feat: implement ERP AI Assistant Phase 1
Backend (FastAPI + SQLAlchemy + Claude API + RAG): - Config management with Pydantic v2 - Database engine with connection pooling and SQL injection prevention - AI engine with Claude API integration (support custom base URL) - RAG engine with ChromaDB and sentence-transformers - Requirement analysis service - Config generation service - Executor engine with SQL validation - REST API endpoints: /analyze, /generate, /execute Frontend (Vue 3 + Element Plus + Pinia): - Complete 3-step workflow: analyze → generate → execute - Step indicator with progress visualization - Analysis result display with field table - SQL preview with monospace font - Execute confirmation dialog with safety warning - Execution result display - State management with Pinia - API service integration Security: - SQL injection prevention with parameterized queries - Dangerous SQL operation blocking - Database password URL encoding - Transaction auto-rollback - Pydantic config validation Features: - Natural language requirement analysis - Automated SQL configuration generation - Safe execution with human review - LAN access support - Custom Claude API endpoint support Documentation: - README with quick start guide - Quick start guide - LAN access configuration - Dependency fixes guide - Claude API configuration - Git operation guide - Implementation report Dependencies fixed: - numpy<2.0.0 for chromadb compatibility - sentence-transformers==2.7.0 for huggingface_hub compatibility Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
104
.gitignore
vendored
Normal file
104
.gitignore
vendored
Normal file
@@ -0,0 +1,104 @@
|
||||
# Python
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
*.so
|
||||
.Python
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
wheels/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
|
||||
# Virtual Environment
|
||||
venv/
|
||||
env/
|
||||
ENV/
|
||||
.venv
|
||||
|
||||
# IDE
|
||||
.vscode/
|
||||
.idea/
|
||||
*.swp
|
||||
*.swo
|
||||
*~
|
||||
|
||||
# Environment Variables
|
||||
.env
|
||||
.env.local
|
||||
.env.*.local
|
||||
|
||||
# Logs
|
||||
*.log
|
||||
logs/
|
||||
|
||||
# Database
|
||||
*.db
|
||||
*.sqlite
|
||||
*.sqlite3
|
||||
|
||||
# Testing
|
||||
.pytest_cache/
|
||||
.coverage
|
||||
htmlcov/
|
||||
.tox/
|
||||
|
||||
# ChromaDB
|
||||
backend/knowledge_base/chroma_db/
|
||||
|
||||
# Node.js
|
||||
node_modules/
|
||||
npm-debug.log*
|
||||
yarn-debug.log*
|
||||
yarn-error.log*
|
||||
pnpm-debug.log*
|
||||
|
||||
# Build
|
||||
frontend/dist/
|
||||
frontend/dist-ssr/
|
||||
frontend/*.local
|
||||
|
||||
# Editor directories and files
|
||||
frontend/.vscode/
|
||||
frontend/.idea/
|
||||
frontend/*.suo
|
||||
frontend*.ntvs*
|
||||
frontend*.njsproj
|
||||
frontend*.sln
|
||||
frontend*.sw?
|
||||
|
||||
# OS
|
||||
.DS_Store
|
||||
Thumbs.db
|
||||
|
||||
# Project specific
|
||||
erp-doc/
|
||||
backend/knowledge_base/documents/*.docx
|
||||
backend/knowledge_base/documents/*.xlsx
|
||||
backend/knowledge_base/documents/*.pdf
|
||||
backend/knowledge_base/documents/*.pptx
|
||||
backend/knowledge_base/documents/*.vsdx
|
||||
backend/knowledge_base/documents/*.xls
|
||||
|
||||
# Temporary files
|
||||
*.tmp
|
||||
*.temp
|
||||
*.bak
|
||||
*.swp
|
||||
*~
|
||||
|
||||
# Archives
|
||||
*.zip
|
||||
*.tar.gz
|
||||
*.rar
|
||||
*.7z
|
||||
160
CHANGELOG.md
Normal file
160
CHANGELOG.md
Normal file
@@ -0,0 +1,160 @@
|
||||
# 更新日志
|
||||
|
||||
## [v1.1.0] - 2026-03-21
|
||||
|
||||
### 🎉 新增功能
|
||||
|
||||
#### 前端完整工作流程
|
||||
|
||||
- ✅ **需求分析界面**: 输入自然语言需求，展示结构化分析结果
|
||||
- ✅ **配置生成界面**: 预览生成的 SQL 配置语句
|
||||
- ✅ **执行配置界面**: 确认对话框 + 执行结果展示
|
||||
- ✅ **步骤指示器**: 清晰显示当前进度（分析 → 生成 → 执行）
|
||||
|
||||
#### API 服务封装
|
||||
|
||||
- 创建 `frontend/src/api/index.js`: 封装三个核心 API 调用
|
||||
- `analyzeRequirement()`: 需求分析
|
||||
- `generateConfig()`: 配置生成
|
||||
- `executeConfig()`: 配置执行
|
||||
|
||||
#### 状态管理
|
||||
|
||||
- 创建 `frontend/src/stores/function.js`: Pinia 状态管理
|
||||
- 会话管理
|
||||
- 分析结果存储
|
||||
- 配置结果存储
|
||||
- 执行结果存储
|
||||
- 加载状态管理
|
||||
|
||||
#### UI 组件增强
|
||||
|
||||
- **分析结果展示**:
|
||||
- 使用 `el-descriptions` 展示基本信息
|
||||
- 使用 `el-table` 展示字段列表
|
||||
- 标签化显示（功能类型、必填项等）
|
||||
|
||||
- **SQL 配置预览**:
|
||||
- 等宽字体显示
|
||||
- 15 行文本框
|
||||
- 只读模式
|
||||
|
||||
- **执行确认对话框**:
|
||||
- 安全警告提示
|
||||
- 二次确认机制
|
||||
|
||||
- **执行结果展示**:
|
||||
- 成功/失败状态图标
|
||||
- 详细消息展示
|
||||
|
||||
### 🔧 功能改进
|
||||
|
||||
#### 后端集成
|
||||
|
||||
- 更新 `backend/app/api/generate.py`: 自动存储生成的 SQL 到会话存储
|
||||
- 完善前后端数据流：分析 → 生成 → 存储 → 执行
|
||||
|
||||
#### 用户体验优化
|
||||
|
||||
- ✅ 所有异步操作添加 loading 状态
|
||||
- ✅ 友好的错误提示消息
|
||||
- ✅ 表单必填项验证
|
||||
- ✅ 危险操作二次确认
|
||||
- ✅ 支持重新开始整个流程
|
||||
|
||||
### 📚 文档更新
|
||||
|
||||
- 创建 `docs/QUICK_START.md`: 完整的快速上手指南
|
||||
- 创建 `docs/FRONTEND_UPDATE.md`: 前端功能说明文档
|
||||
- 更新 `README.md`: 添加快速上手指引
|
||||
|
||||
### 🐛 问题修复
|
||||
|
||||
- 修复前端无分析结果展示的问题
|
||||
- 修复缺少配置生成和执行按钮的问题
|
||||
- 修复工作流程不完整的问题
|
||||
|
||||
---
|
||||
|
||||
## [v1.0.0] - 2026-03-21
|
||||
|
||||
### 🎉 初始发布
|
||||
|
||||
#### 后端核心功能
|
||||
|
||||
- ✅ 配置管理（Pydantic v2）
|
||||
- ✅ 数据库引擎（SQLAlchemy + pyodbc）
|
||||
- ✅ AI 引擎（Claude API 集成）
|
||||
- ✅ Prompt 模板设计
|
||||
- ✅ RAG 引擎（ChromaDB + sentence-transformers）
|
||||
- ✅ 需求解析服务
|
||||
- ✅ 配置生成服务
|
||||
- ✅ 执行引擎（SQL 安全验证）
|
||||
|
||||
#### API 层
|
||||
|
||||
- ✅ FastAPI 应用框架
|
||||
- ✅ 请求/响应模型（Pydantic）
|
||||
- ✅ 三个核心端点:
|
||||
- POST `/api/v1/analyze`
|
||||
- POST `/api/v1/generate`
|
||||
- POST `/api/v1/execute`
|
||||
|
||||
#### 前端基础
|
||||
|
||||
- ✅ Vue 3 + Vite 项目结构
|
||||
- ✅ Vue Router 路由配置
|
||||
- ✅ Element Plus UI 集成
|
||||
- ✅ 基础布局（Layout、CreateFunction、History）
|
||||
|
||||
#### 安全特性
|
||||
|
||||
- ✅ SQL 注入防护（参数化查询）
|
||||
- ✅ 危险 SQL 操作拦截
|
||||
- ✅ 数据库密码 URL 编码
|
||||
- ✅ 事务自动回滚
|
||||
- ✅ Pydantic 配置验证
|
||||
|
||||
#### 配置支持
|
||||
|
||||
- ✅ 自定义 Claude API base URL（支持代理/自托管）
|
||||
- ✅ 局域网访问支持
|
||||
- ✅ 环境变量管理
|
||||
|
||||
#### 文档
|
||||
|
||||
- ✅ README.md
|
||||
- ✅ 实施报告
|
||||
- ✗ API 配置指南
|
||||
- ✗ 局域网访问指南
|
||||
- ✗ 依赖问题修复指南
|
||||
|
||||
---
|
||||
|
||||
## 路线图
|
||||
|
||||
### [v1.2.0] - 计划中
|
||||
|
||||
- [ ] SQL 语法高亮显示
|
||||
- [ ] 配置导出功能
|
||||
- [ ] 历史记录页面
|
||||
- [ ] 数据库元数据查询 API
|
||||
- [ ] 知识库管理界面
|
||||
|
||||
### [v1.3.0] - 计划中
|
||||
|
||||
- [ ] 执行日志和审计系统
|
||||
- [ ] 配置模板库
|
||||
- [ ] 批量操作支持
|
||||
- [ ] 错误诊断功能
|
||||
|
||||
### [v2.0.0] - 未来
|
||||
|
||||
- [ ] 多用户权限管理
|
||||
- [ ] 配置版本控制
|
||||
- [ ] CI/CD 集成
|
||||
- [ ] 性能优化分析工具
|
||||
|
||||
---
|
||||
|
||||
**版本命名规范**: 遵循 [语义化版本](https://semver.org/lang/zh-CN/)
|
||||
264
README.md
Normal file
264
README.md
Normal file
@@ -0,0 +1,264 @@
|
||||
# ERP AI Assistant - 一零软件智能配置助手
|
||||
|
||||
基于 Claude AI 的 ERP 平台智能配置助手，支持自然语言需求分析、自动化配置生成和安全执行。
|
||||
|
||||
## 🌟 核心功能
|
||||
|
||||
- **智能需求分析**: 自然语言输入 → 结构化需求文档
|
||||
- **自动配置生成**: 基于需求自动生成 SQL 配置语句
|
||||
- **安全执行机制**: SQL 安全验证 + 人工审核 + 事务保护
|
||||
- **知识库增强**: RAG 技术提供平台配置知识检索
|
||||
|
||||
## 🚀 快速上手
|
||||
|
||||
**首次使用请阅读**: [快速上手指南](docs/QUICK_START.md)
|
||||
|
||||
### 最快 3 步开始
|
||||
|
||||
```bash
|
||||
# 1. 配置后端
|
||||
cd backend && pip install -r requirements.txt
|
||||
cp .env.example .env # 编辑填入数据库和 API 配置
|
||||
|
||||
# 2. 启动后端
|
||||
python -m app.main
|
||||
|
||||
# 3. 启动前端
|
||||
cd ../frontend && npm install && npm run dev
|
||||
```
|
||||
|
||||
访问 http://localhost:5173 开始使用！
|
||||
|
||||
### 1. 环境要求
|
||||
|
||||
- Python 3.10+
|
||||
- Node.js 18+
|
||||
- SQL Server 数据库
|
||||
- Anthropic API Key
|
||||
|
||||
### 2. 后端安装
|
||||
|
||||
```bash
|
||||
cd backend
|
||||
|
||||
# 创建虚拟环境
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate # Windows: venv\Scripts\activate
|
||||
|
||||
# 安装依赖
|
||||
pip install -r requirements.txt
|
||||
|
||||
# 配置环境变量
|
||||
cp .env.example .env
|
||||
# 编辑 .env 文件，填入配置信息
|
||||
```
|
||||
|
||||
### 3. 前端安装
|
||||
|
||||
```bash
|
||||
cd frontend
|
||||
|
||||
# 安装依赖
|
||||
npm install
|
||||
```
|
||||
|
||||
### 4. 启动服务
|
||||
|
||||
**启动后端:**
|
||||
```bash
|
||||
cd backend
|
||||
source venv/bin/activate
|
||||
python -m app.main
|
||||
```
|
||||
|
||||
后端服务运行在 http://localhost:8000
|
||||
|
||||
**启动前端:**
|
||||
```bash
|
||||
cd frontend
|
||||
npm run dev
|
||||
```
|
||||
|
||||
前端服务运行在 http://localhost:5173
|
||||
|
||||
### 5. 访问应用
|
||||
|
||||
**本地访问:**
|
||||
打开浏览器访问 http://localhost:5173
|
||||
|
||||
**局域网访问:**
|
||||
其他设备可通过服务器 IP 访问：http://192.168.1.100:5173
|
||||
|
||||
详细配置请参考 [局域网访问指南](docs/LAN_ACCESS.md)
|
||||
|
||||
## 📚 API 文档
|
||||
|
||||
启动后端后访问:
|
||||
- Swagger UI: http://localhost:8000/docs
|
||||
- ReDoc: http://localhost:8000/redoc
|
||||
|
||||
### 核心 API 端点
|
||||
|
||||
| 端点 | 方法 | 描述 |
|
||||
|------|------|------|
|
||||
| `/api/v1/analyze` | POST | 分析用户需求 |
|
||||
| `/api/v1/generate` | POST | 生成 SQL 配置 |
|
||||
| `/api/v1/execute` | POST | 执行 SQL 配置 |
|
||||
| `/health` | GET | 健康检查 |
|
||||
|
||||
## 🏗️ 项目结构
|
||||
|
||||
```
|
||||
erp-ass/
|
||||
├── backend/ # 后端服务
|
||||
│ ├── app/
|
||||
│ │ ├── api/ # API 路由
|
||||
│ │ ├── core/ # 核心引擎
|
||||
│ │ ├── models/ # 数据模型
|
||||
│ │ ├── services/ # 业务服务
|
||||
│ │ ├── config.py # 配置管理
|
||||
│ │ └── main.py # 应用入口
|
||||
│ ├── tests/ # 测试文件
|
||||
│ ├── knowledge_base/ # 知识库文档
|
||||
│ └── requirements.txt # Python 依赖
|
||||
├── frontend/ # 前端应用
|
||||
│ ├── src/
|
||||
│ │ ├── router/ # 路由配置
|
||||
│ │ ├── views/ # 页面组件
|
||||
│ │ ├── main.js # 应用入口
|
||||
│ │ └── App.vue # 根组件
|
||||
│ ├── index.html
|
||||
│ ├── vite.config.js
|
||||
│ └── package.json
|
||||
└── docs/ # 项目文档
|
||||
```
|
||||
|
||||
## 🔧 配置说明
|
||||
|
||||
### 后端环境变量 (.env)
|
||||
|
||||
```bash
|
||||
# 应用配置
|
||||
APP_NAME=ERP AI Assistant
|
||||
APP_ENV=development
|
||||
DEBUG=True
|
||||
SECRET_KEY=your-secret-key
|
||||
|
||||
# 数据库配置
|
||||
DB_DRIVER=ODBC Driver 17 for SQL Server
|
||||
DB_SERVER=localhost
|
||||
DB_PORT=1433
|
||||
DB_NAME=ERP_DB
|
||||
DB_USER=sa
|
||||
DB_PASSWORD=your-password
|
||||
|
||||
# Claude API 配置
|
||||
ANTHROPIC_API_KEY=your-api-key
|
||||
# ANTHROPIC_BASE_URL=https://your-proxy.com # Optional: custom base URL for proxy or self-hosted
|
||||
CLAUDE_MODEL=claude-sonnet-4-6
|
||||
CLAUDE_MAX_TOKENS=8192
|
||||
CLAUDE_TEMPERATURE=0.7
|
||||
|
||||
# 知识库配置
|
||||
KNOWLEDGE_BASE_PATH=./knowledge_base
|
||||
CHROMA_DB_PATH=./knowledge_base/chroma_db
|
||||
EMBEDDING_MODEL=all-MiniLM-L6-v2
|
||||
CHUNK_SIZE=500
|
||||
CHUNK_OVERLAP=50
|
||||
```
|
||||
|
||||
## 🧪 运行测试
|
||||
|
||||
```bash
|
||||
cd backend
|
||||
source venv/bin/activate
|
||||
pytest tests/ -v --cov=app
|
||||
```
|
||||
|
||||
## 📖 使用流程
|
||||
|
||||
### 1. 创建新功能
|
||||
|
||||
1. 访问前端页面，进入"新建功能"
|
||||
2. 输入自然语言需求，例如：
|
||||
```
|
||||
创建一个销售订单管理页面，包含订单号、客户、订单日期、金额字段
|
||||
```
|
||||
3. 点击"分析需求"，系统自动生成结构化需求文档
|
||||
|
||||
### 2. 生成配置
|
||||
|
||||
1. 查看需求分析结果
|
||||
2. 确认需求正确后，点击"生成配置"
|
||||
3. 系统自动生成 SQL 配置语句
|
||||
|
||||
### 3. 执行配置
|
||||
|
||||
1. 预览生成的 SQL 语句
|
||||
2. 确认无误后，点击"执行"
|
||||
3. 系统安全执行配置，记录执行日志
|
||||
|
||||
## 🔐 安全特性
|
||||
|
||||
- ✅ SQL 注入防护（参数化查询）
|
||||
- ✅ 危险操作拦截（DROP、TRUNCATE）
|
||||
- ✅ 事务保护（自动回滚）
|
||||
- ✅ 人工审核机制
|
||||
- ✅ 密码安全编码
|
||||
|
||||
## 📋 开发计划
|
||||
|
||||
### Phase 1 (已完成) ✅
|
||||
- 基础架构搭建
|
||||
- 核心引擎实现
|
||||
- API 层开发
|
||||
- 前端基础界面
|
||||
|
||||
### Phase 2 (计划中)
|
||||
- 执行日志和审计系统
|
||||
- 数据库元数据 API
|
||||
- 知识库管理界面
|
||||
- 配置预览组件
|
||||
- 执行监控组件
|
||||
|
||||
### Phase 3 (计划中)
|
||||
- 错误排查系统
|
||||
- 系统优化功能
|
||||
- 性能分析工具
|
||||
|
||||
## 🛠️ 技术栈
|
||||
|
||||
**后端:**
|
||||
- FastAPI - 现代 Web 框架
|
||||
- SQLAlchemy - ORM
|
||||
- Anthropic Claude - AI 引擎
|
||||
- ChromaDB - 向量数据库
|
||||
- sentence-transformers - 文本嵌入
|
||||
|
||||
**前端:**
|
||||
- Vue 3 - 渐进式框架
|
||||
- Vite - 构建工具
|
||||
- Element Plus - UI 组件库
|
||||
- Vue Router - 路由管理
|
||||
- Pinia - 状态管理
|
||||
|
||||
**数据库:**
|
||||
- SQL Server - 业务数据库
|
||||
- ChromaDB - 知识库向量数据库
|
||||
|
||||
## 📄 许可证
|
||||
|
||||
本项目仅供内部使用。
|
||||
|
||||
## 🤝 贡献
|
||||
|
||||
暂不接受外部贡献。
|
||||
|
||||
## 📞 联系方式
|
||||
|
||||
如有问题，请联系项目负责人。
|
||||
|
||||
---
|
||||
|
||||
**版本:** 1.0.0
|
||||
**更新日期:** 2026-03-21
|
||||
26
backend/.env.example
Normal file
26
backend/.env.example
Normal file
@@ -0,0 +1,26 @@
|
||||
APP_NAME=ERP AI Assistant
|
||||
APP_ENV=development
|
||||
DEBUG=True
|
||||
SECRET_KEY=change-this-in-production
|
||||
|
||||
# Database
|
||||
DB_DRIVER=ODBC Driver 17 for SQL Server
|
||||
DB_SERVER=192.168.120.19
|
||||
DB_PORT=1433
|
||||
DB_NAME=DMPF_HY
|
||||
DB_USER=sa
|
||||
DB_PASSWORD=your-password
|
||||
|
||||
# Claude API
|
||||
ANTHROPIC_API_KEY=your-claude-api-key
|
||||
# ANTHROPIC_BASE_URL=https://api.anthropic.com # Optional: uncomment to use custom base URL (for proxy or self-hosted)
|
||||
CLAUDE_MODEL=claude-sonnet-4-6
|
||||
CLAUDE_MAX_TOKENS=8192
|
||||
CLAUDE_TEMPERATURE=0.7
|
||||
|
||||
# Knowledge Base
|
||||
KNOWLEDGE_BASE_PATH=./knowledge_base
|
||||
CHROMA_DB_PATH=./knowledge_base/chroma_db
|
||||
EMBEDDING_MODEL=all-MiniLM-L6-v2
|
||||
CHUNK_SIZE=500
|
||||
CHUNK_OVERLAP=50
|
||||
2
backend/app/__init__.py
Normal file
2
backend/app/__init__.py
Normal file
@@ -0,0 +1,2 @@
|
||||
"""ERP AI Assistant Backend"""
|
||||
__version__ = "1.0.0"
|
||||
1
backend/app/api/__init__.py
Normal file
1
backend/app/api/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""API routes for ERP AI Assistant."""
