yaml)：agentUniverse currently opens six agent evaluation dimensions that are validated in the industry (the MVP version does not open **comprehensive dimension**. The current comprehensive evaluation standard is biased towards the financial field, so it is not mentioned in the open source community)
+- [configuration file](../../../../../sample_standard_app/app/core/agent/data_agent_case/dataset_eval_agent.yaml)
+- [agent file](../../../../../sample_standard_app/app/core/agent/data_agent_case/dataset_eval_agent.py)
+- [prompt file](../../../../../sample_standard_app/app/core/prompt/dataset_eval_agent_en.yaml)：agentUniverse currently opens six agent evaluation dimensions that are validated in the industry (the MVP version does not open **comprehensive dimension**. The current comprehensive evaluation standard is biased towards the financial field, so it is not mentioned in the open source community)
- The **complete evaluation results** produced by dataset_eval_agent are stored locally in Excel format (the file name is eval_result_turn_{i}_{date}, `i` represents the round, and `date` represents the generation time)
- The **comprehensive evaluation report** of dataset_eval_a_agent production is stored locally in Excel format (the file name is eval_report_{date}, and date represents the generation time)
\ No newline at end of file
diff --git a/docs/guidebook/en/2_2_Domain_Component_Principles.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Domain_Component_Principles.md
similarity index 100%
rename from docs/guidebook/en/2_2_Domain_Component_Principles.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Domain_Component_Principles.md
diff --git a/docs/guidebook/en/2_2_4_DocProcessor.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/DocProcessor.md
similarity index 91%
rename from docs/guidebook/en/2_2_4_DocProcessor.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/DocProcessor.md
index 195f1c73..a6e3beb8 100644
--- a/docs/guidebook/en/2_2_4_DocProcessor.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/DocProcessor.md
@@ -82,7 +82,7 @@ doc_processor = ['sample_standard_app.app.core.doc_processor']
## The following DocProcessors are built into agentUniverse:
-### [CharacterTextSplitter](../../../agentuniverse/agent/action/knowledge/doc_processor/character_text_splitter.yaml)
+### [CharacterTextSplitter](../../../../../../agentuniverse/agent/action/knowledge/doc_processor/character_text_splitter.yaml)
This component splits the original text based on the number of characters.
The component definition file is as follows:
```yaml
@@ -100,7 +100,7 @@ metadata:
- chunk_overlap: The length of the overlapping part between adjacent chunks.
- separators: The specified separator.
-### [TokenTextSplitter](../../../agentuniverse/agent/action/knowledge/doc_processor/character_text_splitter.yaml)
+### [TokenTextSplitter](../../../../../../agentuniverse/agent/action/knowledge/doc_processor/character_text_splitter.yaml)
This component splits the text based on the specified tokenizer, splitting the text into multiple segments according to the set chunk_size and chunk_overlap, where each segment contains a specified number of tokens.
The component definition file is as follows:
@@ -120,7 +120,7 @@ metadata:
- chunk_overlap: The number of overlapping tokens between adjacent chunks.
- tokenizer: The specified tokenizer used to split the text into tokens.
-### [RecursiveCharacterTextSplitter](../../../agentuniverse/agent/action/knowledge/doc_processor/recursive_character_text_splitter.yaml)
+### [RecursiveCharacterTextSplitter](../../../../../../agentuniverse/agent/action/knowledge/doc_processor/recursive_character_text_splitter.yaml)
This component recursively splits the original text based on the specified separators. It first tries to split the text using the separator with the highest priority. If it fails to meet the chunk_size requirement, it will recursively use the next separator until the text is successfully split.
@@ -142,7 +142,7 @@ metadata:
- chunk_overlap: The length of the overlapping part between adjacent chunks.
- separators: A list of specified separators. The component will try to split using the separators in order. If the first separator cannot meet the conditions, it will recursively use the next separator.
-### [JiebaKeywordExtractor](../../../agentuniverse/agent/action/knowledge/doc_processor/jieba_keyword_extractor.yaml)
+### [JiebaKeywordExtractor](../../../../../../agentuniverse/agent/action/knowledge/doc_processor/jieba_keyword_extractor.yaml)
This component uses the Jieba segmentation library to extract keywords from the text. It can extract the most important keywords based on the set top_k parameter, which can be used later to build an inverted index.
