diff --git a/README.md b/README.md
index d381370..954fe8d 100644
--- a/README.md
+++ b/README.md
@@ -66,30 +66,10 @@ Our vision is to revolutionize how AI agents collaborate to solve real-world tas
- [🎬 Demo Video](#-demo-video)
- [✨️ Core Features](#️-core-features)
- [🛠️ Installation](#️-installation)
- - [Option 1: Using uv (Recommended)](#option-1-using-uv-recommended)
- - [Option 2: Using venv and pip](#option-2-using-venv-and-pip)
- - [Option 3: Using conda](#option-3-using-conda)
- - [**Setup Environment Variables**](#setup-environment-variables)
- - [Option 1: Using a `.env` File (Recommended)](#option-1-using-a-env-file-recommended)
- - [Option 2: Setting Environment Variables Directly](#option-2-setting-environment-variables-directly)
- - [**Running with Docker**](#running-with-docker)
- [🚀 Quick Start](#-quick-start)
- - [Try MCP (Model Context Protocol) Integration](#try-mcp-model-context-protocol-integration)
- - [Basic Usage](#basic-usage)
- - [Running with Different Models](#running-with-different-models)
- - [Model Requirements](#model-requirements)
- - [Supported Models](#supported-models)
- - [Example Tasks](#example-tasks)
- [🧰 Toolkits and Capabilities](#-toolkits-and-capabilities)
- [Model Context Protocol (MCP)](#model-context-protocol-mcp)
- - [Available Toolkits](#available-toolkits)
- - [Available Toolkits](#available-toolkits-1)
- - [Multimodal Toolkits (Require multimodal model capabilities)](#multimodal-toolkits-require-multimodal-model-capabilities)
- - [Text-Based Toolkits](#text-based-toolkits)
- - [Customizing Your Configuration](#customizing-your-configuration)
- [🌐 Web Interface](#-web-interface)
- - [Starting the Web UI](#starting-the-web-ui)
- - [Features](#features)
- [🧪 Experiments](#-experiments)
- [⏱️ Future Plans](#️-future-plans)
- [📄 License](#-license)
@@ -98,10 +78,8 @@ Our vision is to revolutionize how AI agents collaborate to solve real-world tas
- [🔥 Community](#-community)
- [❓ FAQ](#-faq)
- [📚 Exploring CAMEL Dependency](#-exploring-camel-dependency)
- - [Accessing CAMEL Source Code](#accessing-camel-source-code)
- [⭐ Star History](#-star-history)
-
# 🔥 News
@@ -121,7 +99,20 @@ Our vision is to revolutionize how AI agents collaborate to solve real-world tas
-- **[2025.03.15]**: Restructured the web-based user interface architecture for improved system stability; optimized OWL Agent execution mechanisms for enhanced efficiency and performance; integrated Baidu search engine into SearchToolkit.
+
+
+ 🎉 Latest Major Update - March 15, 2025
+
+
+ Significant Improvements:
+
+ - Restructured web-based UI architecture for enhanced stability 🏗️
+ - Optimized OWL Agent execution mechanisms for better performance 🚀
+
+
Try it now and experience the improved performance in your automation tasks!
+
+
+
- **[2025.03.12]**: Added Bocha search in SearchToolkit, integrated Volcano Engine model platform, and enhanced Azure and OpenAI Compatible models with structured output and tool calling.
- **[2025.03.11]**: We added MCPToolkit, FileWriteToolkit, and TerminalToolkit to enhance OWL agents with MCP tool calling, file writing capabilities, and terminal command execution.
- **[2025.03.09]**: We added a web-based user interface that makes it easier to interact with the system.