|
||||
113
backend/app/api/analyze.py
Normal file
113
backend/app/api/analyze.py
Normal file
@@ -0,0 +1,113 @@
|
||||
"""Analyze API endpoint for requirement analysis.
|
||||
|
||||
This module provides the /analyze endpoint for analyzing user requirements.
|
||||
"""
|
||||
|
||||
import uuid
|
||||
from typing import Dict
|
||||
|
||||
from fastapi import APIRouter, HTTPException, status
|
||||
from loguru import logger
|
||||
|
||||
from app.models.request import AnalyzeRequest
|
||||
from app.models.response import AnalyzeResponse, ErrorResponse
|
||||
from app.services.requirement_service import RequirementService
|
||||
|
||||
# Create router
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.post(
|
||||
"/analyze",
|
||||
response_model=AnalyzeResponse,
|
||||
responses={
|
||||
400: {"model": ErrorResponse, "description": "Invalid request"},
|
||||
500: {"model": ErrorResponse, "description": "Internal server error"}
|
||||
},
|
||||
summary="Analyze user requirement",
|
||||
description="Analyze natural language or structured requirement and return structured specification"
|
||||
)
|
||||
async def analyze_requirement(request: AnalyzeRequest) -> AnalyzeResponse:
|
||||
"""Analyze user requirement and return structured specification.
|
||||
|
||||
This endpoint accepts either natural language or structured input,
|
||||
processes it through Claude AI with RAG knowledge retrieval, and
|
||||
returns a structured requirement specification.
|
||||
|
||||
Args:
|
||||
request: AnalyzeRequest containing input_type, content, and optional session_id
|
||||
|
||||
Returns:
|
||||
AnalyzeResponse with session_id, status, and structured data
|
||||
|
||||
Raises:
|
||||
HTTPException: 400 for invalid input, 500 for processing errors
|
||||
"""
|
||||
# Generate session ID if not provided
|
||||
session_id = request.session_id or str(uuid.uuid4())
|
||||
|
||||
try:
|
||||
# Validate input type
|
||||
if request.input_type not in ["natural_language", "structured"]:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"code": "INVALID_INPUT_TYPE",
|
||||
"message": "input_type must be 'natural_language' or 'structured'",
|
||||
"session_id": session_id
|
||||
}
|
||||
)
|
||||
|
||||
# Validate content
|
||||
if not request.content or not request.content.strip():
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"code": "EMPTY_CONTENT",
|
||||
"message": "content cannot be empty",
|
||||
"session_id": session_id
|
||||
}
|
||||
)
|
||||
|
||||
logger.info(f"[{session_id}] Processing analyze request: {request.content[:50]}...")
|
||||
|
||||
# Create service and analyze
|
||||
service = RequirementService()
|
||||
result = await service.analyze(
|
||||
user_input=request.content,
|
||||
session_id=session_id
|
||||
)
|
||||
|
||||
logger.success(f"[{session_id}] Analysis completed successfully")
|
||||
|
||||
return AnalyzeResponse(
|
||||
session_id=session_id,
|
||||
status="success",
|
||||
data=result
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
# Re-raise HTTP exceptions
|
||||
raise
|
||||
|
||||
except ValueError as e:
|
||||
logger.error(f"[{session_id}] Validation error: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"code": "VALIDATION_ERROR",
|
||||
"message": str(e),
|
||||
"session_id": session_id
|
||||
}
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[{session_id}] Analysis failed: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail={
|
||||
"code": "ANALYSIS_FAILED",
|
||||
"message": f"Failed to analyze requirement: {str(e)}",
|
||||
"session_id": session_id
|
||||
}
|
||||
)
|
||||
151
backend/app/api/execute.py
Normal file
151
backend/app/api/execute.py
Normal file
@@ -0,0 +1,151 @@
|
||||
"""Execute API endpoint for SQL configuration execution.
|
||||
|
||||
This module provides the /execute endpoint for executing SQL configuration.
|
||||
"""
|
||||
|
||||
import uuid
|
||||
from typing import Dict, Any
|
||||
|
||||
from fastapi import APIRouter, HTTPException, status
|
||||
from loguru import logger
|
||||
|
||||
from app.models.request import ExecuteRequest
|
||||
from app.models.response import ExecuteResponse, ErrorResponse
|
||||
from app.core.executor import ConfigExecutor
|
||||
|
||||
# Create router
|
||||
router = APIRouter()
|
||||
|
||||
# In-memory storage for SQL lists (should use Redis/database in production)
|
||||
_session_sql_store: Dict[str, list] = {}
|
||||
|
||||
|
||||
def store_session_sql(session_id: str, sql_list: list) -> None:
|
||||
"""Store SQL list for a session.
|
||||
|
||||
Args:
|
||||
session_id: Session ID
|
||||
sql_list: List of SQL statements
|
||||
"""
|
||||
_session_sql_store[session_id] = sql_list
|
||||
logger.debug(f"Stored {len(sql_list)} SQL statements for session {session_id}")
|
||||
|
||||
|
||||
def get_session_sql(session_id: str) -> list:
|
||||
"""Retrieve SQL list for a session.
|
||||
|
||||
Args:
|
||||
session_id: Session ID
|
||||
|
||||
Returns:
|
||||
List of SQL statements (empty list if not found)
|
||||
"""
|
||||
sql_list = _session_sql_store.get(session_id, [])
|
||||
logger.debug(f"Retrieved {len(sql_list)} SQL statements for session {session_id}")
|
||||
return sql_list
|
||||
|
||||
|
||||
@router.post(
|
||||
"/execute",
|
||||
response_model=ExecuteResponse,
|
||||
responses={
|
||||
400: {"model": ErrorResponse, "description": "Invalid request"},
|
||||
500: {"model": ErrorResponse, "description": "Internal server error"}
|
||||
},
|
||||
summary="Execute SQL configuration",
|
||||
description="Execute SQL configuration after user confirmation"
|
||||
)
|
||||
async def execute_config(request: ExecuteRequest) -> ExecuteResponse:
|
||||
"""Execute SQL configuration after user confirmation.
|
||||
|
||||
This endpoint executes the SQL statements associated with the session.
|
||||
User must set confirmed=True to proceed with execution.
|
||||
|
||||
Args:
|
||||
request: ExecuteRequest with session_id, confirmed, and backup_enabled
|
||||
|
||||
Returns:
|
||||
ExecuteResponse with execution_id, status, and message
|
||||
|
||||
Raises:
|
||||
HTTPException: 400 if not confirmed or invalid, 500 for execution errors
|
||||
"""
|
||||
# Generate execution ID
|
||||
execution_id = str(uuid.uuid4())
|
||||
|
||||
try:
|
||||
# Check user confirmation
|
||||
if not request.confirmed:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"code": "NOT_CONFIRMED",
|
||||
"message": "User must confirm execution by setting confirmed=True",
|
||||
"session_id": request.session_id,
|
||||
"execution_id": execution_id
|
||||
}
|
||||
)
|
||||
|
||||
logger.info(f"[{request.session_id}] Processing execute request")
|
||||
|
||||
# Retrieve SQL list for session
|
||||
sql_list = get_session_sql(request.session_id)
|
||||
|
||||
if not sql_list:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"code": "NO_SQL_FOUND",
|
||||
"message": "No SQL statements found for this session",
|
||||
"session_id": request.session_id,
|
||||
"execution_id": execution_id
|
||||
}
|
||||
)
|
||||
|
||||
logger.info(f"[{request.session_id}] Retrieved {len(sql_list)} SQL statements")
|
||||
|
||||
# Create executor
|
||||
executor = ConfigExecutor()
|
||||
|
||||
# Execute configuration
|
||||
result = executor.execute_config(sql_list, request.session_id)
|
||||
|
||||
if result["success"]:
|
||||
logger.success(
|
||||
f"[{request.session_id}] Execution completed: {result['message']}"
|
||||
)
|
||||
return ExecuteResponse(
|
||||
execution_id=execution_id,
|
||||
status="success",
|
||||
message=result["message"]
|
||||
)
|
||||
else:
|
||||
logger.error(
|
||||
f"[{request.session_id}] Execution failed: {result['failed']}"
|
||||
)
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail={
|
||||
"code": "EXECUTION_FAILED",
|
||||
"message": result["message"],
|
||||
"error": result["failed"],
|
||||
"session_id": request.session_id,
|
||||
"execution_id": execution_id
|
||||
}
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
# Re-raise HTTP exceptions
|
||||
raise
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[{request.session_id}] Execution failed: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail={
|
||||
"code": "EXECUTION_ERROR",
|
||||
"message": f"Failed to execute config: {str(e)}",
|
||||
"session_id": request.session_id,
|
||||
"execution_id": execution_id
|
||||
}
|
||||
)
|
||||
102
backend/app/api/generate.py
Normal file
102
backend/app/api/generate.py
Normal file
@@ -0,0 +1,102 @@
|
||||
"""Generate API endpoint for configuration generation.
|
||||
|
||||
This module provides the /generate endpoint for generating SQL configuration.
|
||||
"""
|
||||
|
||||
from fastapi import APIRouter, HTTPException, status
|
||||
from loguru import logger
|
||||
|
||||
from app.models.request import GenerateRequest
|
||||
from app.models.response import GenerateResponse, ErrorResponse
|
||||
from app.services.config_service import ConfigService
|
||||
from app.api.execute import store_session_sql # Import SQL storage function
|
||||
|
||||
# Create router
|
||||
router = APIRouter()
|
||||
|
||||
|
||||
@router.post(
|
||||
"/generate",
|
||||
response_model=GenerateResponse,
|
||||
responses={
|
||||
400: {"model": ErrorResponse, "description": "Invalid request"},
|
||||
500: {"model": ErrorResponse, "description": "Internal server error"}
|
||||
},
|
||||
summary="Generate SQL configuration",
|
||||
description="Generate SQL configuration based on structured requirements"
|
||||
)
|
||||
async def generate_config(request: GenerateRequest) -> GenerateResponse:
|
||||
"""Generate SQL configuration based on structured requirements.
|
||||
|
||||
This endpoint takes structured requirements from the analysis phase
|
||||
and generates SQL configuration statements using Claude AI.
|
||||
|
||||
Args:
|
||||
request: GenerateRequest with session_id and requirements
|
||||
|
||||
Returns:
|
||||
GenerateResponse with session_id, status, and generated config
|
||||
|
||||
Raises:
|
||||
HTTPException: 400 for invalid input, 500 for processing errors
|
||||
"""
|
||||
try:
|
||||
# Validate requirements
|
||||
if not request.requirements:
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"code": "EMPTY_REQUIREMENTS",
|
||||
"message": "requirements cannot be empty",
|
||||
"session_id": request.session_id
|
||||
}
|
||||
)
|
||||
|
||||
logger.info(f"[{request.session_id}] Processing generate request")
|
||||
|
||||
# Create service and generate config
|
||||
service = ConfigService()
|
||||
result = await service.generate(
|
||||
requirements=request.requirements,
|
||||
session_id=request.session_id
|
||||
)
|
||||
|
||||
# Store generated SQL for later execution
|
||||
if result and result.get("配置方案") and result["配置方案"].get("sql_list"):
|
||||
sql_list = result["配置方案"]["sql_list"]
|
||||
store_session_sql(request.session_id, sql_list)
|
||||
logger.info(f"[{request.session_id}] Stored {len(sql_list)} SQL statements for execution")
|
||||
|
||||
logger.success(f"[{request.session_id}] Config generation completed")
|
||||
|
||||
return GenerateResponse(
|
||||
session_id=request.session_id,
|
||||
status="success",
|
||||
data=result
|
||||
)
|
||||
|
||||
except HTTPException:
|
||||
# Re-raise HTTP exceptions
|
||||
raise
|
||||
|
||||
except ValueError as e:
|
||||
logger.error(f"[{request.session_id}] Validation error: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_400_BAD_REQUEST,
|
||||
detail={
|
||||
"code": "VALIDATION_ERROR",
|
||||
"message": str(e),
|
||||
"session_id": request.session_id
|
||||
}
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[{request.session_id}] Config generation failed: {e}")
|
||||
raise HTTPException(
|
||||
status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
|
||||
detail={
|
||||
"code": "GENERATION_FAILED",
|
||||
"message": f"Failed to generate config: {str(e)}",
|
||||
"session_id": request.session_id
|
||||
}
|
||||
)
|
||||
67
backend/app/config.py
Normal file
67
backend/app/config.py
Normal file
@@ -0,0 +1,67 @@
|
||||
from pydantic_settings import BaseSettings
|
||||
from pydantic import ConfigDict, field_validator
|
||||
from functools import lru_cache
|
||||
from urllib.parse import quote_plus
|
||||
|
||||
|
||||
class Settings(BaseSettings):
|
||||
# Application
|
||||
APP_NAME: str = "ERP AI Assistant"
|
||||
APP_ENV: str = "development"
|
||||
DEBUG: bool = True
|
||||
SECRET_KEY: str
|
||||
|
||||
# Database
|
||||
DB_DRIVER: str
|
||||
DB_SERVER: str
|
||||
DB_PORT: int = 1433
|
||||
DB_NAME: str
|
||||
DB_USER: str
|
||||
DB_PASSWORD: str
|
||||
|
||||
# Claude API
|
||||
ANTHROPIC_API_KEY: str
|
||||
ANTHROPIC_BASE_URL: str | None = None # Optional custom base URL for proxy/self-hosted
|
||||
CLAUDE_MODEL: str = "claude-sonnet-4-6"
|
||||
CLAUDE_MAX_TOKENS: int = 8192
|
||||
CLAUDE_TEMPERATURE: float = 0.7
|
||||
|
||||
# Knowledge Base
|
||||
KNOWLEDGE_BASE_PATH: str = "./knowledge_base"
|
||||
CHROMA_DB_PATH: str = "./knowledge_base/chroma_db"
|
||||
EMBEDDING_MODEL: str = "all-MiniLM-L6-v2"
|
||||
CHUNK_SIZE: int = 500
|
||||
CHUNK_OVERLAP: int = 50
|
||||
|
||||
@property
|
||||
def DATABASE_URL(self) -> str:
|
||||
"""构建数据库连接 URL（密码安全编码）"""
|
||||
password = quote_plus(self.DB_PASSWORD)
|
||||
return (
|
||||
f"mssql+pyodbc://{self.DB_USER}:{password}"
|
||||
f"@{self.DB_SERVER}:{self.DB_PORT}/{self.DB_NAME}"
|
||||
f"?driver={quote_plus(self.DB_DRIVER)}"
|
||||
)
|
||||
|
||||
@field_validator('CLAUDE_TEMPERATURE')
|
||||
@classmethod
|
||||
def validate_temperature(cls, v):
|
||||
if not 0 <= v <= 2:
|
||||
raise ValueError('CLAUDE_TEMPERATURE must be between 0 and 2')
|
||||
return v
|
||||
|
||||
@field_validator('CHUNK_OVERLAP')
|
||||
@classmethod
|
||||
def validate_chunk_overlap(cls, v, info):
|
||||
chunk_size = info.data.get('CHUNK_SIZE', 500)
|
||||
if v >= chunk_size:
|
||||
raise ValueError('CHUNK_OVERLAP must be less than CHUNK_SIZE')
|
||||
return v
|
||||
|
||||
model_config = ConfigDict(env_file=".env", case_sensitive=True)
|
||||
|
||||
|
||||
@lru_cache()
|
||||
def get_settings() -> Settings:
|
||||
"""获取配置单例"""
|
||||
return Settings()
|
||||
1
backend/app/core/__init__.py
Normal file
1
backend/app/core/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Core modules"""
|
||||
120
backend/app/core/ai_engine.py
Normal file
120
backend/app/core/ai_engine.py
Normal file
@@ -0,0 +1,120 @@
|
||||
"""AI Engine for ERP AI Assistant.
|
||||
|
||||
This module provides the ClaudeEngine class that wraps Claude API calls
|
||||
and provides JSON parsing utilities.
|
||||
"""
|
||||
|
||||
import json
|
||||
import re
|
||||
from typing import Any
|
||||
|
||||
import anthropic
|
||||
from loguru import logger
|
||||
|
||||
from app.config import get_settings
|
||||
|
||||
|
||||
class ClaudeEngine:
|
||||
"""Engine for interacting with Claude API.
|
||||
|
||||
This class wraps the Anthropic Claude API client and provides
|
||||
utilities for parsing JSON responses from Claude.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
"""Initialize Claude engine with settings."""
|
||||
settings = get_settings()
|
||||
|
||||
# Initialize Anthropic client with optional custom base_url
|
||||
client_kwargs = {"api_key": settings.ANTHROPIC_API_KEY}
|
||||
if settings.ANTHROPIC_BASE_URL:
|
||||
client_kwargs["base_url"] = settings.ANTHROPIC_BASE_URL
|
||||
logger.info(f"Using custom Anthropic base URL: {settings.ANTHROPIC_BASE_URL}")
|
||||
|
||||
self.client = anthropic.AsyncAnthropic(**client_kwargs)
|
||||
self.model = settings.CLAUDE_MODEL
|
||||
self.max_tokens = settings.CLAUDE_MAX_TOKENS
|
||||
self.temperature = settings.CLAUDE_TEMPERATURE
|
||||
|
||||
def parse_json_response(self, content: str) -> dict[str, Any]:
|
||||
"""Parse JSON from Claude responses.