The component definition file is as follows:
```yaml
@@ -156,7 +156,7 @@ metadata:
```
- top_k: The number of keywords to extract from the text, meaning the top_k keywords will be extracted.
-### [DashscopeReranker](../../../agentuniverse/agent/action/knowledge/doc_processor/dashscope_reranker.yaml)
+### [DashscopeReranker](../../../../../../agentuniverse/agent/action/knowledge/doc_processor/dashscope_reranker.yaml)
This component uses the DashScope API to rerank texts, sorting the content recalled by the Store based on the relevance to the Query content.
diff --git a/docs/guidebook/en/2_2_4_Knowledge.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge.md
similarity index 97%
rename from docs/guidebook/en/2_2_4_Knowledge.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge.md
index 9622389b..af3bbea4 100644
--- a/docs/guidebook/en/2_2_4_Knowledge.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge.md
@@ -10,7 +10,7 @@ agentUniverse defines a standard knowledge format, which includes various knowle
## Knowledge Structure
In agentUniverse, the overall architecture of Knowledge and its related domain objects is illustrated in the following diagram:
-
+
The upper part of the diagram, from Reader to Store, represents the Knowledge injection process, while the lower part represents the Knowledge query process.
### Knowledge Injection Process
diff --git a/docs/guidebook/en/2_2_4_Knowledge_Define_And_Use.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge_Define_And_Use.md
similarity index 93%
rename from docs/guidebook/en/2_2_4_Knowledge_Define_And_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge_Define_And_Use.md
index 283bbbc1..3603f70d 100644
--- a/docs/guidebook/en/2_2_4_Knowledge_Define_And_Use.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge_Define_And_Use.md
@@ -39,7 +39,7 @@ metadata:
## Creating Knowledge Domain Behavior Definition - knowledge_xx.py
agentUniverse provides a standard Knowledge class that you can use directly in the YAML definition file or extend by overriding some of its methods.
-### [Knowledge Class Definition:](../../../agentuniverse/agent/action/knowledge/knowledge.py)
+### [Knowledge Class Definition:](../../../../../../agentuniverse/agent/action/knowledge/knowledge.py)
- _load_data(self, *args: Any, **kwargs: Any) -> List[Document]
: Loads the data source and selects an appropriate reader based on the type of data source (file or URL) to load the document data.
@@ -80,7 +80,7 @@ knowledge = ['sample_standard_app.app.core.knowledge']
# How to Use the Knowledge Component
## Configuring Knowledge in an Agent
-Based on the content in [Creating and Using Agents](2_2_1_Agent_Create_And_Use.md), you can set any created knowledge under the knowledge action in the agent.
+Based on the content in [Creating and Using Agents](../../../In-Depth_Guides/Tutorials/Agent/Agent_Create_And_Use.md), you can set any created knowledge under the knowledge action in the agent.
## Using the Knowledge Manager
You can obtain the Knowledge instance corresponding to the name via the `.get_instance_obj(xx_knowledge_name)` method in the Knowledge Manager, and call it using the `query_knowledge` method.
@@ -94,4 +94,4 @@ knowledge.query_knowledge()
```
## Learn More About Existing Knowledge
-[Legal Consultation Case](7_1_1_Legal_Consultation_Case.md)
\ No newline at end of file
+[Legal Consultation Case](../../../Examples/Legal_Advice.md)
\ No newline at end of file
diff --git a/docs/guidebook/en/2_2_4_Knowledge_Related_Domain_Objects.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge_Related_Domain_Objects.md
similarity index 72%
rename from docs/guidebook/en/2_2_4_Knowledge_Related_Domain_Objects.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge_Related_Domain_Objects.md
index abd510af..17c3c9ae 100644
--- a/docs/guidebook/en/2_2_4_Knowledge_Related_Domain_Objects.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Knowledge_Related_Domain_Objects.md
@@ -4,25 +4,25 @@ In this section, we will list the knowledge and its related core domain objects.
