[update readme][update release content]

Author: lightislost

README.md

@@ -18,7 +18,7 @@
 
 ## 🔔 News
 - [2024.04.01] codefuse-muAgent is now open source, featuring functionalities such as knowledge base, code library, tool usage, code interpreter, and more
-- [2024.09.05] we release muAgent v2.0 about EKG (An Innovative Agent Framework Driven By KG Engine).
+- [2024.09.05] we release muAgent v2.0 - EKG: An Innovative Agent Framework Driven By KG Engine.
 
 
 
@@ -76,12 +76,12 @@ you can see [docs](https://codefuse.ai/docs/api-docs/MuAgent/connector/customed_
 
 
 ## 🧭 Features
-- EKG Builder：Through the design of virtual teams, scene intentions, and semantic nodes, you can experience the differences between online and local documentation, or annotated versus unannotated code handover. For a vast amount of existing documents (text, diagrams, etc.), we support intelligent parsing, which is available for one-click import.
-- EKG Assets：Through comprehensive KG Schema design—including Intention Nodes, Workflow Nodes, Tool Nodes, and Character Nodes—we can meet various SOP Automation requirements. The inclusion of Tool Nodes in the KG enhances the accuracy of tool selection and parameter filling. Additionally, the incorporation of Characters (whether human or agents) in the KG allows for human-involved process advancement, making it flexible for use in multiplayer text-based games.
-- EKG Reasoning：Compared to purely model-based or entirely fix-flow Reasoning, our framework allows LLM to operate under human guidance-flexibility, control, and enabling exploration in unknown scenarios. Additionally, successful exploration experiences can be summarized and documented into KG, minimizing detours for similar issues.
-- Diagnose：After KG editing, visual interface allows for quick debugging, and successful Execution path configurations will be automatically documented, which reduces model interactions, accelerates inference, and minimizes LLM Token costs. Additionally, during online execution, we provide comprehensive end-to-end visual monitoring.
-- Memory：Unified message pooling design supports categorized message delivery and subscription based on the needs of different scenarios, like multi-agent. Additionally, through message retrievel, rerank and distillation, it facilitates long-context handling, improving the overall question-answer quality.
-- ActionSpace：Adhering to Swagger protocol, we provide tool registration, tool categorization, and permission management, facilitating LLM Function Calling. We offer a secure and trustworthy code execution environment, and ensuring precise code generation to meet the demands of various scenarios, including visual plot, numerical calculations, and table editing.
+- **EKG Builder**：Through the design of virtual teams, scene intentions, and semantic nodes, you can experience the differences between online and local documentation, or annotated versus unannotated code handover. For a vast amount of existing documents (text, diagrams, etc.), we support intelligent parsing, which is available for one-click import.
+- **EKG Assets**：Through comprehensive KG Schema design—including Intention Nodes, Workflow Nodes, Tool Nodes, and Character Nodes—we can meet various SOP Automation requirements. The inclusion of Tool Nodes in the KG enhances the accuracy of tool selection and parameter filling. Additionally, the incorporation of Characters (whether human or agents) in the KG allows for human-involved process advancement, making it flexible for use in multiplayer text-based games.
+- **EKG Reasoning**：Compared to purely model-based or entirely fix-flow Reasoning, our framework allows LLM to operate under human guidance-flexibility, control, and enabling exploration in unknown scenarios. Additionally, successful exploration experiences can be summarized and documented into KG, minimizing detours for similar issues.
+- **Diagnose**：After KG editing, visual interface allows for quick debugging, and successful Execution path configurations will be automatically documented, which reduces model interactions, accelerates inference, and minimizes LLM Token costs. Additionally, during online execution, we provide comprehensive end-to-end visual monitoring.
+- **Memory**：Unified message pooling design supports categorized message delivery and subscription based on the needs of different scenarios, like multi-agent. Additionally, through message retrievel, rerank and distillation, it facilitates long-context handling, improving the overall question-answer quality.
+- **ActionSpace**：Adhering to Swagger protocol, we provide tool registration, tool categorization, and permission management, facilitating LLM Function Calling. We offer a secure and trustworthy code execution environment, and ensuring precise code generation to meet the demands of various scenarios, including visual plot, numerical calculations, and table editing.
 
 ## 🤗 Contribution
 We are deeply grateful for your interest in the Codefuse project and warmly welcome any suggestions, opinions (including criticism), comments, and contributions. 