|
||||
|
||||
Attempts multiple parsing strategies:
|
||||
1. Direct JSON parse
|
||||
2. Extract from markdown code blocks
|
||||
3. Extract any {...} block
|
||||
|
||||
Args:
|
||||
content: The response content from Claude
|
||||
|
||||
Returns:
|
||||
Parsed JSON as a dictionary
|
||||
|
||||
Raises:
|
||||
ValueError: If JSON cannot be parsed using any strategy
|
||||
"""
|
||||
if not content or not content.strip():
|
||||
raise ValueError("Empty content provided")
|
||||
|
||||
# Strategy 1: Try direct JSON parse
|
||||
try:
|
||||
return json.loads(content)
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
|
||||
# Strategy 2: Try extracting from markdown code blocks
|
||||
json_code_block_pattern = r'```json\s*(\{.*?\})\s*```'
|
||||
json_match = re.search(json_code_block_pattern, content, re.DOTALL)
|
||||
if json_match:
|
||||
try:
|
||||
return json.loads(json_match.group(1))
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
|
||||
# Also try any code block (not just json tagged)
|
||||
code_block_pattern = r'```\s*(\{.*?\})\s*```'
|
||||
code_block_match = re.search(code_block_pattern, content, re.DOTALL)
|
||||
if code_block_match:
|
||||
try:
|
||||
return json.loads(code_block_match.group(1))
|
||||
except json.JSONDecodeError:
|
||||
pass
|
||||
|
||||
# Strategy 3: Try extracting any {...} block
|
||||
# Find balanced braces
|
||||
brace_pattern = r'\{[^{}]*(?:\{[^{}]*\}[^{}]*)*\}'
|
||||
json_blocks = re.findall(brace_pattern, content, re.DOTALL)
|
||||
for json_block in json_blocks:
|
||||
try:
|
||||
return json.loads(json_block)
|
||||
except json.JSONDecodeError:
|
||||
continue
|
||||
|
||||
# All strategies failed
|
||||
logger.error(f"无法解析 Claude 返回的 JSON: {content[:200]}")
|
||||
raise ValueError("无法解析 Claude 返回的 JSON，请检查响应格式")
|
||||
|
||||
async def call_claude(
|
||||
self,
|
||||
messages: list[dict[str, str]],
|
||||
temperature: float | None = None
|
||||
) -> str:
|
||||
"""Call Claude API.
|
||||
|
||||
Args:
|
||||
messages: List of message dictionaries with 'role' and 'content'
|
||||
temperature: Optional temperature override (0-2)
|
||||
|
||||
Returns:
|
||||
The text content from Claude's response
|
||||
|
||||
Raises:
|
||||
Exception: If the API call fails
|
||||
"""
|
||||
response = await self.client.messages.create(
|
||||
model=self.model,
|
||||
max_tokens=self.max_tokens,
|
||||
temperature=temperature if temperature is not None else self.temperature,
|
||||
messages=messages
|
||||
)
|
||||
return response.content[0].text
|
||||
78
backend/app/core/db_engine.py
Normal file
78
backend/app/core/db_engine.py
Normal file
@@ -0,0 +1,78 @@
|
||||
from typing import Optional
|
||||
from sqlalchemy import create_engine, text
|
||||
from sqlalchemy.orm import sessionmaker
|
||||
from contextlib import contextmanager
|
||||
from loguru import logger
|
||||
from app.config import get_settings
|
||||
|
||||
|
||||
class DatabaseEngine:
|
||||
"""数据库操作引擎"""
|
||||
|
||||
def __init__(self):
|
||||
settings = get_settings()
|
||||
self.engine = create_engine(
|
||||
settings.DATABASE_URL,
|
||||
pool_size=20,
|
||||
max_overflow=10,
|
||||
pool_pre_ping=True,
|
||||
echo=settings.DEBUG
|
||||
)
|
||||
self.Session = sessionmaker(bind=self.engine)
|
||||
|
||||
@contextmanager
|
||||
def get_session(self):
|
||||
"""获取数据库会话（上下文管理器）"""
|
||||
session = self.Session()
|
||||
try:
|
||||
yield session
|
||||
session.commit()
|
||||
except Exception as e:
|
||||
session.rollback()
|
||||
logger.error(f"数据库操作失败：{e}")
|
||||
raise
|
||||
finally:
|
||||
session.close()
|
||||
|
||||
def execute_sql(self, sql: str, params: Optional[dict] = None) -> list:
|
||||
"""执行单条 SQL"""
|
||||
with self.get_session() as session:
|
||||
result = session.execute(text(sql), params or {})
|
||||
return result.fetchall()
|
||||
|
||||
def execute_transaction(self, sql_list: list, params_list: Optional[list] = None) -> bool:
|
||||
"""执行事务（多条 SQL）"""
|
||||
params_list = params_list or [None] * len(sql_list)
|
||||
with self.get_session() as session:
|
||||
for sql, params in zip(sql_list, params_list):
|
||||
session.execute(text(sql), params or {})
|
||||
return True
|
||||
|
||||
def get_table_structure(self, table_name: str):
|
||||
"""获取表结构（安全参数化查询）"""
|
||||
sql = """
|
||||
SELECT
|
||||
COLUMN_NAME,
|
||||
DATA_TYPE,
|
||||
CHARACTER_MAXIMUM_LENGTH,
|
||||
IS_NULLABLE,
|
||||
COLUMN_DEFAULT
|
||||
FROM INFORMATION_SCHEMA.COLUMNS
|
||||
WHERE TABLE_NAME = :table_name
|
||||
ORDER BY ORDINAL_POSITION
|
||||
"""
|
||||
return self.execute_sql(sql, {"table_name": table_name})
|
||||
|
||||
def table_exists(self, table_name: str) -> bool:
|
||||
"""检查表是否存在（安全参数化查询）"""
|
||||
sql = """
|
||||
SELECT COUNT(*)
|
||||
FROM INFORMATION_SCHEMA.TABLES
|
||||
WHERE TABLE_NAME = :table_name
|
||||
"""
|
||||
result = self.execute_sql(sql, {"table_name": table_name})
|
||||
return result[0][0] > 0
|
||||
|
||||
def dispose(self):
|
||||
"""关闭连接池，释放资源"""
|
||||
self.engine.dispose()
|
||||
147
backend/app/core/executor.py
Normal file
147
backend/app/core/executor.py
Normal file
@@ -0,0 +1,147 @@
|
||||
"""Config Executor for ERP AI Assistant.
|
||||
|
||||
This module provides the ConfigExecutor class for validating and executing
|
||||
SQL configuration statements with safety checks.
|
||||
"""
|
||||
|
||||
import re
|
||||
from typing import List, Tuple, Dict, Any
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from app.core.db_engine import DatabaseEngine
|
||||
|
||||
|
||||
class ConfigExecutor:
|
||||
"""Executor for SQL configuration statements with safety validation.
|
||||
|
||||
This class validates SQL statements against dangerous operations before
|
||||
execution and provides transaction-based execution with rollback support.
|
||||
"""
|
||||
|
||||
# Dangerous SQL keywords that should be blocked
|
||||
DANGEROUS_KEYWORDS = [
|
||||
r"DROP\s+DATABASE",
|
||||
r"DROP\s+TABLE",
|
||||
r"TRUNCATE\s+TABLE",
|
||||
r"DELETE\s+FROM",
|
||||
r"UPDATE\s+.*\s+SET",
|
||||
r"ALTER\s+TABLE\s+.*\s+DROP"
|
||||
]
|
||||
|
||||
def __init__(self) -> None:
|
||||
"""Initialize executor with database engine."""
|
||||
self.db_engine = DatabaseEngine()
|
||||
logger.info("ConfigExecutor initialized")
|
||||
|
||||
def validate_sql(self, sql: str) -> Tuple[bool, str]:
|
||||
"""Validate SQL statement for safety.
|
||||
|
||||
Checks SQL against a list of dangerous keywords/patterns to prevent
|
||||
destructive operations.
|
||||
|
||||
Args:
|
||||
sql: SQL statement to validate
|
||||
|
||||
Returns:
|
||||
Tuple of (is_valid, message) where is_valid indicates if SQL is safe
|
||||
"""
|
||||
if not sql or not sql.strip():
|
||||
return False, "SQL语句为空"
|
||||
|
||||
sql_upper = sql.upper().strip()
|
||||
|
||||
# Check for dangerous operations
|
||||
for pattern in self.DANGEROUS_KEYWORDS:
|
||||
if re.search(pattern, sql_upper):
|
||||
# Extract matched keyword for error message
|
||||
match = re.search(pattern, sql_upper)
|
||||
matched_keyword = match.group(0) if match else pattern
|
||||
logger.warning(f"SQL validation failed: dangerous operation '{matched_keyword}' detected")
|
||||
return False, f"危险操作被拦截: {matched_keyword}"
|
||||
|
||||
logger.debug(f"SQL validation passed: {sql[:50]}...")
|
||||
return True, "SQL验证通过"
|
||||
|
||||
def execute_config(
|
||||
self,
|
||||
sql_list: List[str],
|
||||
session_id: str
|
||||
) -> Dict[str, Any]:
|
||||
"""Execute a list of SQL statements in a transaction.
|
||||
|
||||
Validates all SQL statements before execution. If any validation fails,
|
||||
no statements are executed.
|
||||
|
||||
Args:
|
||||
sql_list: List of SQL statements to execute
|
||||
session_id: Session ID for logging and tracking
|
||||
|
||||
Returns:
|
||||
Dictionary containing:
|
||||
- success: Boolean indicating overall success
|
||||
- executed: List of executed SQL statements
|
||||
- failed: Error message if execution failed, None otherwise
|
||||
- message: Human-readable result message
|
||||
"""
|
||||
logger.info(f"[{session_id}] Starting config execution with {len(sql_list)} SQL statements")
|
||||
|
||||
results: Dict[str, Any] = {
|
||||
"success": True,
|
||||
"executed": [],
|
||||
"failed": None,
|
||||
"message": ""
|
||||
}
|
||||
|
||||
try:
|
||||
# Step 1: Validate all SQL statements
|
||||
logger.debug(f"[{session_id}] Validating {len(sql_list)} SQL statements")
|
||||
for i, sql in enumerate(sql_list):
|
||||
is_valid, msg = self.validate_sql(sql)
|
||||
if not is_valid:
|
||||
error_msg = f"SQL #{i+1} 验证失败: {msg}"
|
||||
logger.error(f"[{session_id}] {error_msg}")
|
||||
raise ValueError(error_msg)
|
||||
|
||||
# Step 2: Execute transaction
|
||||
logger.debug(f"[{session_id}] Executing transaction")
|
||||
self.db_engine.execute_transaction(sql_list)
|
||||
|
||||
# Step 3: Record success
|
||||
results["executed"] = sql_list
|
||||
results["message"] = f"成功执行 {len(sql_list)} 条SQL"
|
||||
logger.success(f"[{session_id}] {results['message']}")
|
||||
|
||||
except ValueError as e:
|
||||
# Validation failure
|
||||
results["success"] = False
|
||||
results["failed"] = str(e)
|
||||
results["message"] = f"执行失败: {e}"
|
||||
logger.error(f"[{session_id}] {results['message']}")
|
||||
|
||||
except Exception as e:
|
||||
# Execution failure
|
||||
results["success"] = False
|
||||
results["failed"] = str(e)
|
||||
results["message"] = f"执行失败: {e}"
|
||||
logger.error(f"[{session_id}] {results['message']}")
|
||||
|
||||
return results
|
||||
|
||||
def rollback(self, session_id: str) -> Dict[str, Any]:
|
||||
"""Rollback executed operations for a session.
|
||||
|
||||
This is a placeholder for rollback functionality. Actual implementation
|
||||
would require recording inverse SQL operations during execution.
|
||||
|
||||
Args:
|
||||
session_id: Session ID to rollback
|
||||
|
||||
Returns:
|
||||
Dictionary with success status and message
|
||||
"""
|
||||
logger.warning(f"[{session_id}] Rollback requested but not yet implemented")
|
||||
return {
|
||||
"success": False,
|
||||
"message": "回滚功能待实现"
|
||||
}
|
||||
144
backend/app/core/prompts.py
Normal file
144
backend/app/core/prompts.py
Normal file
@@ -0,0 +1,144 @@
|
||||
"""
|
||||
Prompt 模板定义
|
||||
|
||||
模板说明:
|
||||
- SYSTEM_PROMPT: 系统提示词，定义 Claude 的角色和专业领域
|
||||
- ANALYZE_PROMPT_TEMPLATE: 需求解析模板，占位符：user_input, knowledge_context, existing_tables
|
||||
- GENERATE_PROMPT_TEMPLATE: 配置生成模板，占位符：requirements, platform_rules, similar_cases
|
||||
"""
|
||||
|
||||
SYSTEM_PROMPT = """你是一个 ERP 平台配置专家助手，专门帮助开发人员配置一零软件结构化开发平台。
|
||||
|
||||
## 你的职责
|
||||
|
||||
你是 ERP 系统配置和开发的专业顾问，负责：
|
||||
1. 分析用户需求，理解业务场景
|
||||
2. 设计合理的数据库表结构
|
||||
3. 生成符合平台规范的配置方案
|
||||
4. 提供完整的 SQL 脚本和配置说明
|
||||
|
||||
## 平台知识
|
||||
|
||||
你熟悉以下平台概念：
|
||||
- 窗体类型：基础资料、单据、报表、系统设置等
|
||||
- 标准字段命名规范：F 开头的主键、FPrefix 前缀的自定义字段
|
||||
- 配置流程：需求分析 → 表结构设计 → 功能配置 → 页面配置 → 菜单配置
|
||||
- 命名约定：表名以 T_开头，功能号以功能类别前缀开头
|
||||
|
||||
## 输出要求
|
||||
|
||||
1. 提供完整的 SQL 脚本，包括建表语句、函数配置、页面配置等
|
||||
2. 确保配置符合平台规范和最佳实践
|
||||
3. 进行风险评估，提示潜在问题
|
||||
4. 使用 JSON 格式输出结构化结果
|
||||
5. 所有字段和表名使用英文，注释使用中文
|
||||
|
||||
请始终保持专业、严谨的工作态度，确保输出的配置方案可落地执行。"""
|
||||
|
||||
|
||||
ANALYZE_PROMPT_TEMPLATE = """请分析以下用户需求，生成结构化的需求分析文档。
|
||||
|
||||
## 用户输入
|
||||
{user_input}
|
||||
|
||||
## 相关知识上下文
|
||||
{knowledge_context}
|
||||
|
||||
## 现有表结构
|
||||
{existing_tables}
|
||||
|
||||
## 分析要求
|
||||
|
||||
请输出结构化的需求分析文档，使用 JSON 格式，包含以下字段：
|
||||
|
||||
# Note: Use {{ and }} to escape braces for .format() - rendered as literal { and }
|
||||
```json
|
||||
{{
|
||||
"功能名称": "功能的中文名称",
|
||||
"功能号建议": "建议的功能编号，如 SAL001",
|
||||
"窗体类型": "基础资料/单据/报表/系统设置",
|
||||
"主表名建议": "建议的主表名，如 T_SAL_Order",
|
||||
"从表名建议": "建议的从表名，如 T_SAL_OrderEntry",
|
||||
"主表字段": [
|
||||
{{"字段名": "FOrderId", "字段类型": "varchar(50)", "中文名称": "订单编号", "必填": true}},
|
||||
...
|
||||
],
|
||||
"从表字段": [
|
||||
{{"字段名": "FEntryId", "字段类型": "int", "中文名称": "分录 ID", "必填": true}},
|
||||
...
|
||||
],
|
||||
"业务需求": "详细的业务需求描述",
|
||||
"关联表": ["相关表 1", "相关表 2"],
|
||||
"风险提示": ["潜在风险 1", "潜在风险 2"]
|
||||
}}
|
||||
```
|
||||
|
||||
## 注意事项
|
||||
|
||||
1. 字段命名遵循平台规范：主键以 F 开头，使用 PascalCase
|
||||
2. 表名以 T_开头，使用模块前缀
|
||||
3. 考虑必填字段、默认值、数据长度等约束
|
||||
4. 识别必要的业务关联关系
|
||||
5. 评估潜在的数据一致性和性能风险"""
|
||||
|
||||
|
||||
GENERATE_PROMPT_TEMPLATE = """请根据需求分析结果，生成完整的平台配置方案。
|
||||
|
||||
## 需求分析结果
|
||||
{requirements}
|
||||
|
||||
## 平台规则
|
||||
{platform_rules}
|
||||
|
||||
## 类似案例参考
|
||||
{similar_cases}
|
||||
|
||||
## 生成要求
|
||||
|
||||
请生成完整的配置方案，使用 JSON 格式，包含以下内容：
|
||||
|
||||
# Note: Use {{ and }} to escape braces for .format() - rendered as literal { and }
|
||||
```json
|
||||
{{
|
||||
"table_sql": "建表 SQL 语句，包括主表和从表",
|
||||
"function_config_sql": "功能配置 SQL 语句",
|
||||
"page_config_sql": "页面配置 SQL 语句",
|
||||
"menu_config_sql": "菜单配置 SQL 语句",
|
||||
"ikey_config_sql": "IKEY 配置 SQL 语句",
|
||||
"config_summary": {{
|
||||
"created_tables": ["表 1", "表 2"],
|
||||
"main_entities": ["主要实体 1", "主要实体 2"],
|
||||
"relationships": "表间关系说明"
|
||||
}},
|
||||
"implementation_notes": "实施注意事项",
|
||||
"validation_rules": ["验证规则 1", "验证规则 2"]
|
||||
}}
|
||||
```
|
||||
|
||||
## 配置规范
|
||||
|
||||
1. **建表 SQL**:
|
||||
- 主键使用 FId 或 F+ 表名缩写 + Id
|
||||
- 包含创建时间、创建人、更新时间、更新人等审计字段
|
||||
- 使用合适的索引提高查询性能
|
||||
|
||||
2. **功能配置**:
|
||||
- 定义功能号、功能名称、功能类型
|
||||
- 配置数据权限和操作权限
|
||||
|
||||
3. **页面配置**:
|
||||
- 配置表单布局、字段顺序
|
||||
- 设置字段属性（必填、只读、可见性）
|
||||
|
||||
4. **菜单配置**:
|
||||
- 配置菜单层级、图标、排序
|
||||
|
||||
5. **IKEY 配置**:
|
||||
- 配置编码规则、生成策略
|
||||
|
||||
## 注意事项
|
||||
|
||||
- 所有 SQL 语句需要语法正确、可直接执行
|
||||
- 配置需要符合平台规范
|
||||
- 考虑扩展性和维护性
|
||||
- 提供必要的注释说明"""
|
||||
251
backend/app/core/rag_engine.py
Normal file
251
backend/app/core/rag_engine.py
Normal file
@@ -0,0 +1,251 @@
|
||||
"""RAG Engine for ERP AI Assistant.
|
||||
|
||||
This module provides the RAGEngine class that handles knowledge document
|
||||
storage and retrieval using ChromaDB and sentence-transformers embeddings.
|
||||
"""
|
||||
|
||||
from typing import Optional
|
||||
|
||||
import chromadb
|
||||
from chromadb.config import Settings as ChromaSettings
|
||||
from sentence_transformers import SentenceTransformer
|
||||
from loguru import logger
|
||||
|
||||
from app.config import get_settings
|
||||
|
||||
|
||||
class RAGEngine:
|
||||
"""RAG Engine for knowledge document retrieval.
|
||||
|
||||
This class wraps ChromaDB vector database and sentence-transformers
|
||||
to provide semantic search over knowledge documents.
|
||||
"""
|
||||
|
||||
# Class-level singleton for embedding model (lazy loading)
|
||||
_embedding_model: Optional[SentenceTransformer] = None
|
||||
|
||||
def __init__(self) -> None:
|
||||
"""Initialize RAG engine with ChromaDB and embedding model."""