### Knowledge
Package Path: `agentuniverse.agent.action.knowledge.knowledge.Knowledge`
-Documentation Link: [Knowledge](2_2_4_知识定义与使用.md)
+Documentation Link: [Knowledge](Knowledge.md)
### Reader
Package Path: `agentuniverse.agent.action.knowledge.reader.reader.Reader`
-Documentation Link: [Reader](2_2_4_Reader.md)
+Documentation Link: [Reader](Reader.md)
### DocProcessor
Package Path: `agentuniverse.agent.action.knowledge.doc_processor.doc_processor.DocProcessor`
-Documentation Link: [DocProcessor](2_2_4_DocProcessor.md)
+Documentation Link: [DocProcessor](DocProcessor.md)
### Store
Package Path: `agentuniverse.agent.action.knowledge.store.store.Store`
-Documentation Link: [Store](2_2_4_Store.md)
+Documentation Link: [Store](Store.md)
The following new components are involved in this process:
### QueryParaphraser
Package Path: `agentuniverse.agent.action.knowledge.reader.reader.Reader`
-Documentation Link: [QueryParaphraser](2_2_4_QueryParaphraser.md)
+Documentation Link: [QueryParaphraser](QueryParaphraser.md)
### RagRouter
Package Path: `agentuniverse.agent.action.knowledge.reader.reader.Reader`
-Documentation Link: [RagRouter](2_2_4_RagRouter.md)
+Documentation Link: [RagRouter](RagRouter.md)
diff --git a/docs/guidebook/en/2_2_4_QueryParaphraser.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/QueryParaphraser.md
similarity index 96%
rename from docs/guidebook/en/2_2_4_QueryParaphraser.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/QueryParaphraser.md
index 3e9fdaea..930f9d38 100644
--- a/docs/guidebook/en/2_2_4_QueryParaphraser.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/QueryParaphraser.md
@@ -71,7 +71,7 @@ query_paraphraser = ['sample_standard_app.app.core.query_paraphraser']
```
## The following QueryParaphraser are built into agentUniverse:
-### [query_keyword_extractor](../../../agentuniverse/agent/action/knowledge/query_paraphraser/query_keyword_extractor.yaml)
+### [query_keyword_extractor](../../../../../../agentuniverse/agent/action/knowledge/query_paraphraser/query_keyword_extractor.yaml)
This component extracts keywords from the original text in the Query and saves them into the keywords field of the Query.
The component definition file is as follows:
```yaml
diff --git a/docs/guidebook/en/2_2_4_RagRouter.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/RagRouter.md
similarity index 94%
rename from docs/guidebook/en/2_2_4_RagRouter.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/RagRouter.md
index 58ddfeb3..213f6bae 100644
--- a/docs/guidebook/en/2_2_4_RagRouter.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/RagRouter.md
@@ -49,7 +49,7 @@ rag_router = ['sample_standard_app.app.core.rag_router']
## The following RagRouters are built into agentUniverse:
-### [base_router](../../../agentuniverse/agent/action/knowledge/rag_router/base_router.yaml)
+### [base_router](../../../../../../agentuniverse/agent/action/knowledge/rag_router/base_router.yaml)
This component's primary function is to route the query to all the stores in the system, ensuring that the query can find answers in all possible resources. It is also the default RagRouter in Knowledge.
```yaml
name: 'base_router'
@@ -60,7 +60,7 @@ metadata:
class: 'BaseRouter'
```
-### [nlu_rag_router](../../../agentuniverse/agent/action/knowledge/rag_router/nlu_rag_router.py)
+### [nlu_rag_router](../../../../../../agentuniverse/agent/action/knowledge/rag_router/nlu_rag_router.py)
This component selects the most relevant stores by analyzing the correlation between the description of all stores and the original query text using a configured language model (LLM).