README_zh.md

@@ -18,7 +18,7 @@
 
 ## 🔔 更新
 - [2024.04.01] CodeFuse-muAgent 开源，支持知识库、代码库、工具使用、代码解释器等功能
-- [2024.09.05] muAgent v2.0 全新版本, 实现了由知识图谱引擎驱动的创新Agent框架
+- [2024.09.05] 发布 muAgent v2.0 - EKG：一款由知识图谱引擎驱动的创新代理框架
 
 ## 📜 目录
 - [🤝 介绍](#-介绍)
@@ -70,12 +70,12 @@ pip install codefuse-muagent
 
 ## 🧭 关键技术
 
-- 图谱构建：通过虚拟团队构建、场景意图划分，让你体验在线文档VS本地文档的差别；同时，文本语义输入的节点使用方式，让你感受有注释代码VS无注释代码的差别，充分体现在线协同的优势；面向海量存量文档（通用文本、流程画板等），支持文本智能解析、一键导入
-- 图谱资产：通过场景意图、事件流程、统一工具、组织人物四部分的统一图谱设计，满足各类SOP场景所需知识承载；工具在图谱的纳入进一步提升工具选择、参数填充的准确性，人物/智能体在图谱的纳入，让人可加入流程的推进，可灵活应用于多人文本游戏
-- 图谱推理：相比其他Agent框架纯模型推理、纯人工编排的推理模式，让大模型在人的经验/设计指导下做事，灵活、可控，同时面向未知局面，可自由探索，同时将成功探索经验总结、图谱沉淀，面向相似问题，少走弯路；整体流程唤起支持平台对接（规则配置）、语言触发，满足各类诉求
-- 调试运行：图谱编辑完成后，可视调试，快速发现流程错误、修改优化，同时面向调试成功路径，关联配置自动沉淀，减少模型交互、模型开销，加速推理流程；此外，在线运行中，我们提供全链路可视化监控
-- 记忆管理：统一消息池设计，支持各类场景所需分门别类消息投递、订阅，隔离且互通，便于多Agent场景消息管理使用；同时面向超长上下文，支持消息检索、排序、蒸馏，提升整体问答质量
-- 操作空间：遵循Swagger协议，提供工具注册、权限管理、统一分类，方便LLM在工具调用中接入使用；提供安全可信代码执行环境，同时确保代码精准生成，满足可视绘图、数值计算、图表编辑等各类场景诉求
+- **图谱构建**：通过虚拟团队构建、场景意图划分，让你体验在线文档VS本地文档的差别；同时，文本语义输入的节点使用方式，让你感受有注释代码VS无注释代码的差别，充分体现在线协同的优势；面向海量存量文档（通用文本、流程画板等），支持文本智能解析、一键导入
+- **图谱资产**：通过场景意图、事件流程、统一工具、组织人物四部分的统一图谱设计，满足各类SOP场景所需知识承载；工具在图谱的纳入进一步提升工具选择、参数填充的准确性，人物/智能体在图谱的纳入，让人可加入流程的推进，可灵活应用于多人文本游戏
+- **图谱推理**：相比其他Agent框架纯模型推理、纯人工编排的推理模式，让大模型在人的经验/设计指导下做事，灵活、可控，同时面向未知局面，可自由探索，同时将成功探索经验总结、图谱沉淀，面向相似问题，少走弯路；整体流程唤起支持平台对接（规则配置）、语言触发，满足各类诉求
+- **调试运行**：图谱编辑完成后，可视调试，快速发现流程错误、修改优化，同时面向调试成功路径，关联配置自动沉淀，减少模型交互、模型开销，加速推理流程；此外，在线运行中，我们提供全链路可视化监控
+- **记忆管理**：统一消息池设计，支持各类场景所需分门别类消息投递、订阅，隔离且互通，便于多Agent场景消息管理使用；同时面向超长上下文，支持消息检索、排序、蒸馏，提升整体问答质量
+- **操作空间**：遵循Swagger协议，提供工具注册、权限管理、统一分类，方便LLM在工具调用中接入使用；提供安全可信代码执行环境，同时确保代码精准生成，满足可视绘图、数值计算、图表编辑等各类场景诉求
 
 ## 🤗 贡献指南
 非常感谢您对 Codefuse 项目感兴趣，我们非常欢迎您对 Codefuse 项目的各种建议、意见（包括批评）、评论和贡献。