|
||||
settings = get_settings()
|
||||
|
||||
# Initialize ChromaDB persistent client
|
||||
logger.info(f"Initializing ChromaDB at: {settings.CHROMA_DB_PATH}")
|
||||
self.chroma_client = chromadb.PersistentClient(
|
||||
path=settings.CHROMA_DB_PATH,
|
||||
settings=ChromaSettings(anonymized_telemetry=False)
|
||||
)
|
||||
|
||||
# Load sentence-transformers embedding model (lazy loading, singleton)
|
||||
logger.info(f"Loading embedding model: {settings.EMBEDDING_MODEL}")
|
||||
self.embedding_model = self._get_embedding_model(settings.EMBEDDING_MODEL)
|
||||
|
||||
# Get or create documents collection
|
||||
self.documents_collection = self.chroma_client.get_or_create_collection(
|
||||
name="documents"
|
||||
)
|
||||
|
||||
# Store chunking settings
|
||||
self.chunk_size = settings.CHUNK_SIZE
|
||||
self.chunk_overlap = settings.CHUNK_OVERLAP
|
||||
|
||||
logger.info(
|
||||
f"RAG Engine initialized: chunk_size={self.chunk_size}, "
|
||||
f"chunk_overlap={self.chunk_overlap}"
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def _get_embedding_model(cls, model_name: str) -> SentenceTransformer:
|
||||
"""Get or create the embedding model (lazy loading, singleton).
|
||||
|
||||
Args:
|
||||
model_name: Name of the embedding model to load
|
||||
|
||||
Returns:
|
||||
SentenceTransformer embedding model instance
|
||||
"""
|
||||
if cls._embedding_model is None:
|
||||
logger.info(f"Loading embedding model: {model_name}")
|
||||
cls._embedding_model = SentenceTransformer(model_name)
|
||||
return cls._embedding_model
|
||||
|
||||
def _split_text(self, text: str) -> list[str]:
|
||||
"""Split text into overlapping chunks.
|
||||
|
||||
Args:
|
||||
text: The text to split
|
||||
|
||||
Returns:
|
||||
List of chunk strings
|
||||
"""
|
||||
if not text:
|
||||
return []
|
||||
|
||||
chunks = []
|
||||
start = 0
|
||||
text_length = len(text)
|
||||
|
||||
while start < text_length:
|
||||
end = start + self.chunk_size
|
||||
chunk = text[start:end]
|
||||
|
||||
if chunk.strip(): # Only add non-empty chunks
|
||||
chunks.append(chunk)
|
||||
|
||||
start += self.chunk_size - self.chunk_overlap
|
||||
|
||||
# Avoid infinite loop if overlap >= chunk_size
|
||||
if self.chunk_overlap >= self.chunk_size:
|
||||
start += 1
|
||||
|
||||
return chunks
|
||||
|
||||
def _delete_chunks_for_doc(self, doc_id: str) -> None:
|
||||
"""Delete all chunks associated with a document.
|
||||
|
||||
Args:
|
||||
doc_id: The document ID to delete chunks for
|
||||
"""
|
||||
try:
|
||||
# Find all chunks for this document
|
||||
results = self.documents_collection.get(
|
||||
where={"doc_id": doc_id},
|
||||
include=[]
|
||||
)
|
||||
if results and results.get("ids"):
|
||||
self.documents_collection.delete(ids=results["ids"])
|
||||
logger.debug(f"Deleted {len(results['ids'])} chunks for document '{doc_id}'")
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to delete chunks for document '{doc_id}': {e}")
|
||||
|
||||
def add_document(
|
||||
self,
|
||||
doc_id: str,
|
||||
content: str,
|
||||
metadata: Optional[dict] = None
|
||||
) -> int:
|
||||
"""Add a document to the knowledge base.
|
||||
|
||||
Args:
|
||||
doc_id: Unique identifier for the document
|
||||
content: The document content to index
|
||||
metadata: Optional metadata dict to store with the document
|
||||
|
||||
Returns:
|
||||
Number of chunks added
|
||||
|
||||
Raises:
|
||||
ValueError: If content is empty
|
||||
"""
|
||||
if not content or not content.strip():
|
||||
raise ValueError("Cannot add empty document")
|
||||
|
||||
try:
|
||||
# Delete existing chunks for this doc_id (handles duplicates)
|
||||
self._delete_chunks_for_doc(doc_id)
|
||||
|
||||
# Split content into chunks
|
||||
chunks = self._split_text(content)
|
||||
logger.info(f"Split document '{doc_id}' into {len(chunks)} chunks")
|
||||
|
||||
if not chunks:
|
||||
return 0
|
||||
|
||||
# Generate embeddings for all chunks
|
||||
logger.debug(f"Generating embeddings for {len(chunks)} chunks")
|
||||
embeddings = self.embedding_model.encode(chunks)
|
||||
|
||||
# Prepare chunk IDs and metadata
|
||||
chunk_ids = [f"{doc_id}_chunk_{i}" for i in range(len(chunks))]
|
||||
|
||||
# Add metadata to each chunk
|
||||
chunk_metadata = []
|
||||
base_metadata = metadata or {}
|
||||
for i, chunk in enumerate(chunks):
|
||||
meta = {
|
||||
**base_metadata,
|
||||
"doc_id": doc_id,
|
||||
"chunk_index": i,
|
||||
"total_chunks": len(chunks)
|
||||
}
|
||||
chunk_metadata.append(meta)
|
||||
|
||||
# Add to ChromaDB
|
||||
self.documents_collection.add(
|
||||
ids=chunk_ids,
|
||||
embeddings=embeddings.tolist(),
|
||||
documents=chunks,
|
||||
metadatas=chunk_metadata
|
||||
)
|
||||
|
||||
logger.info(f"Added {len(chunks)} chunks for document '{doc_id}'")
|
||||
return len(chunks)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to add document '{doc_id}': {e}")
|
||||
raise
|
||||
|
||||
def search(self, query: str, top_k: int = 3) -> list[dict]:
|
||||
"""Search for relevant document chunks.
|
||||
|
||||
Args:
|
||||
query: The search query
|
||||
top_k: Number of results to return (default: 3, max: 100)
|
||||
|
||||
Returns:
|
||||
List of dicts with 'content', 'metadata', and 'distance'
|
||||
|
||||
Raises:
|
||||
ValueError: If top_k exceeds maximum limit
|
||||
"""
|
||||
# Validate top_k
|
||||
if top_k > 100:
|
||||
raise ValueError(f"top_k cannot exceed 100 (got: {top_k})")
|
||||
|
||||
if not query or not query.strip():
|
||||
logger.warning("Empty search query provided")
|
||||
return []
|
||||
|
||||
try:
|
||||
# Generate embedding for query
|
||||
logger.debug(f"Generating embedding for query: {query[:50]}...")
|
||||
query_embedding = self.embedding_model.encode([query])
|
||||
|
||||
# Query ChromaDB
|
||||
results = self.documents_collection.query(
|
||||
query_embeddings=query_embedding.tolist(),
|
||||
n_results=top_k,
|
||||
include=["documents", "metadatas", "distances"]
|
||||
)
|
||||
|
||||
# Format results
|
||||
formatted_results = []
|
||||
|
||||
if results and results.get("documents"):
|
||||
documents = results["documents"][0]
|
||||
metadatas = results["metadatas"][0] if results.get("metadatas") else []
|
||||
distances = results["distances"][0] if results.get("distances") else []
|
||||
|
||||
for i, content in enumerate(documents):
|
||||
formatted_results.append({
|
||||
"content": content,
|
||||
"metadata": metadatas[i] if i < len(metadatas) else {},
|
||||
"distance": distances[i] if i < len(distances) else None
|
||||
})
|
||||
|
||||
logger.info(f"Found {len(formatted_results)} results for query")
|
||||
return formatted_results
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Search failed: {e}")
|
||||
raise
|
||||
|
||||
def close(self) -> None:
|
||||
"""Release resources and cleanup the RAG engine.
|
||||
|
||||
This method should be called when the engine is no longer needed
|
||||
to free up memory and other resources.
|
||||
"""
|
||||
logger.info("Closing RAG engine and releasing resources")
|
||||
self.embedding_model = None
|
||||
self.documents_collection = None
|
||||
self.chroma_client = None
|
||||
78
backend/app/main.py
Normal file
78
backend/app/main.py
Normal file
@@ -0,0 +1,78 @@
|
||||
"""FastAPI application entry point for ERP AI Assistant.
|
||||
|
||||
This module creates and configures the main FastAPI application instance.
|
||||
"""
|
||||
|
||||
from fastapi import FastAPI
|
||||
from fastapi.middleware.cors import CORSMiddleware
|
||||
|
||||
from app.config import get_settings
|
||||
from app.api import analyze, generate, execute
|
||||
|
||||
# Get application settings
|
||||
settings = get_settings()
|
||||
|
||||
# Create FastAPI application instance
|
||||
app = FastAPI(
|
||||
title=settings.APP_NAME,
|
||||
version="1.0.0",
|
||||
debug=settings.DEBUG,
|
||||
description="AI-powered assistant for ERP platform configuration"
|
||||
)
|
||||
|
||||
# Configure CORS middleware for frontend communication
|
||||
# For development: allow all origins with port 5173
|
||||
# For production: configure specific origins in environment
|
||||
app.add_middleware(
|
||||
CORSMiddleware,
|
||||
allow_origins=["*"] if settings.DEBUG else [
|
||||
"http://localhost:5173",
|
||||
"http://127.0.0.1:5173",
|
||||
],
|
||||
allow_credentials=True,
|
||||
allow_methods=["*"],
|
||||
allow_headers=["*"],
|
||||
)
|
||||
|
||||
# Register API routers
|
||||
app.include_router(analyze.router, prefix="/api/v1", tags=["Analysis"])
|
||||
app.include_router(generate.router, prefix="/api/v1", tags=["Generation"])
|
||||
app.include_router(execute.router, prefix="/api/v1", tags=["Execution"])
|
||||
|
||||
|
||||
@app.get("/", tags=["Root"])
|
||||
async def root() -> dict:
|
||||
"""Root endpoint returning application info.
|
||||
|
||||
Returns:
|
||||
Dictionary with application name, version, and status
|
||||
"""
|
||||
return {
|
||||
"message": settings.APP_NAME,
|
||||
"version": "1.0.0",
|
||||
"status": "running"
|
||||
}
|
||||
|
||||
|
||||
@app.get("/health", tags=["Health"])
|
||||
async def health_check() -> dict:
|
||||
"""Health check endpoint for monitoring.
|
||||
|
||||
Returns:
|
||||
Dictionary with health status
|
||||
"""
|
||||
return {
|
||||
"status": "healthy",
|
||||
"version": "1.0.0"
|
||||
}
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
import uvicorn
|
||||
|
||||
uvicorn.run(
|
||||
"app.main:app",
|
||||
host="0.0.0.0",
|
||||
port=8000,
|
||||
reload=settings.DEBUG
|
||||
)
|
||||
1
backend/app/models/__init__.py
Normal file
1
backend/app/models/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Pydantic models for ERP AI Assistant."""
|
||||
89
backend/app/models/request.py
Normal file
89
backend/app/models/request.py
Normal file
@@ -0,0 +1,89 @@
|
||||
"""Request models for ERP AI Assistant API.
|
||||
|
||||
This module defines Pydantic models for API request validation.
|
||||
"""
|
||||
|
||||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class AnalyzeRequest(BaseModel):
|
||||
"""Request model for requirement analysis.
|
||||
|
||||
Attributes:
|
||||
input_type: Type of input - 'natural_language' or 'structured'
|
||||
content: Requirement content text
|
||||
session_id: Optional session ID for context continuity
|
||||
"""
|
||||
|
||||
input_type: str = Field(
|
||||
...,
|
||||
description="输入类型: natural_language | structured"
|
||||
)
|
||||
content: str = Field(..., description="需求内容")
|
||||
session_id: Optional[str] = Field(None, description="会话ID")
|
||||
|
||||
model_config = {
|
||||
"json_schema_extra": {
|
||||
"examples": [
|
||||
{
|
||||
"input_type": "natural_language",
|
||||
"content": "创建一个销售订单管理页面",
|
||||
"session_id": "session-123"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class GenerateRequest(BaseModel):
|
||||
"""Request model for config generation.
|
||||
|
||||
Attributes:
|
||||
session_id: Session ID from previous analysis
|
||||
requirements: Structured requirements from analysis
|
||||
"""
|
||||
|
||||
session_id: str = Field(..., description="会话ID")
|
||||
requirements: dict = Field(..., description="结构化需求")
|
||||
|
||||
model_config = {
|
||||
"json_schema_extra": {
|
||||
"examples": [
|
||||
{
|
||||
"session_id": "session-123",
|
||||
"requirements": {
|
||||
"功能名称": "销售订单管理",
|
||||
"功能类型": "列表页面"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class ExecuteRequest(BaseModel):
|
||||
"""Request model for config execution.
|
||||
|
||||
Attributes:
|
||||
session_id: Session ID for tracking
|
||||
confirmed: User confirmation flag
|
||||
backup_enabled: Whether to create backup before execution
|
||||
"""
|
||||
|
||||
session_id: str = Field(..., description="会话ID")
|
||||
confirmed: bool = Field(False, description="用户确认标识")
|
||||
backup_enabled: bool = Field(True, description="是否启用备份")
|
||||
|
||||
model_config = {
|
||||
"json_schema_extra": {
|
||||
"examples": [
|
||||
{
|
||||
"session_id": "session-123",
|
||||
"confirmed": True,
|
||||
"backup_enabled": True
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
133
backend/app/models/response.py
Normal file
133
backend/app/models/response.py
Normal file
@@ -0,0 +1,133 @@
|
||||
"""Response models for ERP AI Assistant API.
|
||||
|
||||
This module defines Pydantic models for API response formatting.
|
||||
"""
|
||||
|
||||
from typing import Any, Optional
|
||||
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
|
||||
class AnalyzeResponse(BaseModel):
|
||||
"""Response model for requirement analysis.
|
||||
|
||||
Attributes:
|
||||
session_id: Session ID for this analysis
|
||||
status: Processing status
|
||||
data: Structured requirement analysis result
|
||||
"""
|
||||
|
||||
session_id: str = Field(..., description="会话ID")
|
||||
status: str = Field(..., description="处理状态")
|
||||
data: dict = Field(..., description="结构化需求分析结果")
|
||||
|
||||
model_config = {
|
||||
"json_schema_extra": {
|
||||
"examples": [
|
||||
{
|
||||
"session_id": "session-123",
|
||||
"status": "success",
|
||||
"data": {
|
||||
"功能名称": "销售订单管理",
|
||||
"功能类型": "列表页面"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class GenerateResponse(BaseModel):
|
||||
"""Response model for config generation.
|
||||
|
||||
Attributes:
|
||||
session_id: Session ID
|
||||
status: Processing status
|
||||
data: Generated SQL configuration
|
||||
"""
|
||||
|
||||
session_id: str = Field(..., description="会话ID")
|
||||
status: str = Field(..., description="处理状态")
|
||||
data: dict = Field(..., description="生成的SQL配置")
|
||||
|
||||
model_config = {
|
||||
"json_schema_extra": {
|
||||
"examples": [
|
||||
{
|
||||
"session_id": "session-123",
|
||||
"status": "success",
|
||||
"data": {
|
||||
"sql_list": ["INSERT INTO SYS_FORM ...", "INSERT INTO SYS_MENU ..."]
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class ExecuteResponse(BaseModel):
|
||||
"""Response model for config execution.
|
||||
|
||||
Attributes:
|
||||
execution_id: Unique execution ID
|
||||
status: Execution status
|
||||
message: Human-readable result message
|
||||
"""
|
||||
|
||||
execution_id: str = Field(..., description="执行ID")
|
||||
status: str = Field(..., description="执行状态")
|
||||
message: str = Field(..., description="执行结果消息")
|
||||
|
||||
model_config = {
|
||||
"json_schema_extra": {
|
||||
"examples": [
|
||||
{
|
||||
"execution_id": "exec-456",
|
||||
"status": "success",
|
||||
"message": "成功执行 5 条SQL"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class ErrorResponse(BaseModel):
|
||||
"""Response model for errors.
|
||||
|
||||
Attributes:
|
||||
error: Error details dictionary
|
||||
"""
|
||||
|
||||
error: dict = Field(..., description="错误详情")
|
||||
|
||||
model_config = {
|
||||
"json_schema_extra": {
|
||||
"examples": [
|
||||
{
|
||||
"error": {
|
||||
"code": "VALIDATION_ERROR",
|
||||
"message": "Invalid input",
|
||||
"details": "Field 'input_type' must be 'natural_language' or 'structured'"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
class HealthResponse(BaseModel):
|
||||
"""Response model for health check.
|
||||
|
||||
Attributes:
|
||||
status: Service health status
|
||||
version: Application version
|
||||
"""
|
||||
|
||||
status: str = Field(..., description="服务状态")
|
||||
version: str = Field(default="1.0.0", description="版本号")
|
||||
|
||||
model_config = {
|
||||
"json_schema_extra": {
|
||||
"examples": [{"status": "healthy", "version": "1.0.0"}]
|
||||
}
|
||||
}
|
||||
1
backend/app/services/__init__.py
Normal file
1
backend/app/services/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Service modules for ERP AI Assistant."""
|
||||
135
backend/app/services/config_service.py
Normal file
135
backend/app/services/config_service.py
Normal file
@@ -0,0 +1,135 @@
|
||||
"""Config Generation Service.
|
||||
|
||||
This module provides the ConfigService class for generating ERP platform
|
||||
configuration SQL based on structured requirements.
|
||||
"""
|
||||
|
||||
from typing import Dict, Any
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from app.core.ai_engine import ClaudeEngine
|
||||
from app.core.rag_engine import RAGEngine
|
||||
from app.core.prompts import SYSTEM_PROMPT, GENERATE_PROMPT_TEMPLATE
|
||||
from app.core.db_engine import DatabaseEngine
|
||||
|
||||
|
||||
class ConfigService:
|
||||
"""Service for generating ERP platform configuration.
|
||||
|
||||
This service uses Claude AI with RAG knowledge retrieval to generate
|
||||
SQL configuration statements based on structured requirements.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
"""Initialize config service with required engines."""
|
||||
self.ai_engine = ClaudeEngine()
|
||||
self.rag_engine = RAGEngine()
|
||||
self.db_engine = DatabaseEngine()
|
||||
logger.info("ConfigService initialized")
|
||||
|
||||
async def generate(
|
||||
self,
|
||||
requirements: Dict[str, Any],
|
||||
session_id: str
|
||||
) -> Dict[str, Any]:
|
||||
"""Generate configuration SQL based on requirements.
|
||||
|
||||
Args:
|
||||
requirements: Structured requirement specification
|
||||
session_id: Session ID for tracking
|
||||
|
||||
Returns:
|
||||
Configuration plan with SQL statements
|
||||
|
||||
Raises:
|
||||
ValueError: If requirements are invalid
|
||||
Exception: If generation fails
|
||||
"""
|
||||
if not requirements:
|
||||
raise ValueError("Requirements cannot be empty")
|
||||
|
||||
function_name = requirements.get("功能名称", "Unknown")
|
||||
logger.info(f"[{session_id}] Starting config generation for: {function_name}")
|
||||
|
||||
try:
|
||||
# Step 1: Retrieve platform rules for form type
|
||||
form_type = requirements.get("窗体类型", "0")
|
||||
logger.debug(f"[{session_id}] Retrieving platform rules for form type: {form_type}")
|
||||
platform_rules = self._get_platform_rules(form_type)
|
||||
logger.info(f"[{session_id}] Retrieved platform rules")
|
||||
|
||||
# Step 2: Retrieve similar cases
|
||||
logger.debug(f"[{session_id}] Retrieving similar cases")
|
||||
similar_cases = self._get_similar_cases(function_name)
|
||||
logger.info(f"[{session_id}] Retrieved similar cases")
|
||||
|
||||
# Step 3: Build prompt
|
||||
prompt = GENERATE_PROMPT_TEMPLATE.format(
|
||||
requirements=str(requirements),
|
||||
platform_rules=platform_rules,
|
||||
similar_cases=similar_cases
|
||||
)
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": SYSTEM_PROMPT},
|
||||
{"role": "assistant", "content": "我已了解，请提供需求信息。"},
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
|
||||
# Step 4: Call Claude API
|
||||
logger.debug(f"[{session_id}] Calling Claude API for config generation")
|
||||
response = await self.ai_engine.call_claude(messages, temperature=0.5)
|
||||
|
||||
# Step 5: Parse JSON response
|
||||
result = self.ai_engine.parse_json_response(response)
|
||||
|
||||
logger.success(f"[{session_id}] Config generation completed")
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[{session_id}] Config generation failed: {e}")
|
||||
raise
|
||||
|
||||
def _get_platform_rules(self, form_type: str) -> str:
|
||||
"""Retrieve platform configuration rules for specific form type.