@@ -307,21 +298,6 @@ For more detailed Docker usage instructions, including cross-platform support, o
# 🚀 Quick Start
-## Try MCP (Model Context Protocol) Integration
-
-Experience the power of MCP by running our example that demonstrates multi-agent information retrieval and processing:
-
-```bash
-# Set up MCP servers (one-time setup)
-npx -y @smithery/cli install @wonderwhy-er/desktop-commander --client claude
-npx @wonderwhy-er/desktop-commander setup
-
-# Run the MCP example
-python examples/run_mcp.py
-```
-
-This example showcases how OWL agents can seamlessly interact with file systems, web automation, and information retrieval through the MCP protocol. Check out `examples/run_mcp.py` for the full implementation.
-
## Basic Usage
After installation and setting up your environment variables, you can start using OWL right away:
@@ -430,6 +406,8 @@ tools = [
SearchToolkit().search_duckduckgo,
SearchToolkit().search_google, # Comment out if unavailable
SearchToolkit().search_wiki,
+ SearchToolkit().search_bocha,
+ SearchToolkit().search_baidu,
*ExcelToolkit().get_tools(),
*DocumentProcessingToolkit(model=models["document"]).get_tools(),
*FileWriteToolkit(output_dir="./").get_tools(),
@@ -476,7 +454,15 @@ Selecting only necessary toolkits optimizes performance and reduces resource usa
# 🌐 Web Interface
-OWL includes an intuitive web-based user interface that makes it easier to interact with the system.
+
+
+ 🚀 Enhanced Web Interface Now Available!
+
+
+ Experience improved system stability and optimized performance with our latest update.
+ Start exploring the power of OWL through our user-friendly interface!
+
+
## Starting the Web UI
@@ -564,7 +550,7 @@ Join us ([*Discord*](https://discord.camel-ai.org/) or [*WeChat*](https://ghli.o
Join us for further discussions!
-
+
# ❓ FAQ
diff --git a/README_zh.md b/README_zh.md
index 8d303f5..c52da43 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -67,13 +67,9 @@
- [🎬 演示视频](#-演示视频)
- [✨️ 核心功能](#-核心功能)
- [🛠️ 安装](#️-安装)
- - [**选项1:使用 uv(推荐)**](#选项1使用-uv推荐)
- - [**选项2:使用 venv 和 pip**](#选项2使用-venv-和-pip)
- - [**选项3:使用 conda**](#选项3使用-conda)
- - [**设置环境变量**](#设置环境变量)
- - [**使用Docker运行**](#使用docker运行)
- [🚀 快速开始](#-快速开始)
- [🧰 工具包与功能](#-工具包与功能)
+ - [模型上下文协议 (MCP)](#模型上下文协议-mcp)
- [🌐 网页界面](#-网页界面)
- [🧪 实验](#-实验)
- [⏱️ 未来计划](#️-未来计划)
@@ -85,7 +81,6 @@
- [📚 探索 CAMEL 依赖](#-探索-camel-依赖)
- [⭐ Star History](#-star-history)
-
# 🔥 新闻
@@ -104,7 +99,20 @@
-- **[2025.03.15]**: 重构网页用户界面,提升系统稳定性;优化OWL Agent的运行机制,提高执行效率与性能;在SearchToolkit中整合百度搜索引擎
+
+
+ 🎉 最新重大更新 - 2025年3月15日
+
+
+ 重要改进:
+
+ - 重构网页用户界面架构,显著提升系统稳定性 🏗️
+ - 优化OWL Agent执行机制,大幅提升性能与效率 🚀
+
+
立即体验全新升级的自动化任务处理能力!
