refactor(data_juicer_agent): update imports and add tests

Author: cmgzn

data_juicer_agent/.gitignore

@@ -4,31 +4,32 @@ A multi-agent data processing system built on [AgentScope](https://github.com/mo
 
 ## 📋 Table of Contents
 
-- [📋 Table of Contents](#-table-of-contents)
-- [What Does This Agent Do?](#what-does-this-agent-do)
-- [Architecture](#architecture)
-- [Quick Start](#quick-start)
-  - [System Requirements](#system-requirements)
-  - [Installation](#installation)
-  - [Configuration](#configuration)
-  - [Usage](#usage)
-- [Agent Introduction](#agent-introduction)
-  - [Data Processing Agent](#data-processing-agent)
-  - [Code Development Agent (DJ Dev Agent)](#code-development-agent-dj-dev-agent)
-- [Advanced Features](#advanced-features)
-  - [Operator Retrieval](#operator-retrieval)
-    - [Retrieval Modes](#retrieval-modes)
-    - [Usage](#usage-1)
-  - [MCP Agent](#mcp-agent)
-    - [MCP Server Types](#mcp-server-types)
-    - [Configuration](#configuration-1)
-    - [Usage Methods](#usage-methods)
-- [Feature Preview](#feature-preview)
-  - [Data-Juicer Q\&A Agent (Demo Available)](#data-juicer-qa-agent-demo-available)
-  - [Data Analysis and Visualization Agent (In Development)](#data-analysis-and-visualization-agent-in-development)
-- [Troubleshooting](#troubleshooting)
-  - [Common Issues](#common-issues)
-  - [Optimization Recommendations](#optimization-recommendations)
+- [DataJuicer Agent](#datajuicer-agent)
+  - [📋 Table of Contents](#-table-of-contents)
+  - [What Does This Agent Do?](#what-does-this-agent-do)
+  - [Architecture](#architecture)
+  - [Quick Start](#quick-start)
+    - [System Requirements](#system-requirements)
+    - [Installation](#installation)
+    - [Configuration](#configuration)
+    - [Usage](#usage)
+  - [Agent Introduction](#agent-introduction)
+    - [Data Processing Agent](#data-processing-agent)
+    - [Code Development Agent (DJ Dev Agent)](#code-development-agent-dj-dev-agent)
+  - [Advanced Features](#advanced-features)
+    - [Operator Retrieval](#operator-retrieval)
+      - [Retrieval Modes](#retrieval-modes)
+      - [Usage](#usage-1)
+    - [MCP Agent](#mcp-agent)
+      - [MCP Server Types](#mcp-server-types)
+      - [Configuration](#configuration-1)
+      - [Usage Methods](#usage-methods)
+  - [Feature Preview](#feature-preview)
+    - [Data-Juicer Q\&A Agent (Demo Available)](#data-juicer-qa-agent-demo-available)
+    - [Data Analysis and Visualization Agent (In Development)](#data-analysis-and-visualization-agent-in-development)
+  - [Troubleshooting](#troubleshooting)
+    - [Common Issues](#common-issues)
+    - [Optimization Recommendations](#optimization-recommendations)
 
 ## What Does This Agent Do?
 
@@ -68,7 +69,14 @@ Router Agent ──┐
 ### Installation
 
 ```bash
-uv pip install -e .
+# Recommended to use uv
+uv pip install -r requirements.txt
+```
+
+or
+
+```bash
+pip install -r requirements.txt
 ```
 