Users need to create their own YAML file for this component, with a format similar to the following:
diff --git a/docs/guidebook/en/2_2_4_Reader.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Reader.md
similarity index 72%
rename from docs/guidebook/en/2_2_4_Reader.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Reader.md
index c677e315..72e8c122 100644
--- a/docs/guidebook/en/2_2_4_Reader.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Reader.md
@@ -48,8 +48,8 @@ reader = ['sample_standard_app.app.core.reader']
```
## Prebuilt Readers in agentUniverse:
-- [default_docx_reader](../../../agentuniverse/agent/action/knowledge/reader/file/docx_reader.yaml): Reads text content from local Docx files.
-- [default_pdf_reader](../../../agentuniverse/agent/action/knowledge/reader/file/pdf_reader.yaml): Reads text content from local PDF files.
-- [default_pptx_reader](../../../agentuniverse/agent/action/knowledge/reader/file/pptx_reader.yaml): Reads text content from local PPTX files.
-- [default_txt_reader](../../../agentuniverse/agent/action/knowledge/reader/file/txt_reader.yaml): Reads text content from TXT files.
-- [default_web_pdf_reader](../../../agentuniverse/agent/action/knowledge/reader/file/web_pdf_reader.yaml): Reads text content from PDF files found on the web.
\ No newline at end of file
+- [default_docx_reader](../../../../../../agentuniverse/agent/action/knowledge/reader/file/docx_reader.yaml): Reads text content from local Docx files.
+- [default_pdf_reader](../../../../../../agentuniverse/agent/action/knowledge/reader/file/pdf_reader.yaml): Reads text content from local PDF files.
+- [default_pptx_reader](../../../../../../agentuniverse/agent/action/knowledge/reader/file/pptx_reader.yaml): Reads text content from local PPTX files.
+- [default_txt_reader](../../../../../../agentuniverse/agent/action/knowledge/reader/file/txt_reader.yaml): Reads text content from TXT files.
+- [default_web_pdf_reader](../../../../../../agentuniverse/agent/action/knowledge/reader/file/web_pdf_reader.yaml): Reads text content from PDF files found on the web.
\ No newline at end of file
diff --git a/docs/guidebook/en/2_2_4_Store.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Store.md
similarity index 87%
rename from docs/guidebook/en/2_2_4_Store.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Store.md
index 6618226b..328f9e4b 100644
--- a/docs/guidebook/en/2_2_4_Store.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Knowledge/Store.md
@@ -52,7 +52,7 @@ class Store(ComponentBase):
def update_document(self, documents: List[Document], **kwargs):
raise NotImplementedError
```
-- `_new_client` and `_new_async_client` are used to create database connections. These methods are added to the [post_fork](2_4_1_Web_Server.md) execution list during the component registration phase to ensure that the database connections created are independent in Gunicorn mode child processes.
+- `_new_client` and `_new_async_client` are used to create database connections. These methods are added to the [post_fork](../../../In-Depth_Guides/Tech_Capabilities/Service/Web_Server.md) execution list during the component registration phase to ensure that the database connections created are independent in Gunicorn mode child processes.
- The `query`function is called by the knowledge component during a query, responsible for searching the store for relevant content based on the passed Query instance and returning the results in the form of Document objects.
- The `Store` also includes CRUD (Create, Read, Update, Delete) operations for Document data, serving as the management interface for knowledge storage.
@@ -77,6 +77,6 @@ store = ['sample_standard_app.app.core.store']
```
## Prebuilt Stores in agentUniverse:
-- [Chroma](3_3_2_ChromaDB.md)
-- [Milvus](3_3_1_Milvus.md)
-- [Sqlite](3_3_3_Sqlite.md)
\ No newline at end of file
+- [Chroma](../../../In-Depth_Guides/Tech_Capabilities/Storage/ChromaDB.md)
+- [Milvus](../../../In-Depth_Guides/Tech_Capabilities/Storage/Milvus.md)
+- [Sqlite](../../../In-Depth_Guides/Tech_Capabilities/Storage/Sqlite.md)
\ No newline at end of file
diff --git a/docs/guidebook/en/2_2_2_LLM.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/LLM/LLM.md
similarity index 100%
rename from docs/guidebook/en/2_2_2_LLM.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/LLM/LLM.md
diff --git a/docs/guidebook/en/2_2_2_LLM_Related_Domain_Objects.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/LLM/LLM_Related_Domain_Objects.md
similarity index 74%
rename from docs/guidebook/en/2_2_2_LLM_Related_Domain_Objects.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/LLM/LLM_Related_Domain_Objects.md
index 1627b449..170adc52 100644
--- a/docs/guidebook/en/2_2_2_LLM_Related_Domain_Objects.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/LLM/LLM_Related_Domain_Objects.md
@@ -1,5 +1,5 @@
# LLM and Related Domain Objects
-In this chapter, we will highlight LLM and related core domain objects. We have omitted their corresponding code parts. If you wish to learn more, please read the [API Reference](4_1_API_Reference.md) Section.