|
||||
|
||||
Args:
|
||||
form_type: Form type code
|
||||
|
||||
Returns:
|
||||
Platform rules text
|
||||
"""
|
||||
try:
|
||||
results = self.rag_engine.search(
|
||||
f"窗体类型{form_type}配置规则",
|
||||
top_k=2
|
||||
)
|
||||
if not results:
|
||||
return "未找到相关配置规则"
|
||||
|
||||
return "\n\n".join([r["content"] for r in results])
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to retrieve platform rules: {e}")
|
||||
return "无法获取平台配置规则"
|
||||
|
||||
def _get_similar_cases(self, keywords: str) -> str:
|
||||
"""Retrieve similar configuration cases from knowledge base.
|
||||
|
||||
Args:
|
||||
keywords: Search keywords
|
||||
|
||||
Returns:
|
||||
Similar cases text
|
||||
"""
|
||||
try:
|
||||
results = self.rag_engine.search(keywords, top_k=2)
|
||||
if not results:
|
||||
return "未找到相似案例"
|
||||
|
||||
return "\n\n".join([r["content"] for r in results])
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to retrieve similar cases: {e}")
|
||||
return "无法获取相似案例"
|
||||
147
backend/app/services/requirement_service.py
Normal file
147
backend/app/services/requirement_service.py
Normal file
@@ -0,0 +1,147 @@
|
||||
"""Requirement Analysis Service.
|
||||
|
||||
This module provides the RequirementService class for analyzing user requirements
|
||||
using Claude AI with RAG knowledge retrieval.
|
||||
"""
|
||||
|
||||
from typing import Optional, Dict, Any
|
||||
import uuid
|
||||
|
||||
from loguru import logger
|
||||
|
||||
from app.core.ai_engine import ClaudeEngine
|
||||
from app.core.rag_engine import RAGEngine
|
||||
from app.core.prompts import SYSTEM_PROMPT, ANALYZE_PROMPT_TEMPLATE
|
||||
from app.core.db_engine import DatabaseEngine
|
||||
|
||||
|
||||
class RequirementService:
|
||||
"""Service for analyzing user requirements with AI assistance.
|
||||
|
||||
This service integrates Claude AI, RAG knowledge retrieval, and database
|
||||
metadata to provide comprehensive requirement analysis.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
"""Initialize requirement service with required engines."""
|
||||
self.ai_engine = ClaudeEngine()
|
||||
self.rag_engine = RAGEngine()
|
||||
self.db_engine = DatabaseEngine()
|
||||
logger.info("RequirementService initialized")
|
||||
|
||||
async def analyze(
|
||||
self,
|
||||
user_input: str,
|
||||
session_id: Optional[str] = None
|
||||
) -> Dict[str, Any]:
|
||||
"""Analyze user requirement and generate structured specification.
|
||||
|
||||
Args:
|
||||
user_input: Natural language requirement from user
|
||||
session_id: Session ID for context management (auto-generated if None)
|
||||
|
||||
Returns:
|
||||
Structured requirement document as dictionary
|
||||
|
||||
Raises:
|
||||
ValueError: If user_input is empty
|
||||
Exception: If AI analysis fails
|
||||
"""
|
||||
# Validate input
|
||||
if not user_input or not user_input.strip():
|
||||
raise ValueError("User input cannot be empty")
|
||||
|
||||
# Generate session ID if not provided
|
||||
session_id = session_id or str(uuid.uuid4())
|
||||
logger.info(f"[{session_id}] Starting requirement analysis: {user_input[:50]}...")
|
||||
|
||||
try:
|
||||
# Step 1: Retrieve relevant knowledge from RAG
|
||||
logger.debug(f"[{session_id}] Searching knowledge base")
|
||||
knowledge_results = self.rag_engine.search(user_input, top_k=3)
|
||||
knowledge_context = self._format_knowledge_context(knowledge_results)
|
||||
logger.info(f"[{session_id}] Retrieved {len(knowledge_results)} knowledge chunks")
|
||||
|
||||
# Step 2: Query existing database tables
|
||||
logger.debug(f"[{session_id}] Querying existing tables")
|
||||
existing_tables = self._get_existing_tables(user_input)
|
||||
logger.info(f"[{session_id}] Retrieved existing table information")
|
||||
|
||||
# Step 3: Build prompt
|
||||
prompt = ANALYZE_PROMPT_TEMPLATE.format(
|
||||
user_input=user_input,
|
||||
knowledge_context=knowledge_context,
|
||||
existing_tables=existing_tables
|
||||
)
|
||||
|
||||
messages = [
|
||||
{"role": "user", "content": SYSTEM_PROMPT},
|
||||
{"role": "assistant", "content": "我已了解平台配置规范，请告诉我您的需求。"},
|
||||
{"role": "user", "content": prompt}
|
||||
]
|
||||
|
||||
# Step 4: Call Claude API
|
||||
logger.debug(f"[{session_id}] Calling Claude API")
|
||||
response = await self.ai_engine.call_claude(messages, temperature=0.7)
|
||||
|
||||
# Step 5: Parse JSON response
|
||||
result = self.ai_engine.parse_json_response(response)
|
||||
|
||||
function_name = result.get("功能名称", "Unknown")
|
||||
logger.success(f"[{session_id}] Requirement analysis completed: {function_name}")
|
||||
|
||||
return result
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"[{session_id}] Requirement analysis failed: {e}")
|
||||
raise
|
||||
|
||||
def _format_knowledge_context(self, knowledge_results: list) -> str:
|
||||
"""Format knowledge search results into context string.
|
||||
|
||||
Args:
|
||||
knowledge_results: List of knowledge search results
|
||||
|
||||
Returns:
|
||||
Formatted knowledge context string
|
||||
"""
|
||||
if not knowledge_results:
|
||||
return "未找到相关知识库内容"
|
||||
|
||||
context_parts = []
|
||||
for result in knowledge_results:
|
||||
source = result.get("metadata", {}).get("source", "文档")
|
||||
content = result.get("content", "")
|
||||
if content:
|
||||
context_parts.append(f"【{source}】\n{content}")
|
||||
|
||||
return "\n\n".join(context_parts) if context_parts else "未找到相关知识库内容"
|
||||
|
||||
def _get_existing_tables(self, user_input: str) -> str:
|
||||
"""Query existing database tables relevant to user input.
|
||||
|
||||
Args:
|
||||
user_input: User requirement text
|
||||
|
||||
Returns:
|
||||
Formatted string listing existing tables
|
||||
"""
|
||||
try:
|
||||
# Query top 10 tables (simplified version - could be enhanced with relevance matching)
|
||||
sql = """
|
||||
SELECT TOP 10 TABLE_NAME
|
||||
FROM INFORMATION_SCHEMA.TABLES
|
||||
WHERE TABLE_TYPE = 'BASE TABLE'
|
||||
ORDER BY TABLE_NAME
|
||||
"""
|
||||
tables = self.db_engine.execute_sql(sql)
|
||||
|
||||
if not tables:
|
||||
return "未找到现有数据表"
|
||||
|
||||
table_list = [f"- {t[0]}" for t in tables]
|
||||
return "\n".join(table_list)
|
||||
|
||||
except Exception as e:
|
||||
logger.warning(f"Failed to query existing tables: {e}")
|
||||
return "无法获取现有表信息"
|
||||
31
backend/fix_dependencies.sh
Normal file
31
backend/fix_dependencies.sh
Normal file
@@ -0,0 +1,31 @@
|
||||
#!/bin/bash
|
||||
# 一键修复依赖问题脚本
|
||||
|
||||
echo "🔧 开始修复依赖问题..."
|
||||
|
||||
cd backend
|
||||
|
||||
# 激活虚拟环境
|
||||
if [ -d "venv" ]; then
|
||||
echo "✓ 找到虚拟环境"
|
||||
source venv/bin/activate
|
||||
else
|
||||
echo "✗ 未找到虚拟环境，正在创建..."
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
fi
|
||||
|
||||
echo "📦 卸载冲突的包..."
|
||||
pip uninstall -y numpy sentence-transformers huggingface-hub
|
||||
|
||||
echo "📥 重新安装所有依赖..."
|
||||
pip install -r requirements.txt
|
||||
|
||||
echo "✅ 验证安装..."
|
||||
python -c "import numpy; print(f'NumPy version: {numpy.__version__}')"
|
||||
python -c "import sentence_transformers; print(f'SentenceTransformers installed successfully')"
|
||||
python -c "import chromadb; print(f'ChromaDB installed successfully')"
|
||||
|
||||
echo ""
|
||||
echo "✨ 修复完成！现在可以运行后端服务："
|
||||
echo " python -m app.main"
|
||||
0
backend/knowledge_base/documents/.gitkeep
Normal file
0
backend/knowledge_base/documents/.gitkeep
Normal file
8
backend/pytest.ini
Normal file
8
backend/pytest.ini
Normal file
@@ -0,0 +1,8 @@
|
||||
[pytest]
|
||||
asyncio_mode = auto
|
||||
asyncio_default_fixture_loop_scope = function
|
||||
testpaths = tests
|
||||
python_files = test_*.py
|
||||
python_classes = Test*
|
||||
python_functions = test_*
|
||||
addopts = -v --cov=app --cov-report=term-missing
|
||||
21
backend/requirements.txt
Normal file
21
backend/requirements.txt
Normal file
@@ -0,0 +1,21 @@
|
||||
fastapi==0.104.1
|
||||
uvicorn[standard]==0.24.0
|
||||
sqlalchemy==2.0.23
|
||||
pyodbc==5.0.1
|
||||
anthropic==0.18.1
|
||||
chromadb==0.4.18
|
||||
sentence-transformers==2.7.0
|
||||
pydantic==2.5.0
|
||||
pydantic-settings==2.1.0
|
||||
python-dotenv==1.0.0
|
||||
loguru==0.7.2
|
||||
tenacity==8.2.3
|
||||
python-jose[cryptography]==3.3.0
|
||||
pytest==7.4.3
|
||||
pytest-asyncio==0.21.1
|
||||
httpx==0.25.2
|
||||
pytest-cov==4.1.0
|
||||
pytest-mock==3.12.0
|
||||
|
||||
# Fix NumPy compatibility issue with chromadb
|
||||
numpy<2.0.0
|
||||
178
backend/scripts/init_knowledge.py
Normal file
178
backend/scripts/init_knowledge.py
Normal file
@@ -0,0 +1,178 @@
|
||||
#!/usr/bin/env python3
|
||||
"""Initialize knowledge base with sample documents.
|
||||
|
||||
This script adds sample knowledge documents to the RAG engine
|
||||
for the ERP AI Assistant.
|
||||
"""
|
||||
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
# NOTE: Development workaround to enable direct script execution.
|
||||
# For production, use: python -m backend.scripts.init_knowledge
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent))
|
||||
|
||||
from loguru import logger
|
||||
from app.core.rag_engine import RAGEngine
|
||||
|
||||
# Sample document: Platform basics
|
||||
PLATFORM_BASICS_CONTENT = """
|
||||
# ERP 平台基础知识
|
||||
|
||||
## 窗体类型 (Form Types)
|
||||
|
||||
ERP 系统支持以下几种窗体类型：
|
||||
|
||||
1. **标准窗体 (Standard Form)**
|
||||
- 用于单一数据实体的 CRUD 操作
|
||||
- 包含字段、按钮、表格等基本控件
|
||||
- 适用于简单的数据录入和查询场景
|
||||
|
||||
2. **列表窗体 (List Form)**
|
||||
- 用于展示多条记录的列表
|
||||
- 支持排序、筛选、分页功能
|
||||
- 可配置列显示和隐藏
|
||||
|
||||
3. **报表窗体 (Report Form)**
|
||||
- 用于生成统计报表
|
||||
- 支持图表展示
|
||||
- 可导出 Excel、PDF 格式
|
||||
|
||||
4. **流程窗体 (Workflow Form)**
|
||||
- 用于业务流程处理
|
||||
- 包含审批、流转、会签等功能
|
||||
- 支持流程状态跟踪
|
||||
|
||||
## 标准字段 (Standard Fields)
|
||||
|
||||
系统预定义以下标准字段类型：
|
||||
|
||||
1. **文本字段**
|
||||
- ShortText: 短文本 (最多 255 字符)
|
||||
- LongText: 长文本 (最多 4000 字符)
|
||||
- Memo: 备注文本 (不限长度)
|
||||
|
||||
2. **数值字段**
|
||||
- Integer: 整数
|
||||
- Decimal: 小数 (可配置精度)
|
||||
- Currency: 货币 (带币种符号)
|
||||
|
||||
3. **日期字段**
|
||||
- Date: 日期
|
||||
- DateTime: 日期时间
|
||||
- Time: 时间
|
||||
|
||||
4. **选择字段**
|
||||
- Dropdown: 下拉选择
|
||||
- Radio: 单选
|
||||
- Checkbox: 复选框
|
||||
- MultiSelect: 多选
|
||||
|
||||
5. **关联字段**
|
||||
- Lookup: 查找关联
|
||||
- Reference: 引用关联
|
||||
- Master-Detail: 主从关联
|
||||
|
||||
## 配置流程 (Configuration Process)
|
||||
|
||||
### 1. 需求分析
|
||||
- 明确业务场景
|
||||
- 确定窗体类型
|
||||
- 梳理字段清单
|
||||
|
||||
### 2. 窗体设计
|
||||
- 创建新窗体
|
||||
- 配置窗体属性
|
||||
- 添加字段控件
|
||||
|
||||
### 3. 字段配置
|
||||
- 选择字段类型
|
||||
- 设置字段属性 (必填、只读、默认值等)
|
||||
- 配置验证规则
|
||||
|
||||
### 4. 权限设置
|
||||
- 配置角色权限
|
||||
- 设置数据访问范围
|
||||
- 配置操作权限
|
||||
|
||||
### 5. 测试验证
|
||||
- 功能测试
|
||||
- 权限测试
|
||||
- 性能测试
|
||||
|
||||
### 6. 发布上线
|
||||
- 提交发布申请
|
||||
- 通过审批流程
|
||||
- 正式发布
|
||||
|
||||
## 常用术语 (Common Terms)
|
||||
|
||||
- **窗体 (Form)**: 用户界面的基本单元，用于数据展示和操作
|
||||
- **字段 (Field)**: 窗体中的数据项，对应数据库列
|
||||
- **控件 (Control)**: 窗体上的可视化元素
|
||||
- **数据源 (Data Source)**: 窗体绑定的数据表或查询
|
||||
- **动作 (Action)**: 窗体上的操作按钮
|
||||
- **验证 (Validation)**: 数据输入的合法性检查
|
||||
- **权限 (Permission)**: 用户对资源的访问控制
|
||||
- **工作流 (Workflow)**: 业务流程的自动化流转
|
||||
|
||||
## 最佳实践 (Best Practices)
|
||||
|
||||
1. **字段命名规范**
|
||||
- 使用英文命名，遵循下划线分隔
|
||||
- 字段名应清晰表达业务含义
|
||||
- 避免使用系统保留字
|
||||
|
||||
2. **性能优化**
|
||||
- 列表窗体配置合理的分页大小
|
||||
- 为常用查询字段建立索引
|
||||
- 避免在窗体中加载过多数据
|
||||
|
||||
3. **用户体验**
|
||||
- 必填字段应明确标识
|
||||
- 提供清晰的错误提示
|
||||
- 常用操作应放在明显位置
|
||||
|
||||
4. **安全性**
|
||||
- 敏感数据应设置访问权限
|
||||
- 用户输入应进行验证
|
||||
- 定期审计权限配置
|
||||
"""
|
||||
|
||||
|
||||
def main() -> None:
|
||||
"""Initialize knowledge base with sample documents."""
|
||||
logger.info("Starting knowledge base initialization...")
|
||||
|
||||
try:
|
||||
# Initialize RAG engine
|
||||
logger.info("Initializing RAG engine...")
|
||||
rag = RAGEngine()
|
||||
|
||||
# Add platform basics document
|
||||
logger.info("Adding platform basics document...")
|
||||
metadata = {
|
||||
"title": "平台基础知识",
|
||||
"category": "platform",
|
||||
"language": "zh-CN",
|
||||
"version": "1.0"
|
||||
}
|
||||
|
||||
chunks_added = rag.add_document(
|
||||
doc_id="platform_basics",
|
||||
content=PLATFORM_BASICS_CONTENT,
|
||||
metadata=metadata
|
||||
)
|
||||
|
||||
logger.success(
|
||||
f"Knowledge base initialized successfully! "
|
||||
f"Added {chunks_added} chunks from 'platform_basics' document."