+
+
+
- **[2025.03.12]**: 在SearchToolkit中添加了Bocha搜索功能,集成了火山引擎模型平台,并更新了Azure和OpenAI Compatible模型的结构化输出和工具调用能力。
- **[2025.03.11]**: 我们添加了 MCPToolkit、FileWriteToolkit 和 TerminalToolkit,增强了 OWL Agent 的 MCP(模型上下文协议)集成、文件写入能力和终端命令执行功能。MCP 作为一个通用协议层,标准化了 AI 模型与各种数据源和工具的交互方式。
- **[2025.03.09]**: 我们添加了基于网页的用户界面,使系统交互变得更加简便。
@@ -284,21 +292,6 @@ chmod +x build_docker.sh
# 🚀 快速开始
-## 尝试 MCP(模型上下文协议)集成
-
-体验 MCP 的强大功能,运行我们的示例来展示多智能体信息检索和处理:
-
-```bash
-# 设置 MCP 服务器(仅需一次性设置)
-npx -y @smithery/cli install @wonderwhy-er/desktop-commander --client claude
-npx @wonderwhy-er/desktop-commander setup
-
-# 运行 MCP 示例
-python examples/run_mcp.py
-```
-
-这个示例展示了 OWL 智能体如何通过 MCP 协议无缝地与文件系统、网页自动化和信息检索进行交互。查看 `examples/run_mcp.py` 了解完整实现。
-
## 基本用法
运行以下示例:
@@ -403,6 +396,8 @@ tools = [
SearchToolkit().search_duckduckgo,
SearchToolkit().search_google, # 如果不可用请注释
SearchToolkit().search_wiki,
+ SearchToolkit().search_bocha,
+ SearchToolkit().search_baidu,
*ExcelToolkit().get_tools(),
*DocumentProcessingToolkit(model=models["document"]).get_tools(),
*FileWriteToolkit(output_dir="./").get_tools(),
@@ -449,6 +444,16 @@ assistant_agent_kwargs = {"model": models["assistant"], "tools": tools}
# 🌐 网页界面
+
+
+ 🚀 全新升级的网页界面现已发布!
+
+
+ 体验更稳定的系统性能和优化后的执行效率。
+ 通过我们直观的界面,开启OWL强大功能的探索之旅!
+
+
+
OWL 现在包含一个基于网页的用户界面,使与系统交互变得更加容易。要启动网页界面,请运行:
```bash
@@ -532,9 +537,8 @@ python examples/run_gaia_roleplaying.py
加入我们的 ([*Discord*](https://discord.camel-ai.org/) 或 [*微信*](https://ghli.org/camel/wechat.png)) 社区,一起探索智能体扩展规律的边界。
加入我们,参与更多讨论!
-
-
-
+
+
# ❓ 常见问题
diff --git a/examples/run_deepseek_zh.py b/examples/run_deepseek_zh.py
index 3228b6d..d67b3ae 100644
--- a/examples/run_deepseek_zh.py
+++ b/examples/run_deepseek_zh.py
@@ -71,6 +71,7 @@ def construct_society(question: str) -> RolePlaying:
*CodeExecutionToolkit(sandbox="subprocess", verbose=True).get_tools(),
SearchToolkit().search_duckduckgo,
SearchToolkit().search_wiki,
+ SearchToolkit().search_baidu,
*ExcelToolkit().get_tools(),
*FileWriteToolkit(output_dir="./").get_tools(),
]
diff --git a/examples/run_qwen_mini_zh.py b/examples/run_qwen_mini_zh.py
index 0ba81f1..b8d9d2c 100644
--- a/examples/run_qwen_mini_zh.py
+++ b/examples/run_qwen_mini_zh.py
@@ -70,7 +70,7 @@ def construct_society(question: str) -> RolePlaying:
planning_agent_model=planning_model,
output_language="Chinese",
).get_tools(),
- SearchToolkit().search_duckduckgo,
+ SearchToolkit().search_baidu,
*FileWriteToolkit(output_dir="./").get_tools(),
]
diff --git a/examples/run_qwen_zh.py b/examples/run_qwen_zh.py
index 1e22b14..0d8cc88 100644
--- a/examples/run_qwen_zh.py
+++ b/examples/run_qwen_zh.py
@@ -103,6 +103,7 @@ def construct_society(question: str) -> RolePlaying:
SearchToolkit().search_duckduckgo,
SearchToolkit().search_google, # Comment this out if you don't have google search
SearchToolkit().search_wiki,
+ SearchToolkit().search_baidu,
*ExcelToolkit().get_tools(),
*DocumentProcessingToolkit(model=models["document"]).get_tools(),
*FileWriteToolkit(output_dir="./").get_tools(),