+In this chapter, we will highlight LLM and related core domain objects. We have omitted their corresponding code parts. If you wish to learn more, please read the [API Reference](../../../In-Depth_Guides/Tech_Capabilities/Others/API_Reference.md) Section.
## LLM Base Class
Package path: `agentuniverse.llm.llm.LLM`
diff --git a/docs/guidebook/en/2_2_2_LLM_component_define_and_usage.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/LLM/LLM_component_define_and_usage.md
similarity index 99%
rename from docs/guidebook/en/2_2_2_LLM_component_define_and_usage.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/LLM/LLM_component_define_and_usage.md
index bf49694f..22bd5c89 100644
--- a/docs/guidebook/en/2_2_2_LLM_component_define_and_usage.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/LLM/LLM_component_define_and_usage.md
@@ -484,7 +484,7 @@ You can find more LLM metadata in the [Understanding More Existing LLM Component
# How to Use Model LLM Components
## Configure for use in an Agent
-You can set up any LLM you have created in the llm_model of your agent according to the contents of [Agent Creation and Usage section](2_2_1_Agent_Create_And_Use.md).
+You can set up any LLM you have created in the llm_model of your agent according to the contents of [Agent Creation and Usage section](../Agent/Agent_Create_And_Use.md).
Refer to the example: `demo_multillm_agent`, with the specific file path being `sample_standard_app/app/core/agent/rag_agent_case/demo_multillm_agent.yaml`.
diff --git a/docs/guidebook/en/2_2_5_Memory.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Memory/Memory.md
similarity index 100%
rename from docs/guidebook/en/2_2_5_Memory.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Memory/Memory.md
diff --git a/docs/guidebook/en/2_2_5_Memory_Define_And_Use.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Memory/Memory_Define_And_Use.md
similarity index 91%
rename from docs/guidebook/en/2_2_5_Memory_Define_And_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Memory/Memory_Define_And_Use.md
index 63ac2b36..e7ae446f 100644
--- a/docs/guidebook/en/2_2_5_Memory_Define_And_Use.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Memory/Memory_Define_And_Use.md
@@ -3,7 +3,7 @@ The current version of the agentUniverse memory component includes default memor
# How to Use the Memory Component
## Configuring Memory in the Agent
-Following the [Creating and Using Agents](2_2_1_Agent_Create_And_Use.md) guide, you can set up your memory instance in the agent's memory section. The current version of aU includes a default memory type, which you can configure as follows:
+Following the [Creating and Using Agents](../Agent/Agent_Create_And_Use.md) guide, you can set up your memory instance in the agent's memory section. The current version of aU includes a default memory type, which you can configure as follows:
```yaml
info:
name: 'demo_rag_agent'
diff --git a/docs/guidebook/en/2_2_5_Memory_Related_Domain_Objects.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Memory/Memory_Related_Domain_Objects.md
similarity index 80%
rename from docs/guidebook/en/2_2_5_Memory_Related_Domain_Objects.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Memory/Memory_Related_Domain_Objects.md
index 8c18ce35..0deddb72 100644
--- a/docs/guidebook/en/2_2_5_Memory_Related_Domain_Objects.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Memory/Memory_Related_Domain_Objects.md
@@ -1,5 +1,5 @@
# Memory and Related Domain Objects
-In this chapter, we will focus on listing the Memory and related core domain objects. We have omitted their corresponding code parts. If you would like to learn more, please refer to the [API Reference Section](4_1_API_Reference.md).