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to initialize knowledge base: {e}")
|
||||
raise
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
1
backend/tests/__init__.py
Normal file
1
backend/tests/__init__.py
Normal file
@@ -0,0 +1 @@
|
||||
"""Tests"""
|
||||
26
backend/tests/conftest.py
Normal file
26
backend/tests/conftest.py
Normal file
@@ -0,0 +1,26 @@
|
||||
import pytest
|
||||
from app.config import get_settings
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def test_settings():
|
||||
"""Test settings"""
|
||||
return get_settings()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_db_engine(mocker):
|
||||
"""Mock database engine"""
|
||||
from app.core.db_engine import DatabaseEngine
|
||||
return mocker.MagicMock(spec=DatabaseEngine)
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_ai_engine(mocker):
|
||||
"""Mock AI engine with default parse_json_response behavior"""
|
||||
from app.core.ai_engine import ClaudeEngine
|
||||
mock_engine = mocker.MagicMock(spec=ClaudeEngine)
|
||||
# Default behavior: returns a test function dict
|
||||
# Can be overridden in individual tests via mock_ai_engine.parse_json_response.return_value = {...}
|
||||
mock_engine.parse_json_response.return_value = {"function_name": "test_function"}
|
||||
return mock_engine
|
||||
148
backend/tests/test_ai_engine.py
Normal file
148
backend/tests/test_ai_engine.py
Normal file
@@ -0,0 +1,148 @@
|
||||
import pytest
|
||||
from app.core.ai_engine import ClaudeEngine
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_settings(mocker):
|
||||
"""Mock settings for test isolation."""
|
||||
mock_settings = mocker.MagicMock()
|
||||
mock_settings.ANTHROPIC_API_KEY = "test-key"
|
||||
mock_settings.CLAUDE_MODEL = "claude-sonnet-4-6"
|
||||
mock_settings.CLAUDE_MAX_TOKENS = 1024
|
||||
mock_settings.CLAUDE_TEMPERATURE = 0.7
|
||||
mocker.patch('app.core.ai_engine.get_settings', return_value=mock_settings)
|
||||
return mock_settings
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_anthropic_client(mocker):
|
||||
"""Mock Anthropic async client."""
|
||||
mock_client = mocker.AsyncMock()
|
||||
mocker.patch('app.core.ai_engine.anthropic.AsyncAnthropic', return_value=mock_client)
|
||||
return mock_client
|
||||
|
||||
|
||||
def test_claude_engine_init(mocker, mock_settings):
|
||||
"""测试 Claude 引擎初始化"""
|
||||
engine = ClaudeEngine()
|
||||
assert engine.client is not None
|
||||
assert engine.model == "claude-sonnet-4-6"
|
||||
assert engine.max_tokens == 1024
|
||||
assert engine.temperature == 0.7
|
||||
|
||||
|
||||
def test_parse_json_response(mocker, mock_settings):
|
||||
"""测试 JSON 解析"""
|
||||
engine = ClaudeEngine()
|
||||
|
||||
# 测试纯 JSON
|
||||
json_str = '{"name": "test", "value": 123}'
|
||||
result = engine.parse_json_response(json_str)
|
||||
assert result["name"] == "test"
|
||||
assert result["value"] == 123
|
||||
|
||||
# 测试 markdown 代码块
|
||||
md_str = '```json\n{"name": "test"}\n```'
|
||||
result = engine.parse_json_response(md_str)
|
||||
assert result["name"] == "test"
|
||||
|
||||
|
||||
def test_parse_json_response_empty_content(mocker, mock_settings):
|
||||
"""测试空内容错误处理"""
|
||||
engine = ClaudeEngine()
|
||||
|
||||
with pytest.raises(ValueError, match="Empty content provided"):
|
||||
engine.parse_json_response("")
|
||||
|
||||
with pytest.raises(ValueError, match="Empty content provided"):
|
||||
engine.parse_json_response(" ")
|
||||
|
||||
|
||||
def test_parse_json_response_invalid_json(mocker, mock_settings):
|
||||
"""测试无效 JSON 错误处理"""
|
||||
engine = ClaudeEngine()
|
||||
|
||||
# 无效 JSON 且无法提取任何代码块
|
||||
invalid_str = "This is not JSON at all"
|
||||
with pytest.raises(ValueError, match="无法解析 Claude 返回的 JSON"):
|
||||
engine.parse_json_response(invalid_str)
|
||||
|
||||
# 无效的 JSON 代码块
|
||||
invalid_json_block = '```json\n{invalid json}\n```'
|
||||
with pytest.raises(ValueError, match="无法解析 Claude 返回的 JSON"):
|
||||
engine.parse_json_response(invalid_json_block)
|
||||
|
||||
|
||||
def test_parse_json_response_code_block(mocker, mock_settings):
|
||||
"""测试代码块 JSON 解析"""
|
||||
engine = ClaudeEngine()
|
||||
|
||||
# 普通代码块（无 json 标签）
|
||||
code_block = '```\n{"status": "ok"}\n```'
|
||||
result = engine.parse_json_response(code_block)
|
||||
assert result["status"] == "ok"
|
||||
|
||||
|
||||
def test_parse_json_response_nested_json(mocker, mock_settings):
|
||||
"""测试嵌套 JSON 解析"""
|
||||
engine = ClaudeEngine()
|
||||
|
||||
# 带有一些额外文本的 JSON
|
||||
text_with_json = 'Some text before {"key": "value"} and after'
|
||||
result = engine.parse_json_response(text_with_json)
|
||||
assert result["key"] == "value"
|
||||
|
||||
# 嵌套 JSON
|
||||
nested_json = '{"outer": {"inner": "value"}}'
|
||||
result = engine.parse_json_response(nested_json)
|
||||
assert result["outer"]["inner"] == "value"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_call_claude(mocker, mock_settings, mock_anthropic_client):
|
||||
"""测试 call_claude 方法"""
|
||||
# 设置 mock 响应
|
||||
mock_response = mocker.MagicMock()
|
||||
mock_response.content = [mocker.MagicMock(text="Hello, I am Claude")]
|
||||
mock_anthropic_client.messages.create.return_value = mock_response
|
||||
|
||||
engine = ClaudeEngine()
|
||||
messages = [{"role": "user", "content": "Hello"}]
|
||||
result = await engine.call_claude(messages)
|
||||
|
||||
assert result == "Hello, I am Claude"
|
||||
mock_anthropic_client.messages.create.assert_called_once_with(
|
||||
model="claude-sonnet-4-6",
|
||||
max_tokens=1024,
|
||||
temperature=0.7,
|
||||
messages=messages
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_call_claude_with_temperature(mocker, mock_settings, mock_anthropic_client):
|
||||
"""测试 call_claude 带温度参数"""
|
||||
mock_response = mocker.MagicMock()
|
||||
mock_response.content = [mocker.MagicMock(text="Response")]
|
||||
mock_anthropic_client.messages.create.return_value = mock_response
|
||||
|
||||
engine = ClaudeEngine()
|
||||
messages = [{"role": "user", "content": "Hello"}]
|
||||
result = await engine.call_claude(messages, temperature=1.5)
|
||||
|
||||
assert result == "Response"
|
||||
call_args = mock_anthropic_client.messages.create.call_args
|
||||
assert call_args.kwargs["temperature"] == 1.5
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_call_claude_error(mocker, mock_settings, mock_anthropic_client):
|
||||
"""测试 call_claude 错误处理"""
|
||||
# 设置 mock 抛出异常
|
||||
mock_anthropic_client.messages.create.side_effect = Exception("API Error")
|
||||
|
||||
engine = ClaudeEngine()
|
||||
messages = [{"role": "user", "content": "Hello"}]
|
||||
|
||||
with pytest.raises(Exception, match="API Error"):
|
||||
await engine.call_claude(messages)
|
||||
94
backend/tests/test_config_service.py
Normal file
94
backend/tests/test_config_service.py
Normal file
@@ -0,0 +1,94 @@
|
||||
"""Tests for Config Service.
|
||||
|
||||
This module tests the ConfigService class for configuration generation.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, AsyncMock, patch
|
||||
from app.services.config_service import ConfigService
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_generate_config():
|
||||
"""Test config generation with mocked dependencies."""
|
||||
with patch('app.services.config_service.ClaudeEngine') as MockClaudeEngine, \
|
||||
patch('app.services.config_service.RAGEngine') as MockRAGEngine, \
|
||||
patch('app.services.config_service.DatabaseEngine') as MockDBEngine:
|
||||
|
||||
# Setup mocks
|
||||
mock_ai_engine = MagicMock()
|
||||
mock_ai_engine.call_claude = AsyncMock(return_value='{"配置方案": {"sql_list": ["INSERT INTO SYS_FORM..."]}}')
|
||||
mock_ai_engine.parse_json_response = MagicMock(return_value={
|
||||
"配置方案": {
|
||||
"sql_list": ["INSERT INTO SYS_FORM VALUES (...)"]
|
||||
}
|
||||
})
|
||||
MockClaudeEngine.return_value = mock_ai_engine
|
||||
|
||||
mock_rag_engine = MagicMock()
|
||||
mock_rag_engine.search = MagicMock(return_value=[
|
||||
{"content": "Sample rule", "metadata": {}}
|
||||
])
|
||||
MockRAGEngine.return_value = mock_rag_engine
|
||||
|
||||
MockDBEngine.return_value = MagicMock()
|
||||
|
||||
# Create service and test
|
||||
service = ConfigService()
|
||||
|
||||
requirements = {
|
||||
"功能名称": "销售订单",
|
||||
"功能号建议": "11-001",
|
||||
"窗体类型": "5",
|
||||
"主表名建议": "SA_ORDER",
|
||||
"主表字段": [
|
||||
{"字段名": "订单号", "字段类型": "varchar(50)", "必填": True}
|
||||
]
|
||||
}
|
||||
|
||||
result = await service.generate(requirements, "test-session")
|
||||
|
||||
assert result is not None
|
||||
assert "配置方案" in result
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_platform_rules():
|
||||
"""Test platform rules retrieval."""
|
||||
with patch('app.services.config_service.ClaudeEngine'), \
|
||||
patch('app.services.config_service.RAGEngine') as MockRAGEngine, \
|
||||
patch('app.services.config_service.DatabaseEngine'):
|
||||
|
||||
mock_rag_engine = MagicMock()
|
||||
mock_rag_engine.search = MagicMock(return_value=[
|
||||
{"content": "Rule 1"},
|
||||
{"content": "Rule 2"}
|
||||
])
|
||||
MockRAGEngine.return_value = mock_rag_engine
|
||||
|
||||
service = ConfigService()
|
||||
rules = service._get_platform_rules("5")
|
||||
|
||||
assert "Rule 1" in rules
|
||||
assert "Rule 2" in rules
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_similar_cases():
|
||||
"""Test similar cases retrieval."""
|
||||
with patch('app.services.config_service.ClaudeEngine'), \
|
||||
patch('app.services.config_service.RAGEngine') as MockRAGEngine, \
|
||||
patch('app.services.config_service.DatabaseEngine'):
|
||||
|
||||
mock_rag_engine = MagicMock()
|
||||
mock_rag_engine.search = MagicMock(return_value=[
|
||||
{"content": "Case 1"},
|
||||
{"content": "Case 2"}
|
||||
])
|
||||
MockRAGEngine.return_value = mock_rag_engine
|
||||
|
||||
service = ConfigService()
|
||||
cases = service._get_similar_cases("销售订单")
|
||||
|
||||
assert "Case 1" in cases
|
||||
assert "Case 2" in cases
|
||||
25
backend/tests/test_db_engine.py
Normal file
25
backend/tests/test_db_engine.py
Normal file
@@ -0,0 +1,25 @@
|
||||
import pytest
|
||||
from app.core.db_engine import DatabaseEngine
|
||||
|
||||
|
||||
def test_database_engine_init():
|
||||
"""测试数据库引擎初始化"""
|
||||
engine = DatabaseEngine()
|
||||
assert engine.engine is not None
|
||||
assert engine.Session is not None
|
||||
|
||||
|
||||
def test_execute_sql_select():
|
||||
"""测试执行 SELECT 查询"""
|
||||
engine = DatabaseEngine()
|
||||
result = engine.execute_sql("SELECT 1 AS test")
|
||||
assert result is not None
|
||||
assert len(result) > 0
|
||||
|
||||
|
||||
def test_table_exists():
|
||||
"""测试表存在性检查"""
|
||||
engine = DatabaseEngine()
|
||||
# 假设 SYS_FORM 表存在
|
||||
exists = engine.table_exists("SYS_FORM")
|
||||
assert exists is True
|
||||
141
backend/tests/test_executor.py
Normal file
141
backend/tests/test_executor.py
Normal file
@@ -0,0 +1,141 @@
|
||||
"""Tests for Config Executor.
|
||||
|
||||
This module tests the ConfigExecutor class for SQL validation and execution.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, patch
|
||||
from app.core.executor import ConfigExecutor
|
||||
|
||||
|
||||
def test_executor_init():
|
||||
"""Test executor initialization."""
|
||||
executor = ConfigExecutor()
|
||||
assert executor.db_engine is not None
|
||||
|
||||
|
||||
def test_validate_sql_safe():
|
||||
"""Test validation of safe SQL statements."""
|
||||
executor = ConfigExecutor()
|
||||
|
||||
# Test SELECT
|
||||
is_valid, msg = executor.validate_sql("SELECT * FROM SYS_FORM")
|
||||
assert is_valid is True
|
||||
assert "验证通过" in msg
|
||||
|
||||
# Test INSERT
|
||||
is_valid, msg = executor.validate_sql(
|
||||
"INSERT INTO SYS_FORM (IKEY, FORM_NAME) VALUES (1, 'Test')"
|
||||
)
|
||||
assert is_valid is True
|
||||
|
||||
# Test UPDATE with safe WHERE clause
|
||||
is_valid, msg = executor.validate_sql(
|
||||
"UPDATE SYS_FORM SET FORM_NAME = 'Test' WHERE IKEY = 1"
|
||||
)
|
||||
assert is_valid is True
|
||||
|
||||
|
||||
def test_validate_sql_dangerous():
|
||||
"""Test validation catches dangerous SQL statements."""
|
||||
executor = ConfigExecutor()
|
||||
|
||||
# Test DROP DATABASE
|
||||
is_valid, msg = executor.validate_sql("DROP DATABASE test_db")
|
||||
assert is_valid is False
|
||||
assert "危险操作" in msg
|
||||
|
||||
# Test DROP TABLE
|
||||
is_valid, msg = executor.validate_sql("DROP TABLE users")
|
||||
assert is_valid is False
|
||||
assert "危险操作" in msg
|
||||
|
||||
# Test TRUNCATE
|
||||
is_valid, msg = executor.validate_sql("TRUNCATE TABLE important_data")
|
||||
assert is_valid is False
|
||||
assert "危险操作" in msg
|
||||
|
||||
# Test DELETE without WHERE
|
||||
is_valid, msg = executor.validate_sql("DELETE FROM users")
|
||||
assert is_valid is False
|
||||
assert "危险操作" in msg
|
||||
|
||||
|
||||
def test_execute_config_success():
|
||||
"""Test successful execution of SQL list."""
|
||||
with patch('app.core.executor.DatabaseEngine') as MockDBEngine:
|
||||
mock_db_engine = MagicMock()
|
||||
mock_db_engine.execute_transaction = MagicMock(return_value=True)
|
||||
MockDBEngine.return_value = mock_db_engine
|
||||
|
||||
executor = ConfigExecutor()
|
||||
|
||||
sql_list = [
|
||||
"INSERT INTO SYS_FORM (IKEY, FORM_NAME) VALUES (1, 'Test1')",
|
||||
"INSERT INTO SYS_FORM (IKEY, FORM_NAME) VALUES (2, 'Test2')"
|
||||
]
|
||||
|
||||
result = executor.execute_config(sql_list, session_id="test-session")
|
||||
|
||||
assert result["success"] is True
|
||||
assert len(result["executed"]) == 2
|
||||
assert result["failed"] is None
|
||||
assert "成功执行" in result["message"]
|
||||
|
||||
|
||||
def test_execute_config_validation_failure():
|
||||
"""Test execution fails when SQL validation fails."""
|
||||
executor = ConfigExecutor()
|
||||
|
||||
sql_list = [
|
||||
"SELECT * FROM SYS_FORM",
|
||||
"DROP DATABASE test" # Dangerous SQL
|
||||
]
|
||||
|
||||
result = executor.execute_config(sql_list, session_id="test-session")
|
||||
|
||||
assert result["success"] is False
|
||||
assert result["failed"] is not None
|
||||
assert "验证失败" in result["message"]
|
||||
assert len(result["executed"]) == 0
|
||||
|
||||
|
||||
def test_execute_config_execution_failure():
|
||||
"""Test execution handles database errors."""
|
||||
with patch('app.core.executor.DatabaseEngine') as MockDBEngine:
|
||||
mock_db_engine = MagicMock()
|
||||
mock_db_engine.execute_transaction = MagicMock(
|
||||
side_effect=Exception("Database connection error")
|
||||
)
|
||||
MockDBEngine.return_value = mock_db_engine
|
||||
|
||||
executor = ConfigExecutor()
|
||||
|
||||
sql_list = ["SELECT * FROM SYS_FORM"]
|
||||
|
||||
result = executor.execute_config(sql_list, session_id="test-session")
|
||||
|
||||
assert result["success"] is False
|
||||
assert result["failed"] is not None
|
||||
assert "执行失败" in result["message"]
|
||||
|
||||
|
||||
def test_rollback_placeholder():
|
||||
"""Test rollback functionality placeholder."""
|
||||
executor = ConfigExecutor()
|
||||
|
||||
result = executor.rollback(session_id="test-session")
|
||||
|
||||
assert result["success"] is False
|
||||
assert "待实现" in result["message"]
|
||||
|
||||
|
||||
def test_dangerous_keywords_exist():
|
||||
"""Test that dangerous keywords list is properly defined."""
|
||||
executor = ConfigExecutor()
|
||||
|
||||
assert hasattr(executor, 'DANGEROUS_KEYWORDS')
|
||||
assert len(executor.DANGEROUS_KEYWORDS) > 0
|
||||
assert "DROP DATABASE" in executor.DANGEROUS_KEYWORDS
|
||||
assert "DROP TABLE" in executor.DANGEROUS_KEYWORDS
|
||||
assert "TRUNCATE TABLE" in executor.DANGEROUS_KEYWORDS
|
||||
36
backend/tests/test_prompts.py
Normal file
36
backend/tests/test_prompts.py
Normal file
@@ -0,0 +1,36 @@
|
||||
"""Tests for prompt templates."""
|
||||
|
||||
from app.core.prompts import SYSTEM_PROMPT, ANALYZE_PROMPT_TEMPLATE, GENERATE_PROMPT_TEMPLATE
|
||||
|
||||
|
||||
def test_system_prompt_exists():
|
||||
"""测试系统 Prompt 存在"""
|
||||
assert SYSTEM_PROMPT is not None
|
||||
assert len(SYSTEM_PROMPT) > 100
|
||||
# Test for stable characteristics rather than exact wording
|
||||
assert "ERP" in SYSTEM_PROMPT
|
||||
assert "配置" in SYSTEM_PROMPT
|
||||
|
||||
|
||||
def test_analyze_prompt_template():
|
||||
"""测试需求解析模板"""
|
||||
rendered = ANALYZE_PROMPT_TEMPLATE.format(
|
||||
user_input="创建销售订单",
|
||||
knowledge_context="测试知识",
|
||||
existing_tables="测试表"
|
||||
)
|
||||
assert "创建销售订单" in rendered
|
||||
assert "测试知识" in rendered
|
||||
assert "测试表" in rendered
|
||||
|
||||
|
||||
def test_generate_prompt_template():
|
||||
"""测试配置生成模板"""
|
||||
rendered = GENERATE_PROMPT_TEMPLATE.format(
|
||||
requirements="需求分析结果",
|
||||
platform_rules="平台规则",
|
||||
similar_cases="类似案例"
|
||||
)
|
||||
assert "需求分析结果" in rendered
|
||||
assert "平台规则" in rendered
|
||||
assert "类似案例" in rendered
|
||||
156
backend/tests/test_rag_engine.py
Normal file
156
backend/tests/test_rag_engine.py
Normal file
@@ -0,0 +1,156 @@
|
||||
"""Tests for RAG Engine.
|
||||
|
||||
This module tests the RAGEngine class for document indexing and retrieval.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, patch
|
||||
from app.core.rag_engine import RAGEngine
|
||||
|
||||
|
||||
def test_rag_engine_init():
|
||||
"""Test RAG engine initialization."""
|
||||
engine = RAGEngine()
|
||||
assert engine.chroma_client is not None
|
||||
assert engine.documents_collection is not None
|
||||
assert engine.chunk_size > 0
|
||||
assert engine.chunk_overlap >= 0
|
||||
assert engine.chunk_overlap < engine.chunk_size
|
||||
|
||||
|
||||
def test_split_text_basic():
|
||||
"""Test basic text splitting functionality."""
|
||||
engine = RAGEngine()
|
||||
|
||||
# Test with text longer than chunk_size
|
||||
long_text = "A" * 1000
|
||||
chunks = engine._split_text(long_text)
|
||||
|
||||
assert len(chunks) > 0
|
||||
assert all(len(chunk) <= engine.chunk_size for chunk in chunks)
|
||||
assert all(chunk.strip() for chunk in chunks) # No empty chunks
|
||||
|
||||
|
||||
def test_split_text_empty():
|
||||
"""Test splitting empty text."""
|
||||
engine = RAGEngine()
|
||||
|
||||
# Test with empty text
|
||||
assert engine._split_text("") == []
|
||||
assert engine._split_text(" ") == []
|
||||
|
||||
|
||||
def test_split_text_overlap():
|
||||
"""Test text splitting with overlap."""
