update readme

This commit is contained in:
xieyxclack
2025-11-03 16:49:58 +08:00
parent b498677c51
commit 8bfe829c7b
4 changed files with 136 additions and 3 deletions

View File

@@ -102,7 +102,7 @@ It includes **agent deployment** and **secure sandboxed tool execution**, and ca
| | conversational_agents/multiagent_conversation | ✅ | ❌ | Multi-agent dialogue scenario | | | conversational_agents/multiagent_conversation | ✅ | ❌ | Multi-agent dialogue scenario |
| | conversational_agents/multiagent_debate | ✅ | ❌ | Agents engaging in debates | | | conversational_agents/multiagent_debate | ✅ | ❌ | Agents engaging in debates |
| **Evaluation** | evaluation/ace_bench | ✅ | ❌ | Benchmarks with ACE Bench | | **Evaluation** | evaluation/ace_bench | ✅ | ❌ | Benchmarks with ACE Bench |
| **Alias** | alias/ | ✅ | ✅ | Agent application running in sandbox to solve diverse real-world problems | | **General AI Agent** | alias/ | ✅ | ✅ | Agent application running in sandbox to solve diverse real-world problems |
------ ------
@@ -120,6 +120,18 @@ A powerful multi-agent data processing system that leverages Data-Juicer's 200+
📖 **Documentation**: [English](data_juicer_agent/README.md) | [中文](data_juicer_agent/README_ZH.md) 📖 **Documentation**: [English](data_juicer_agent/README.md) | [中文](data_juicer_agent/README_ZH.md)
### Alias-Agent
*Alias-Agent* (short for *Alias*) is designed to serve as an intelligent assistant for tackle diverse and complicated real-world tasks, providing three operational modes for flexible task execution:
- **Simple React**: Employs vanilla reasoning-acting loops to iteratively solve problems and execute tool calls.
- **Planner-Worker**: Uses intelligent planning to decompose complex tasks into manageable subtasks, with dedicated worker agents handling each subtask independently.
- **Built-in Agents**: Leverages specialized agents tailored for specific domains, including *Deep Research Agent* for comprehensive analysis and *Browser-use Agent* for web-based interactions.
Beyond being a ready-to-use agent, we envision Alias as a foundational template that can be adapted to different scenarios.
📖 **Documentation**: [English](alias/README.md) | [中文](alias/README_ZH.md)
------ ------
## Getting Help ## Getting Help

View File

@@ -102,7 +102,7 @@ AgentScope Runtime 是一个**全面的运行时框架**,主要解决部署和
| | conversational_agents/multiagent_conversation | ✅ | ❌ | 多 Agent 对话场景 | | | conversational_agents/multiagent_conversation | ✅ | ❌ | 多 Agent 对话场景 |
| | conversational_agents/multiagent_debate | ✅ | ❌ | Agent 辩论 | | | conversational_agents/multiagent_debate | ✅ | ❌ | Agent 辩论 |
| **评估** | evaluation/ace_bench | ✅ | ❌ | ACE Bench 基准测试 | | **评估** | evaluation/ace_bench | ✅ | ❌ | ACE Bench 基准测试 |
| **Alias** | alias/ | ✅ | ✅ | 在沙盒中运行的可以解决真实问题的智能体程序 | | **通用智能体** | alias/ | ✅ | ✅ | 在沙盒中运行的可以解决真实问题的智能体程序 |
--- ---
@@ -120,6 +120,17 @@ AgentScope Runtime 是一个**全面的运行时框架**,主要解决部署和
📖 **文档**[English](data_juicer_agent/README.md) | [中文](data_juicer_agent/README_ZH.md) 📖 **文档**[English](data_juicer_agent/README.md) | [中文](data_juicer_agent/README_ZH.md)
### Alias 智能体
*Alias-Agent*(简称 *Alias*)旨在作为一个智能助手来处理多样且复杂的真实世界任务,提供三种操作模式以实现灵活的任务执行:
- **Simple React**:采用经典的推理-行动循环来迭代解决问题并执行工具调用。
- **Planner-Worker**:使用智能规划将复杂任务分解为可管理的子任务,并由专门的执行智能体独立处理每个子任务。
- **Built-in Agents**利用针对特定领域定制的专用智能体包括用于全面分析的Deep Research Agent和用于基于 Web 交互的Browser-use Agent。
除了作为一个即用型智能体,我们也希望 Alias 能够成为一个基础模板,可以迁移到不同的场景。
📖 **文档**[English](alias/README.md) | [中文](alias/README_ZH.md)
--- ---
## 获取帮助 ## 获取帮助

View File

@@ -6,8 +6,9 @@
</div> </div>
## Project introduction ## Project introduction
*Alias-Agent* (short for *Alias*) is an LLM-empowered agent built on [AgentScope](https://github.com/agentscope-ai/agentscope) and [AgentScope-runtime](https://github.com/agentscope-ai/agentscope-runtime/), designed to solve diverse real-world problems. It provides three operational modes for flexible task execution: *Alias-Agent* (short for *Alias*) is an LLM-empowered agent built on [AgentScope](https://github.com/agentscope-ai/agentscope) and [AgentScope-runtime](https://github.com/agentscope-ai/agentscope-runtime/), designed to serve as an intelligent assistant for responding to user queries. Alias excels at decomposing complicated problems, constructing roadmaps, and applying appropriate strategies to tackle diverse real-world tasks.
Specifically, Alias provides three operational modes for flexible task execution:
- **Simple React**: Employs vanilla reasoning-acting loops to iteratively solve problems and execute tool calls. - **Simple React**: Employs vanilla reasoning-acting loops to iteratively solve problems and execute tool calls.
- **Planner-Worker**: Uses intelligent planning to decompose complex tasks into manageable subtasks, with dedicated worker agents handling each subtask independently. - **Planner-Worker**: Uses intelligent planning to decompose complex tasks into manageable subtasks, with dedicated worker agents handling each subtask independently.
- **Built-in Agents**: Leverages specialized agents tailored for specific domains, including *Deep Research Agent* for comprehensive analysis and *Browser-use Agent* for web-based interactions. More details can refer to the following "Basic Usage" section. - **Built-in Agents**: Leverages specialized agents tailored for specific domains, including *Deep Research Agent* for comprehensive analysis and *Browser-use Agent* for web-based interactions. More details can refer to the following "Basic Usage" section.