+In this chapter, we will focus on listing the Memory and related core domain objects. We have omitted their corresponding code parts. If you would like to learn more, please refer to the [API Reference Section](../../../In-Depth_Guides/Tech_Capabilities/Others/API_Reference.md).
## Memory Base Class
Package Path:`agentuniverse.agent.memory.memory.Memory`
diff --git a/docs/guidebook/en/2_2_6_Planner.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Plan/Planner.md
similarity index 100%
rename from docs/guidebook/en/2_2_6_Planner.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Plan/Planner.md
diff --git a/docs/guidebook/en/2_2_6_Planner_Define_And_Use.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Plan/Planner_Define_And_Use.md
similarity index 96%
rename from docs/guidebook/en/2_2_6_Planner_Define_And_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Plan/Planner_Define_And_Use.md
index 6979676b..d387d631 100644
--- a/docs/guidebook/en/2_2_6_Planner_Define_And_Use.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Plan/Planner_Define_And_Use.md
@@ -184,7 +184,7 @@ planner = ['sample_standard_app.app.core.planner']
# How to Use the Planner Component
## Configuring Use in the Agent
-Following the [Creating and Using Agents guide](2_2_1_Agent_Create_And_Use.md), you can set up any created Planner component in the agent's planner section. Refer to the example: `demo_rag_agent`, with the specific file path `sample_standard_app/app/core/agent/rag_agent_case/demo_rag_agent.yaml`.
+Following the [Creating and Using Agents guide](../Agent/Agent_Create_And_Use.md), you can set up any created Planner component in the agent's planner section. Refer to the example: `demo_rag_agent`, with the specific file path `sample_standard_app/app/core/agent/rag_agent_case/demo_rag_agent.yaml`.
## Using the Planner Manager
You can get the Planner instance corresponding to its name using the `.get_instance_obj(xx_planner_name)` method in the Planner Manager and call it using the `invoke` method.
diff --git a/docs/guidebook/en/2_2_6_Planner_Related_Domain_Objects.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Plan/Planner_Related_Domain_Objects.md
similarity index 82%
rename from docs/guidebook/en/2_2_6_Planner_Related_Domain_Objects.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Plan/Planner_Related_Domain_Objects.md
index 5e75afc1..0e48aee9 100644
--- a/docs/guidebook/en/2_2_6_Planner_Related_Domain_Objects.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Plan/Planner_Related_Domain_Objects.md
@@ -1,5 +1,5 @@
# Planner and Related Domain Objects
-In this chapter, we will focus on listing the Planner and related core domain objects. We have omitted their corresponding code parts. If you would like to learn more, please refer to the [API Reference Section](4_1_API_Reference.md).
+In this chapter, we will focus on listing the Planner and related core domain objects. We have omitted their corresponding code parts. If you would like to learn more, please refer to the [API Reference Section](../../Tech_Capabilities/Others/API_Reference.md).
## Planner Base Class
Package Path:`agentuniverse.agent.plan.planner.planner.Planner`
diff --git a/docs/guidebook/en/2_2_4_RAG.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/RAG.md
similarity index 85%
rename from docs/guidebook/en/2_2_4_RAG.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/RAG.md
index 4e57aa64..9a081050 100644
--- a/docs/guidebook/en/2_2_4_RAG.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/RAG.md
@@ -3,7 +3,7 @@
Retrieval-Augmented Generation (RAG) is a cutting-edge natural language processing (NLP) technique that significantly enhances the accuracy and diversity of text generation tasks by combining information retrieval and generative models. The core idea of RAG is to first retrieve the most relevant content from a large document corpus based on the input query and then pass this retrieved information as context to the generative model. This allows the generative model to not only rely on its training data but also dynamically access up-to-date external knowledge, enabling the agent to generate responses that are more contextually appropriate.