|
||||
engine = RAGEngine()
|
||||
|
||||
# Test that chunks overlap correctly
|
||||
text = "A" * 600
|
||||
chunks = engine._split_text(text)
|
||||
|
||||
if len(chunks) > 1:
|
||||
# Check overlap exists between consecutive chunks
|
||||
# (This is a basic check; actual overlap content depends on implementation)
|
||||
assert len(chunks) > 1
|
||||
|
||||
|
||||
def test_add_document_success():
|
||||
"""Test adding a document to the knowledge base."""
|
||||
engine = RAGEngine()
|
||||
|
||||
# Mock the collection's add method
|
||||
engine.documents_collection.add = MagicMock()
|
||||
|
||||
doc_id = "test_doc_1"
|
||||
content = "This is a test document for the knowledge base."
|
||||
metadata = {"source": "test", "type": "sample"}
|
||||
|
||||
num_chunks = engine.add_document(doc_id, content, metadata)
|
||||
|
||||
assert num_chunks > 0
|
||||
assert engine.documents_collection.add.called
|
||||
|
||||
# Verify add was called with correct parameters
|
||||
call_args = engine.documents_collection.add.call_args
|
||||
assert "ids" in call_args.kwargs
|
||||
assert "embeddings" in call_args.kwargs
|
||||
assert "documents" in call_args.kwargs
|
||||
assert "metadatas" in call_args.kwargs
|
||||
|
||||
|
||||
def test_add_document_empty_content():
|
||||
"""Test that adding empty document raises ValueError."""
|
||||
engine = RAGEngine()
|
||||
|
||||
with pytest.raises(ValueError, match="Cannot add empty document"):
|
||||
engine.add_document("test_doc", "")
|
||||
|
||||
with pytest.raises(ValueError, match="Cannot add empty document"):
|
||||
engine.add_document("test_doc", " ")
|
||||
|
||||
|
||||
def test_search_basic():
|
||||
"""Test basic search functionality."""
|
||||
engine = RAGEngine()
|
||||
|
||||
# Mock the collection's query method
|
||||
mock_results = {
|
||||
"documents": [["Result 1", "Result 2"]],
|
||||
"metadatas": [[{"doc_id": "doc1"}, {"doc_id": "doc2"}]],
|
||||
"distances": [[0.1, 0.2]]
|
||||
}
|
||||
engine.documents_collection.query = MagicMock(return_value=mock_results)
|
||||
|
||||
results = engine.search("test query", top_k=2)
|
||||
|
||||
assert len(results) == 2
|
||||
assert results[0]["content"] == "Result 1"
|
||||
assert results[0]["metadata"]["doc_id"] == "doc1"
|
||||
assert results[0]["distance"] == 0.1
|
||||
assert engine.documents_collection.query.called
|
||||
|
||||
|
||||
def test_search_empty_query():
|
||||
"""Test search with empty query returns empty results."""
|
||||
engine = RAGEngine()
|
||||
|
||||
results = engine.search("", top_k=3)
|
||||
assert results == []
|
||||
|
||||
results = engine.search(" ", top_k=3)
|
||||
assert results == []
|
||||
|
||||
|
||||
def test_search_invalid_top_k():
|
||||
"""Test that search with invalid top_k raises ValueError."""
|
||||
engine = RAGEngine()
|
||||
|
||||
with pytest.raises(ValueError, match="top_k cannot exceed 100"):
|
||||
engine.search("test", top_k=101)
|
||||
|
||||
|
||||
def test_delete_chunks_for_doc():
|
||||
"""Test deleting chunks for a document."""
|
||||
engine = RAGEngine()
|
||||
|
||||
# Mock the get and delete methods
|
||||
engine.documents_collection.get = MagicMock(return_value={
|
||||
"ids": ["doc1_chunk_0", "doc1_chunk_1"]
|
||||
})
|
||||
engine.documents_collection.delete = MagicMock()
|
||||
|
||||
engine._delete_chunks_for_doc("doc1")
|
||||
|
||||
assert engine.documents_collection.get.called
|
||||
assert engine.documents_collection.delete.called
|
||||
|
||||
|
||||
def test_close():
|
||||
"""Test closing the RAG engine releases resources."""
|
||||
engine = RAGEngine()
|
||||
|
||||
engine.close()
|
||||
|
||||
assert engine.embedding_model is None
|
||||
assert engine.documents_collection is None
|
||||
assert engine.chroma_client is None
|
||||
116
backend/tests/test_requirement_service.py
Normal file
116
backend/tests/test_requirement_service.py
Normal file
@@ -0,0 +1,116 @@
|
||||
"""Tests for Requirement Service.
|
||||
|
||||
This module tests the RequirementService class for requirement analysis.
|
||||
"""
|
||||
|
||||
import pytest
|
||||
from unittest.mock import MagicMock, AsyncMock, patch
|
||||
from app.services.requirement_service import RequirementService
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_analyze_requirement():
|
||||
"""Test requirement analysis with mocked dependencies."""
|
||||
# Create service with mocked engines
|
||||
with patch('app.services.requirement_service.ClaudeEngine') as MockClaudeEngine, \
|
||||
patch('app.services.requirement_service.RAGEngine') as MockRAGEngine, \
|
||||
patch('app.services.requirement_service.DatabaseEngine') as MockDBEngine:
|
||||
|
||||
# Setup mocks
|
||||
mock_ai_engine = MagicMock()
|
||||
mock_ai_engine.call_claude = AsyncMock(return_value='{"功能名称": "销售订单管理", "功能类型": "列表页面"}')
|
||||
mock_ai_engine.parse_json_response = MagicMock(return_value={
|
||||
"功能名称": "销售订单管理",
|
||||
"功能类型": "列表页面"
|
||||
})
|
||||
MockClaudeEngine.return_value = mock_ai_engine
|
||||
|
||||
mock_rag_engine = MagicMock()
|
||||
mock_rag_engine.search = MagicMock(return_value=[
|
||||
{"content": "Sample knowledge", "metadata": {"source": "docs"}}
|
||||
])
|
||||
MockRAGEngine.return_value = mock_rag_engine
|
||||
|
||||
mock_db_engine = MagicMock()
|
||||
mock_db_engine.execute_sql = MagicMock(return_value=[("SYS_FORM",), ("SYS_MENU",)])
|
||||
MockDBEngine.return_value = mock_db_engine
|
||||
|
||||
# Create service and test
|
||||
service = RequirementService()
|
||||
result = await service.analyze(
|
||||
user_input="创建一个销售订单管理页面",
|
||||
session_id="test-session"
|
||||
)
|
||||
|
||||
assert result is not None
|
||||
assert "功能名称" in result
|
||||
assert result["功能名称"] == "销售订单管理"
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_analyze_requirement_without_session_id():
|
||||
"""Test that session_id is auto-generated if not provided."""
|
||||
with patch('app.services.requirement_service.ClaudeEngine') as MockClaudeEngine, \
|
||||
patch('app.services.requirement_service.RAGEngine') as MockRAGEngine, \
|
||||
patch('app.services.requirement_service.DatabaseEngine') as MockDBEngine:
|
||||
|
||||
# Setup mocks
|
||||
mock_ai_engine = MagicMock()
|
||||
mock_ai_engine.call_claude = AsyncMock(return_value='{"功能名称": "测试功能"}')
|
||||
mock_ai_engine.parse_json_response = MagicMock(return_value={"功能名称": "测试功能"})
|
||||
MockClaudeEngine.return_value = mock_ai_engine
|
||||
|
||||
mock_rag_engine = MagicMock()
|
||||
mock_rag_engine.search = MagicMock(return_value=[])
|
||||
MockRAGEngine.return_value = mock_rag_engine
|
||||
|
||||
mock_db_engine = MagicMock()
|
||||
mock_db_engine.execute_sql = MagicMock(return_value=[])
|
||||
MockDBEngine.return_value = mock_db_engine
|
||||
|
||||
# Test without session_id
|
||||
service = RequirementService()
|
||||
result = await service.analyze(user_input="测试输入")
|
||||
|
||||
assert result is not None
|
||||
assert "功能名称" in result
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_existing_tables_success():
|
||||
"""Test successful retrieval of existing tables."""
|
||||
with patch('app.services.requirement_service.ClaudeEngine'), \
|
||||
patch('app.services.requirement_service.RAGEngine'), \
|
||||
patch('app.services.requirement_service.DatabaseEngine') as MockDBEngine:
|
||||
|
||||
mock_db_engine = MagicMock()
|
||||
mock_db_engine.execute_sql = MagicMock(return_value=[
|
||||
("SYS_FORM",),
|
||||
("SYS_MENU",),
|
||||
("SYS_USER",)
|
||||
])
|
||||
MockDBEngine.return_value = mock_db_engine
|
||||
|
||||
service = RequirementService()
|
||||
tables = service._get_existing_tables("测试")
|
||||
|
||||
assert "SYS_FORM" in tables
|
||||
assert "SYS_MENU" in tables
|
||||
assert "SYS_USER" in tables
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_existing_tables_failure():
|
||||
"""Test handling of database query failure."""
|
||||
with patch('app.services.requirement_service.ClaudeEngine'), \
|
||||
patch('app.services.requirement_service.RAGEngine'), \
|
||||
patch('app.services.requirement_service.DatabaseEngine') as MockDBEngine:
|
||||
|
||||
mock_db_engine = MagicMock()
|
||||
mock_db_engine.execute_sql = MagicMock(side_effect=Exception("DB Error"))
|
||||
MockDBEngine.return_value = mock_db_engine
|
||||
|
||||
service = RequirementService()
|
||||
tables = service._get_existing_tables("测试")
|
||||
|
||||
assert "无法获取现有表信息" in tables
|
||||
146
docs/CLAUDE_API_CONFIG.md
Normal file
146
docs/CLAUDE_API_CONFIG.md
Normal file
@@ -0,0 +1,146 @@
|
||||
# Claude API 配置指南
|
||||
|
||||
## 概述
|
||||
|
||||
本项目支持自定义 Anthropic API 的 base URL，允许您使用代理服务或自托管服务。
|
||||
|
||||
## 配置方法
|
||||
|
||||
### 1. 使用官方 Anthropic API（默认）
|
||||
|
||||
在 `.env` 文件中配置：
|
||||
|
||||
```bash
|
||||
ANTHROPIC_API_KEY=your-api-key-here
|
||||
# 不需要设置 ANTHROPIC_BASE_URL，将自动使用官方 API
|
||||
```
|
||||
|
||||
### 2. 使用代理服务
|
||||
|
||||
如果您使用代理服务（例如 OpenRouter、AWS Bedrock 代理等），配置如下：
|
||||
|
||||
```bash
|
||||
ANTHROPIC_API_KEY=your-api-key-here
|
||||
ANTHROPIC_BASE_URL=https://your-proxy-service.com/v1
|
||||
```
|
||||
|
||||
### 3. 使用自托管服务
|
||||
|
||||
如果您部署了自托管的 Claude API 兼容服务：
|
||||
|
||||
```bash
|
||||
ANTHROPIC_API_KEY=your-custom-key
|
||||
ANTHROPIC_BASE_URL=http://localhost:8080/v1
|
||||
```
|
||||
|
||||
## 配置参数说明
|
||||
|
||||
| 参数 | 类型 | 必需 | 默认值 | 说明 |
|
||||
|------|------|------|--------|------|
|
||||
| `ANTHROPIC_API_KEY` | string | ✅ 是 | - | Anthropic API 密钥或自定义密钥 |
|
||||
| `ANTHROPIC_BASE_URL` | string | ❌ 否 | `None` | 自定义 API 端点 URL |
|
||||
| `CLAUDE_MODEL` | string | ❌ 否 | `claude-sonnet-4-6` | 使用的模型名称 |
|
||||
| `CLAUDE_MAX_TOKENS` | int | ❌ 否 | `8192` | 最大生成 token 数 |
|
||||
| `CLAUDE_TEMPERATURE` | float | ❌ 否 | `0.7` | 生成温度（0-2） |
|
||||
|
||||
## 支持的代理服务示例
|
||||
|
||||
### OpenRouter
|
||||
|
||||
```bash
|
||||
ANTHROPIC_API_KEY=sk-or-xxx
|
||||
ANTHROPIC_BASE_URL=https://openrouter.ai/api/v1
|
||||
CLAUDE_MODEL=anthropic/claude-sonnet-4-6
|
||||
```
|
||||
|
||||
### AWS Bedrock (通过代理)
|
||||
|
||||
```bash
|
||||
ANTHROPIC_API_KEY=your-aws-key
|
||||
ANTHROPIC_BASE_URL=https://bedrock.us-east-1.amazonaws.com
|
||||
CLAUDE_MODEL=anthropic.claude-3-sonnet-20240229-v1:0
|
||||
```
|
||||
|
||||
### Azure OpenAI (Claude 兼容)
|
||||
|
||||
```bash
|
||||
ANTHROPIC_API_KEY=your-azure-key
|
||||
ANTHROPIC_BASE_URL=https://your-resource.openai.azure.com
|
||||
CLAUDE_MODEL=claude-sonnet-4-6
|
||||
```
|
||||
|
||||
## 代码实现
|
||||
|
||||
配置在以下文件中实现：
|
||||
|
||||
1. **配置定义**: `backend/app/config.py`
|
||||
```python
|
||||
ANTHROPIC_BASE_URL: str | None = None # Optional custom base URL
|
||||
```
|
||||
|
||||
2. **API 客户端初始化**: `backend/app/core/ai_engine.py`
|
||||
```python
|
||||
client_kwargs = {"api_key": settings.ANTHROPIC_API_KEY}
|
||||
if settings.ANTHROPIC_BASE_URL:
|
||||
client_kwargs["base_url"] = settings.ANTHROPIC_BASE_URL
|
||||
self.client = anthropic.AsyncAnthropic(**client_kwargs)
|
||||
```
|
||||
|
||||
## 验证配置
|
||||
|
||||
启动后端服务后，检查日志输出：
|
||||
|
||||
```
|
||||
[INFO] Using custom Anthropic base URL: https://your-proxy.com
|
||||
```
|
||||
|
||||
如果看到此日志，说明自定义 base URL 已生效。
|
||||
|
||||
## 故障排查
|
||||
|
||||
### 问题 1: 连接超时
|
||||
|
||||
**症状**: API 调用超时或连接失败
|
||||
|
||||
**解决方案**:
|
||||
- 检查 `ANTHROPIC_BASE_URL` 是否正确
|
||||
- 确认代理服务可访问
|
||||
- 检查网络防火墙设置
|
||||
|
||||
### 问题 2: 认证失败
|
||||
|
||||
**症状**: 401 Unauthorized 错误
|
||||
|
||||
**解决方案**:
|
||||
- 验证 `ANTHROPIC_API_KEY` 是否正确
|
||||
- 确认代理服务的认证方式
|
||||
- 检查 API key 是否有权限访问指定模型
|
||||
|
||||
### 问题 3: 模型不存在
|
||||
|
||||
**症状**: 404 Not Found - Model not found
|
||||
|
||||
**解决方案**:
|
||||
- 确认代理服务支持您指定的 `CLAUDE_MODEL`
|
||||
- 检查模型名称格式（不同服务可能使用不同的命名）
|
||||
|
||||
## 安全建议
|
||||
|
||||
1. **不要提交 `.env` 文件到 Git**
|
||||
- `.env` 文件已在 `.gitignore` 中
|
||||
- 只提交 `.env.example` 模板
|
||||
|
||||
2. **生产环境配置**
|
||||
- 使用环境变量或密钥管理服务
|
||||
- 不要在代码中硬编码 API key
|
||||
|
||||
3. **API Key 权限**
|
||||
- 使用最小权限原则
|
||||
- 定期轮换 API key
|
||||
- 监控 API 使用情况
|
||||
|
||||
## 相关文档
|
||||
|
||||
- [Anthropic API 文档](https://docs.anthropic.com/)
|
||||
- [OpenRouter 文档](https://openrouter.ai/docs)
|
||||
- [项目 README](./README.md)
|
||||
288
docs/DEPENDENCY_FIXES.md
Normal file
288
docs/DEPENDENCY_FIXES.md
Normal file
@@ -0,0 +1,288 @@
|
||||
# 依赖问题修复指南
|
||||
|
||||
## 🐛 已知问题及解决方案
|
||||
|
||||
### 问题 1: NumPy 2.0 兼容性错误 ✅ 已修复
|
||||
|
||||
**错误信息:**
|
||||
```
|
||||
AttributeError: `np.float_` was removed in the NumPy 2.0 release. Use `np.float64` instead.