 ### Configuration

data_juicer_agent/README.md

@@ -4,30 +4,31 @@
 
 ## 📋 目录
 
-- [📋 目录](#-目录)
-- [这个智能体做了什么？](#这个智能体做了什么)
-- [架构](#架构)
-- [快速开始](#快速开始)
-  - [系统要求](#系统要求)
-  - [安装](#安装)
-  - [配置](#配置)
-  - [使用](#使用)
-- [智能体介绍](#智能体介绍)
-  - [数据处理智能体](#数据处理智能体)
-  - [代码开发智能体](#代码开发智能体)
-- [高级功能](#高级功能)
-  - [算子检索](#算子检索)
-    - [检索模式](#检索模式)
-    - [使用](#使用-1)
-  - [MCP 智能体](#mcp-智能体)
-    - [MCP 服务器类型](#mcp-服务器类型)
-    - [配置](#配置-1)
-    - [使用方法](#使用方法)
-- [功能预览](#功能预览)
-  - [Data-Juicer 问答智能体 (演示可用)](#data-juicer-问答智能体-演示可用)
-  - [数据分析与可视化智能体 (开发中)](#数据分析与可视化智能体-开发中)
-  - [常见问题](#常见问题)
-  - [优化建议](#优化建议)
+- [DataJuicer 智能体](#datajuicer-智能体)
+  - [📋 目录](#-目录)
+  - [这个智能体做了什么？](#这个智能体做了什么)
+  - [架构](#架构)
+  - [快速开始](#快速开始)
+    - [系统要求](#系统要求)
+    - [安装](#安装)
+    - [配置](#配置)
+    - [使用](#使用)
+  - [智能体介绍](#智能体介绍)
+    - [数据处理智能体](#数据处理智能体)
+    - [代码开发智能体](#代码开发智能体)
+  - [高级功能](#高级功能)
+    - [算子检索](#算子检索)
+      - [检索模式](#检索模式)
+      - [使用](#使用-1)
+    - [MCP 智能体](#mcp-智能体)
+      - [MCP 服务器类型](#mcp-服务器类型)
+      - [配置](#配置-1)
+      - [使用方法](#使用方法)
+  - [功能预览](#功能预览)
+    - [Data-Juicer 问答智能体 (演示可用)](#data-juicer-问答智能体-演示可用)
+    - [数据分析与可视化智能体 (开发中)](#数据分析与可视化智能体-开发中)
+    - [常见问题](#常见问题)
+    - [优化建议](#优化建议)
 
 ## 这个智能体做了什么？
 
@@ -67,7 +68,14 @@ Data-Juicer (DJ) 是一个一站式系统，面向大模型的文本及多模态
 ### 安装
 
 ```bash
-uv pip install -e .
+# 推荐使用uv
+uv pip install -r requirements.txt
+```
+
+或
+
+```bash
+pip install -r requirements.txt
 ```
 
 ### 配置

data_juicer_agent/README_ZH.md

@@ -7,11 +7,16 @@
 from agentscope.formatter import DashScopeChatFormatter
 from agentscope.memory import InMemoryMemory
 from agentscope.agent import UserAgent
-from agentscope.tool import Toolkit
 
-from agent_factory import create_agent
-from prompts import DJ_SYS_PROMPT, DJ_DEV_SYS_PROMPT, ROUTER_SYS_PROMPT, MCP_SYS_PROMPT
-from tools import dj_toolkit, dj_dev_toolkit, mcp_tools, get_mcp_toolkit, agents2toolkit
+from .agent_factory import create_agent
+from .prompts import DJ_SYS_PROMPT, DJ_DEV_SYS_PROMPT, ROUTER_SYS_PROMPT, MCP_SYS_PROMPT
+from .tools import (
+    dj_toolkit,
+    dj_dev_toolkit,
+    mcp_tools,
+    get_mcp_toolkit,
+    agents2toolkit,
+)
 
 # Create shared configuration
 model = DashScopeChatModel(
@@ -145,10 +150,14 @@ async def main(
 if __name__ == "__main__":
     # Example tasks
     # project_root = os.path.abspath(os.path.dirname(__file__))
-    # task = f"数据存储在{project_root}/data/demo-dataset-images.jsonl，筛选掉样本中，文本字段长度小于5的样本，以及图片size小于100Kb的样本。并将输出结果保存到./outputs路径下。"
+    # task = (
+    #     f"The data is stored in {project_root}/data/demo-dataset-images.jsonl. "
+    #     "Among the samples, the text field length is less than 5 "
+    #     "and the image size is less than 100Kb. "
+    #     "And save the output results to the ./outputs path."
+    # )
     #
     # DJ Development example task:
-    # task = "我想开发一个新的DataJuicer过滤算子，用于过滤掉没有人声的音频文件"
+    # task = "I want to develop a new DataJuicer filter operator to filter out audio files without vocals"
     #
-    # MCP Agent will be automatically selected for advanced processing tasks
     fire.Fire(main)

data_juicer_agent/main.py

@@ -0,0 +1,5 @@
+agentscope>=1.0.5
+py-data-juicer>=1.4.2
+faiss-cpu>=1.12.0
+fire>=0.7.1
+langchain-community