## General RAG Workflow
-
+
According to [this review](https://arxiv.org/pdf/2312.10997), the majority of current RAG workflows can be summarized into three parts:
@@ -14,9 +14,9 @@ According to [this review](https://arxiv.org/pdf/2312.10997), the majority of cu
## RAG in agentUniverse
In contrast to the general RAG workflow described above, agentUniverse breaks down RAG into two parts:
-1. Knowledge Component: This includes the ability to build a knowledge base from documents and retrieve knowledge based on a query. You can refer to [Knowledge](2_2_4_知识.md) for detailed usage instructions.
-2. Agent-Driven Response Generation Using Knowledge: Once the knowledge component is built in the first step, the agent can use it to retrieve documents relevant to the query and then pass these, along with the prompt and context, to a large model to generate the final response. For specific usage methods, you can refer to [Agent Creation and Use ](2_2_1_Agent_Create_And_Use.md) and set any knowledge you’ve created under the agent's action knowledge section.
+1. Knowledge Component: This includes the ability to build a knowledge base from documents and retrieve knowledge based on a query. You can refer to [Knowledge](../../In-Depth_Guides/Tutorials/Knowledge/Knowledge.md) for detailed usage instructions.
+2. Agent-Driven Response Generation Using Knowledge: Once the knowledge component is built in the first step, the agent can use it to retrieve documents relevant to the query and then pass these, along with the prompt and context, to a large model to generate the final response. For specific usage methods, you can refer to [Agent Creation and Use ](../../In-Depth_Guides/Tutorials/Agent/Agent_Create_And_Use.md) and set any knowledge you’ve created under the agent's action knowledge section.
-If you want to quickly build a RAG workflow using your own documents and use it in an agent, you can refer to [How to Build a Knowledge-Based RAG Agent](2_2_4_How_To_Build_A_RAG_Agent).
+If you want to quickly build a RAG workflow using your own documents and use it in an agent, you can refer to [How to Build a Knowledge-Based RAG Agent](../../How-to/How_To_Build_A_RAG_Agent.md).
diff --git a/docs/guidebook/en/2_2_3_Tool.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool.md
similarity index 100%
rename from docs/guidebook/en/2_2_3_Tool.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool.md
diff --git a/docs/guidebook/en/2_2_3_Tool_Create_And_Use.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool_Create_And_Use.md
similarity index 99%
rename from docs/guidebook/en/2_2_3_Tool_Create_And_Use.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool_Create_And_Use.md
index 3e822188..1bc9933b 100644
--- a/docs/guidebook/en/2_2_3_Tool_Create_And_Use.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool_Create_And_Use.md
@@ -86,7 +86,7 @@ tool = ['sample_standard_app.app.core.tool']
# How to Use the Tool Component
## Configure for use in an Agent
-You can set up any tool you have created in the tool of your agent according to the contents of [Agent Creation and Usage section](2_2_1_Agent_Create_And_Use.md).
+You can set up any tool you have created in the tool of your agent according to the contents of [Agent Creation and Usage section](../Agent/Agent_Create_And_Use.md).
Refer to the example: `demo_rag_agent`, with the specific file path being `sample_standard_app/app/core/agent/rag_agent_case/demo_rag_agent.yaml`.
diff --git a/docs/guidebook/en/2_2_3_Tool_Related_Domain_Objects.md b/docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool_Related_Domain_Objects.md
similarity index 78%
rename from docs/guidebook/en/2_2_3_Tool_Related_Domain_Objects.md
rename to docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool_Related_Domain_Objects.md
index 23b83614..b39ad0a8 100644
--- a/docs/guidebook/en/2_2_3_Tool_Related_Domain_Objects.md
+++ b/docs/guidebook/en/In-Depth_Guides/Tutorials/Tool/Tool_Related_Domain_Objects.md
@@ -1,5 +1,5 @@
# Tool and Related Domain Objects
-In this chapter, we will highlight tool and related core domain objects. We have omitted their corresponding code parts. If you wish to learn more, please read the [API Reference](4_1_API_Reference.md) Section.
+In this chapter, we will highlight tool and related core domain objects. We have omitted their corresponding code parts. If you wish to learn more, please read the [API Reference](../../Tech_Capabilities/Others/API_Reference.md) Section.
## Tool Base Class
Package path: `agentuniverse.agent.action.tool.tool.Tool`