109
alias/README_ZH.md Normal file
View File

@@ -0,0 +1,109 @@
<div align="center">
<img src="assets/alias.png" alt="Alias-Agent Logo" width="500" height="250" style="vertical-align: middle; margin-right: 20px;">
<h1 style="text-decoration: none; border-bottom: none; display: inline; vertical-align: middle; margin: 0;">Alias-Agent: 即开即用,自由扩展,轻松部署</h1>
</div>
## 项目介绍
*Alias-Agent*(简称 *Alias*)是一个基于 [AgentScope](https://github.com/agentscope-ai/agentscope) 和 [AgentScope-runtime](https://github.com/agentscope-ai/agentscope-runtime/) 构建的LLM驱动的智能体旨在作为响应用户查询的智能助手。Alias擅长分解复杂问题、构建路线图并应用适当的策略来处理各种现实世界的任务。
具体而言Alias提供了三种操作模式以实现灵活的任务执行
- **Simple React简单React模式**:采用经典的推理-行动循环来迭代解决问题和执行工具调用。
- **Planner-Worker规划者-工作者模式)**:使用智能规划将复杂任务分解为可管理的子任务,由专门的工作者智能体独立处理每个子任务。
- **Built-in Agents内置智能体**:利用针对特定领域定制的专业智能体,包括用于全面分析的*深度研究智能体*和用于基于网络交互的*浏览器使用智能体*。更多详细信息可参考下面的"基本使用"部分。
我们的目标是让Alias成为一个开箱即用的解决方案用户可以随时部署以处理各种任务。
## 即将推出
除了作为现成的智能体我们还设想Alias作为一个基础模板可以迁移适配到不同的场景。开发者可以在工具、提示词和智能体级别扩展和自定义Alias以满足他们的特定需求。
我们正在积极开发以下领域的专业增强和适配:
- **商业智能BI** 场景
- **金融**分析应用
- **问答QA** 系统
敬请期待即将发布的版本!
## 安装
以开发模式安装Alias包
```bash
pip install -e .
# 设置沙箱环境
# 如果您使用的是colima则需要运行以下命令
# export DOCKER_HOST=unix://$HOME/.colima/default/docker.sock
# 更多详细信息可参考 https://runtime.agentscope.io/en/sandbox.html
# 方式1从registry拉取
export RUNTIME_SANDBOX_REGISTRY=agentscope-registry.ap-southeast-1.cr.aliyuncs.com
docker pull agentscope-registry.ap-southeast-1.cr.aliyuncs.com/agentscope/runtime-sandbox-alias:latest
# 方式2从docker hub拉取
docker pull agentscope/runtime-sandbox-alias:latest
```
这将安装 `alias` 命令行工具。
## 基本使用
`alias` CLI提供了一个终端界面来运行AI智能体以处理各种任务。
### 运行命令
首先设置API密钥
```bash
# 模型API密钥
export DASHSCOPE_API_KEY=your_dashscope_api_key_here
# 使用其他模型:前往 src/alias/agent/run.py将您的模型添加到 MODEL_FORMATTER_MAPPING然后运行bash来设置您的模型和API密钥。例如
#export MODEL=gpt-5
#export OPENAI_API_KEY=your_openai_api_key_here
# 搜索API密钥深度研究所需
export TAVILY_API_KEY=your_tavily_api_key_here
```
执行智能体任务:
```bash
alias_agent run --task "Your task description here"
```
### 示例
#### 使用所有智能体运行(元规划者与工作者):
```bash
alias_agent run --task "Analyze Meta stock performance in Q1 2025"
```
#### 仅使用Browser-use Agent运行
```bash
alias_agent run --mode browser --task "Search five latest research papers about browser-use agent"
```
#### 上传文件到沙箱工作区:
```bash
# 上传单个文件
alias_agent run --task "Analyze this data" --files data.csv
# 上传多个文件
alias_agent run --task "Process these files and create a summary report" --files report.txt data.csv notes.md
# 使用简短形式 (-f)
alias_agent run --task "Review the documents" -f document1.pdf document2.txt
# 与其他选项结合使用
alias_agent run --mode all --task "Analyze the data and generate insights" --files dataset.csv --verbose
```
**注意**:使用 `--files` 上传的文件会自动复制到沙箱中的 `/workspace` 目录,并保留其原始文件名,使其立即可供智能体访问。
### 获取智能体生成的文件
在您运行 `alias_agent` 的目录中,您应该会找到一个 `sessions_mount_dir` 目录,其中包含子目录,每个子目录都包含来自沙箱挂载文件系统的 `/workspace` 的内容。所有生成的文件都应位于该处。