|
||||
```
|
||||
|
||||
**原因:**
|
||||
- ChromaDB 0.4.18 依赖旧版 NumPy API
|
||||
- NumPy 2.0 移除了 `np.float_` 等类型别名
|
||||
- 版本冲突导致运行失败
|
||||
|
||||
**解决方案:**
|
||||
已在 `requirements.txt` 中添加约束：
|
||||
```txt
|
||||
numpy<2.0.0
|
||||
```
|
||||
|
||||
### 问题 2: Sentence-Transformers 与 HuggingFace Hub 不兼容 ✅ 已修复
|
||||
|
||||
**错误信息:**
|
||||
```
|
||||
ImportError: cannot import name 'cached_download' from 'huggingface_hub'
|
||||
```
|
||||
|
||||
**原因:**
|
||||
- sentence-transformers 2.2.2 使用了已弃用的 `cached_download` API
|
||||
- 新版 huggingface_hub 移除了该 API
|
||||
|
||||
**解决方案:**
|
||||
已升级到兼容版本：
|
||||
```txt
|
||||
sentence-transformers==2.7.0 # 从 2.2.2 升级
|
||||
```
|
||||
|
||||
**修复步骤:**
|
||||
```bash
|
||||
cd backend
|
||||
source venv/bin/activate # Windows: venv\Scripts\activate
|
||||
|
||||
# 卸载当前 numpy
|
||||
pip uninstall numpy -y
|
||||
|
||||
# 重新安装依赖（会安装 numpy 1.x）
|
||||
pip install -r requirements.txt
|
||||
|
||||
# 验证 numpy 版本
|
||||
python -c "import numpy; print(numpy.__version__)"
|
||||
# 应输出: 1.x.x (小于 2.0)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📦 依赖版本说明
|
||||
|
||||
### 核心依赖版本
|
||||
|
||||
| 包名 | 版本 | 说明 |
|
||||
|------|------|------|
|
||||
| numpy | < 2.0.0 | 降级以兼容 chromadb |
|
||||
| chromadb | 0.4.18 | 向量数据库 |
|
||||
| sentence-transformers | 2.2.2 | 文本嵌入模型 |
|
||||
| fastapi | 0.104.1 | Web 框架 |
|
||||
| anthropic | 0.18.1 | Claude API SDK |
|
||||
| pydantic | 2.5.0 | 数据验证 |
|
||||
|
||||
### 为什么锁定版本？
|
||||
|
||||
1. **兼容性保证**: 避免主版本升级引入破坏性更改
|
||||
2. **可重现构建**: 确保开发和生产环境一致
|
||||
3. **安全性**: 便于安全审计和漏洞修复
|
||||
|
||||
---
|
||||
|
||||
## 🔄 更新依赖
|
||||
|
||||
### 更新单个包
|
||||
|
||||
```bash
|
||||
pip install --upgrade package-name
|
||||
pip freeze > requirements.txt # 更新版本
|
||||
```
|
||||
|
||||
### 更新所有包（谨慎）
|
||||
|
||||
```bash
|
||||
pip install --upgrade pip
|
||||
pip-review --auto # 需要 pip-review 工具
|
||||
```
|
||||
|
||||
### 安全更新
|
||||
|
||||
仅更新补丁版本（修复 bug 和安全漏洞）：
|
||||
```bash
|
||||
pip install --upgrade package-name==1.2.* # 保持在 1.2.x
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## ⚠️ 常见依赖问题
|
||||
|
||||
### 问题 1: pip 安装超时
|
||||
|
||||
**解决方案:**
|
||||
```bash
|
||||
# 使用国内镜像
|
||||
pip install -r requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
|
||||
|
||||
# 或配置全局镜像
|
||||
pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
|
||||
```
|
||||
|
||||
### 问题 2: pyodbc 安装失败
|
||||
|
||||
**原因:** 缺少 ODBC 驱动开发包
|
||||
|
||||
**解决方案:**
|
||||
|
||||
**Ubuntu/Debian:**
|
||||
```bash
|
||||
sudo apt-get install unixodbc-dev
|
||||
pip install pyodbc
|
||||
```
|
||||
|
||||
**CentOS/RHEL:**
|
||||
```bash
|
||||
sudo yum install unixODBC-devel
|
||||
pip install pyodbc
|
||||
```
|
||||
|
||||
**Windows:**
|
||||
无需额外操作，直接安装即可。
|
||||
|
||||
### 问题 3: sentence-transformers 下载模型慢
|
||||
|
||||
**原因:** HuggingFace 模型下载速度慢
|
||||
|
||||
**解决方案:**
|
||||
```bash
|
||||
# 使用镜像站
|
||||
export HF_ENDPOINT=https://hf-mirror.com
|
||||
|
||||
# 或在 Python 代码中设置
|
||||
import os
|
||||
os.environ['HF_ENDPOINT'] = 'https://hf-mirror.com'
|
||||
```
|
||||
|
||||
### 问题 4: ChromaDB 初始化错误
|
||||
|
||||
**可能原因:**
|
||||
- 权限问题
|
||||
- SQLite 版本过低
|
||||
- 磁盘空间不足
|
||||
|
||||
**解决方案:**
|
||||
```bash
|
||||
# 检查目录权限
|
||||
chmod -R 755 backend/knowledge_base/
|
||||
|
||||
# 检查 SQLite 版本（需要 >= 3.35.0）
|
||||
python -c "import sqlite3; print(sqlite3.sqlite_version)"
|
||||
|
||||
# 清理并重新初始化
|
||||
rm -rf backend/knowledge_base/chroma_db
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🔍 依赖诊断命令
|
||||
|
||||
### 检查已安装版本
|
||||
|
||||
```bash
|
||||
# 列出所有包
|
||||
pip list
|
||||
|
||||
# 查看特定包信息
|
||||
pip show numpy
|
||||
|
||||
# 检查过时的包
|
||||
pip list --outdated
|
||||
|
||||
# 检查安全漏洞
|
||||
pip audit # 需要 pip-audit 工具
|
||||
```
|
||||
|
||||
### 依赖树分析
|
||||
|
||||
```bash
|
||||
# 安装 pipdeptree
|
||||
pip install pipdeptree
|
||||
|
||||
# 查看依赖树
|
||||
pipdeptree
|
||||
|
||||
# 查看反向依赖（谁依赖了这个包）
|
||||
pipdeptree -r -p numpy
|
||||
```
|
||||
|
||||
### 冲突检测
|
||||
|
||||
```bash
|
||||
# 检查依赖冲突
|
||||
pip check
|
||||
|
||||
# 查看版本约束
|
||||
pip-compile --dry-run requirements.txt
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 📝 最佳实践
|
||||
|
||||
### 1. 使用虚拟环境
|
||||
|
||||
```bash
|
||||
# 创建虚拟环境
|
||||
python3 -m venv venv
|
||||
|
||||
# 激活虚拟环境
|
||||
source venv/bin/activate # Linux/Mac
|
||||
venv\Scripts\activate # Windows
|
||||
|
||||
# 确认使用虚拟环境
|
||||
which python # Linux/Mac
|
||||
where python # Windows
|
||||
```
|
||||
|
||||
### 2. 定期更新依赖
|
||||
|
||||
```bash
|
||||
# 每月检查更新
|
||||
pip list --outdated
|
||||
|
||||
# 更新前查看变更日志
|
||||
pip install --upgrade package-name --dry-run
|
||||
```
|
||||
|
||||
### 3. 锁定依赖版本
|
||||
|
||||
```bash
|
||||
# 生成精确版本
|
||||
pip freeze > requirements.txt
|
||||
|
||||
# 或使用 pip-tools
|
||||
pip-compile requirements.in
|
||||
```
|
||||
|
||||
### 4. 分离开发和生产依赖
|
||||
|
||||
创建 `requirements-dev.txt`:
|
||||
```txt
|
||||
-r requirements.txt
|
||||
|
||||
pytest==7.4.3
|
||||
pytest-asyncio==0.21.1
|
||||
pytest-cov==4.1.0
|
||||
pytest-mock==3.12.0
|
||||
httpx==0.25.2
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 🆘 依赖问题排查流程
|
||||
|
||||
1. **确认错误信息** → 找到具体的包名和错误类型
|
||||
2. **检查版本冲突** → `pip check`
|
||||
3. **查看依赖关系** → `pipdeptree -r -p package-name`
|
||||
4. **搜索已知问题** → GitHub Issues / Stack Overflow
|
||||
5. **尝试降级/升级** → 调整版本约束
|
||||
6. **清理重新安装** → `pip cache purge && pip install -r requirements.txt`
|
||||
|
||||
---
|
||||
|
||||
## 📚 相关资源
|
||||
|
||||
- [NumPy 2.0 迁移指南](https://numpy.org/doc/stable/numpy_2_0_migration_guide.html)
|
||||
- [ChromaDB 文档](https://docs.trychroma.com/)
|
||||
- [Python 依赖管理最佳实践](https://packaging.python.org/en/latest/guides/installing-using-pip-and-virtual-environments/)
|
||||
|
||||
---
|
||||
|
||||
**更新时间**: 2026-03-21
|
||||
**适用版本**: v1.0.0+
|
||||
236
docs/FRONTEND_UPDATE.md
Normal file
236
docs/FRONTEND_UPDATE.md
Normal file
@@ -0,0 +1,236 @@
|
||||
# 前端功能完善说明
|
||||
|
||||
## 🎉 已完成的功能
|
||||
|
||||
### 1. 完整的工作流程
|
||||
|
||||
前端现在支持完整的三个步骤工作流程：
|
||||
|
||||
**步骤 1: 需求分析**
|
||||
- 输入自然语言需求
|
||||
- 调用后端 `/api/v1/analyze` 接口
|
||||
- 展示结构化的分析结果
|
||||
|
||||
**步骤 2: 配置生成**
|
||||
- 基于分析结果生成 SQL 配置
|
||||
- 调用后端 `/api/v1/generate` 接口
|
||||
- 展示 SQL 配置语句（只读预览）
|
||||
|
||||
**步骤 3: 执行配置**
|
||||
- 确认对话框（带安全警告）
|
||||
- 调用后端 `/api/v1/execute` 接口
|
||||
- 展示执行结果（成功/失败）
|
||||
|
||||
### 2. 新增功能组件
|
||||
|
||||
#### 📦 API 服务 (`frontend/src/api/index.js`)
|
||||
|
||||
封装了三个核心 API 调用：
|
||||
```javascript
|
||||
analyzeRequirement(data) // 分析需求
|
||||
generateConfig(data) // 生成配置
|
||||
executeConfig(data) // 执行配置
|
||||
```
|
||||
|
||||
#### 🗃️ 状态管理 (`frontend/src/stores/function.js`)
|
||||
|
||||
使用 Pinia 管理全局状态：
|
||||
- `currentSession`: 当前会话 ID
|
||||
- `analysisResult`: 需求分析结果
|
||||
- `configResult`: 配置生成结果
|
||||
- `executeResult`: 执行结果
|
||||
- `loading`: 各步骤加载状态
|
||||
|
||||
#### 🎨 UI 组件增强 (`frontend/src/views/CreateFunction.vue`)
|
||||
|
||||
**步骤指示器:**
|
||||
- 清晰展示当前进度
|
||||
- 三步流程可视化
|
||||
|
||||
**需求分析结果展示:**
|
||||
- 使用 `el-descriptions` 展示基本信息
|
||||
- 使用 `el-table` 展示字段列表
|
||||
- 支持标签显示（功能类型、必填项等）
|
||||
|
||||
**SQL 配置预览:**
|
||||
- 使用等宽字体显示 SQL
|
||||
- 15 行高度文本框
|
||||
- 只读模式，防止误修改
|
||||
|
||||
**执行确认对话框:**
|
||||
- 醒目的安全警告
|
||||
- 列出注意事项
|
||||
- 确认/取消按钮
|
||||
|
||||
**执行结果展示:**
|
||||
- 成功/失败状态图标
|
||||
- 详细消息展示
|
||||
- "创建新功能"按钮重新开始
|
||||
|
||||
### 3. 交互优化
|
||||
|
||||
✅ **加载状态**: 所有异步操作都有 loading 状态
|
||||
✅ **错误处理**: 友好的错误提示消息
|
||||
✅ **表单验证**: 必填项验证
|
||||
✅ **操作确认**: 危险操作二次确认
|
||||
✅ **状态重置**: 支持重新开始整个流程
|
||||
|
||||
## 📋 使用指南
|
||||
|
||||
### 启动前端服务
|
||||
|
||||
```bash
|
||||
cd frontend
|
||||
npm install
|
||||
npm run dev
|
||||
```
|
||||
|
||||
### 访问应用
|
||||
|
||||
- 本地: http://localhost:5173
|
||||
- 局域网: http://192.168.1.100:5173
|
||||
|
||||
### 完整操作流程
|
||||
|
||||
1. **输入需求**
|
||||
```
|
||||
创建一个销售订单管理页面，包含订单号、客户、订单日期、金额字段
|
||||
```
|
||||
|
||||
2. **点击"开始分析需求"**
|
||||
- 等待 1-3 秒（取决于 Claude API 响应时间）
|
||||
- 查看分析结果（功能名称、类型、字段等）
|
||||
|
||||
3. **点击"生成配置方案"**
|
||||
- 等待 AI 生成 SQL 配置
|
||||
- 仔细检查 SQL 语句
|
||||
|
||||
4. **点击"确认并执行"**
|
||||
- 阅读安全警告
|
||||
- 点击"确认执行"按钮
|
||||
- 查看执行结果
|
||||
|
||||
5. **完成**
|
||||
- 成功: 显示成功消息
|
||||
- 失败: 显示错误详情
|
||||
|
||||
## 🔧 技术实现
|
||||
|
||||
### 状态管理流程
|
||||
|
||||
```
|
||||
用户输入
|
||||
↓
|
||||
分析需求 → 保存 analysisResult + sessionId
|
||||
↓
|
||||
生成配置 → 保存 configResult (包含 SQL)
|
||||
↓
|
||||
执行配置 → 保存 executeResult (成功/失败)
|
||||
```
|
||||
|
||||
### API 调用示例
|
||||
|
||||
```javascript
|
||||
// 1. 分析需求
|
||||
const analyzeResult = await analyzeRequirement({
|
||||
content: '创建销售订单管理页面',
|
||||
session_id: null // 后端自动生成
|
||||
})
|
||||
|
||||
// 2. 生成配置
|
||||
const configResult = await generateConfig({
|
||||
session_id: analyzeResult.session_id,
|
||||
requirements: analyzeResult.data
|
||||
})
|
||||
|
||||
// 3. 执行配置
|
||||
const executeResult = await executeConfig({
|
||||
session_id: analyzeResult.session_id,
|
||||
confirmed: true,
|
||||
backup_enabled: true
|
||||
})
|
||||
```
|
||||
|
||||
## ⚠️ 注意事项
|
||||
|
||||
### 1. 后端必须先启动
|
||||
|
||||
前端依赖后端 API，请确保：
|
||||
```bash
|
||||
cd backend
|
||||
python -m app.main
|
||||
```
|
||||
|
||||
### 2. 环境配置
|
||||
|
||||
确保后端 `.env` 已配置：
|
||||
- `ANTHROPIC_API_KEY`: Claude API 密钥
|
||||
- `DB_*`: 数据库连接信息
|
||||
|
||||
### 3. 测试数据
|
||||
|
||||
首次测试建议使用简单的需求：
|
||||
```
|
||||
创建一个简单的用户管理页面
|
||||
```
|
||||
|
||||
### 4. 跨域问题
|
||||
|
||||
开发环境已配置 CORS：
|
||||
- 后端允许所有来源 (`DEBUG=True`)
|
||||
- 前端代理 `/api` 到后端
|
||||
|
||||
## 🐛 已知问题
|
||||
|
||||
### 问题 1: API 超时
|
||||
|
||||
**现象**: 分析需求时超时
|
||||
|
||||
**原因**: Claude API 响应慢或网络问题
|
||||
|
||||
**解决**:
|
||||
- 检查网络连接
|
||||
- 确认 API Key 有效
|
||||
- 查看后端日志
|
||||
|
||||
### 问题 2: 数据库连接失败
|
||||
|
||||
**现象**: 执行配置失败
|
||||
|
||||
**原因**: 数据库配置错误或服务未启动
|
||||
|
||||
**解决**:
|
||||
- 检查 `.env` 数据库配置
|
||||
- 确认 SQL Server 运行中
|
||||
- 测试数据库连接
|
||||
|
||||
## 🚀 后续优化建议
|
||||
|
||||
### 功能增强
|
||||
- [ ] SQL 语法高亮
|
||||
- [ ] 配置导出功能
|
||||
- [ ] 历史记录查看
|
||||
- [ ] 配置模板库
|
||||
- [ ] 批量操作
|
||||
|
||||
### UI/UX 优化
|
||||
- [ ] 深色模式
|
||||
- [ ] 响应式布局优化
|
||||
- [ ] 加载动画优化
|
||||
- [ ] 快捷键支持
|
||||
|
||||
### 性能优化
|
||||
- [ ] API 响应缓存
|
||||
- [ ] 长文本虚拟滚动
|
||||
- [ ] 懒加载优化
|
||||
|
||||
## 📚 相关文档
|
||||
|
||||
- [后端 API 文档](http://localhost:8000/docs)
|
||||
- [局域网访问配置](./LAN_ACCESS.md)
|
||||
- [依赖问题修复](./DEPENDENCY_FIXES.md)
|
||||
|
||||
---
|
||||
|
||||
**更新时间**: 2026-03-21
|
||||
**版本**: v1.1.0
|
||||
266
docs/GIT_GUIDE.md
Normal file
266
docs/GIT_GUIDE.md
Normal file
@@ -0,0 +1,266 @@
|
||||
# Git 操作指南 - 撤回和重新添加文件
|
||||
|
||||
## ✅ 已完成的操作
|
||||
|
||||
### 1. 撤回暂存区
|
||||
|
||||
已执行 `git reset` 命令，清空了暂存区的所有文件。
|
||||
|
||||
## 📝 修改的 .gitignore
|
||||
|
||||
已在 `.gitignore` 中添加以下规则：
|
||||
|
||||
```gitignore
|
||||
# Project specific - 忽略知识库文档
|
||||
backend/knowledge_base/documents/*.docx
|
||||
backend/knowledge_base/documents/*.xlsx
|
||||
backend/knowledge_base/documents/*.pdf
|
||||
backend/knowledge_base/documents/*.pptx
|
||||
backend/knowledge_base/documents/*.vsdx
|
||||
backend/knowledge_base/documents/*.xls
|
||||
|
||||
# Temporary files - 忽略临时文件
|
||||
*.tmp
|
||||
*.temp
|
||||
*.bak
|
||||
*.swp
|
||||
*~
|
||||
|
||||
# Archives - 忽略压缩包
|
||||
*.zip
|
||||
*.tar.gz
|
||||
*.rar
|
||||
*.7z
|
||||
```
|
||||
|
||||
## 🔍 下一步操作
|
||||
|
||||
### 1. 查看将要提交的文件
|
||||
|
||||
先查看哪些文件会被添加：
|
||||
|
||||
```bash
|
||||
# 查看所有未跟踪的文件
|
||||
git status
|
||||
|
||||
# 或者更详细地查看
|
||||
git status --short
|
||||
```
|
||||
|
||||
### 2. 重新添加文件
|
||||
|
||||
确认文件列表无误后：
|
||||
|
||||
```bash
|
||||
# 方式 1: 添加所有文件（推荐）
|
||||
git add .
|
||||
|
||||
# 方式 2: 逐个添加文件类型（更安全）
|
||||
git add backend/app/
|
||||
git add backend/tests/
|
||||
git add backend/*.txt backend/*.ini
|
||||
git add backend/.env.example
|
||||
git add frontend/src/
|
||||
git add frontend/*.json frontend/*.js frontend/*.html
|
||||
git add *.md .gitignore
|
||||
```
|
||||
|
||||
### 3. 检查暂存区
|
||||
|
||||
添加后再次检查：
|
||||
|
||||
```bash
|
||||
# 查看暂存区状态
|
||||
git status
|
||||
|
||||
# 查看暂存区的文件列表
|
||||
git diff --cached --name-only
|
||||
|
||||
# 查看具体改动
|
||||
git diff --cached
|
||||
```
|
||||
|
||||
### 4. 提交
|
||||
|
||||
确认无误后提交：
|
||||
|
||||
```bash
|
||||
git commit -m "feat: implement ERP AI Assistant Phase 1
|
||||
|
||||
- Backend: FastAPI + SQLAlchemy + Claude API + RAG
|
||||
- Frontend: Vue 3 + Element Plus + Pinia
|
||||
- Features: requirement analysis, config generation, safe execution
|
||||
- Security: SQL injection prevention, parameterized queries
|
||||
- Support: LAN access, custom API endpoint"
|
||||
```
|
||||
|
||||
## 🎯 建议忽略的文件
|
||||
|
||||
如果发现还有其他不需要提交的文件，可以在 `.gitignore` 中添加：
|
||||
|
||||
### 常见需要忽略的文件类型
|
||||
|
||||
```gitignore
|
||||
# 大文件
|
||||
*.dmg
|
||||
*.iso
|
||||
*.img
|
||||
|
||||
# 编译产物
|
||||
*.class
|
||||
*.exe
|
||||
*.dll
|
||||
*.so
|
||||
*.dylib
|
||||
|
||||
# 包文件
|
||||
*.jar
|
||||
*.war
|
||||
*.ear
|
||||
|
||||
# 日志文件
|
||||
logs/
|
||||
*.log
|
||||
|
||||
# 数据文件
|
||||
*.csv
|
||||
*.dat
|
||||
*.out
|
||||
|
||||
# 模型文件（如果很大的话）
|
||||
*.model
|
||||
*.pkl
|
||||
*.h5
|
||||
*.pt
|
||||
*.pth
|
||||
```
|
||||
|
||||
### 项目特定的忽略规则
|
||||
|
||||
```gitignore
|
||||
# 知识库向量数据库（可能很大）
|
||||
backend/knowledge_base/chroma_db/
|
||||
|
||||
# 用户上传的文档
|
||||
backend/knowledge_base/documents/
|
||||
|
||||
# 测试覆盖率报告
|
||||
htmlcov/
|
||||
.coverage
|
||||
|
||||
# 本地配置
|
||||
.env.local
|
||||
.env.*.local
|
||||
```
|
||||
|
||||
## 🔧 Git 常用命令
|
||||
|
||||
### 撤回操作
|
||||
|
||||
```bash
|
||||
# 撤回所有已 add 的文件
|
||||
git reset
|
||||
|
||||
# 撤回特定文件
|
||||
git reset <file>
|
||||
|
||||
# 撤回最近一次 commit（保留修改）
|
||||
git reset --soft HEAD~1
|
||||
|
||||
# 撤回最近一次 commit（丢弃修改，慎用）
|
||||
git reset --hard HEAD~1
|
||||
```
|
||||
|
||||
### 查看状态
|
||||
|
||||
```bash
|
||||
# 查看当前状态
|
||||
git status
|
||||
|
||||
# 查看简洁状态
|
||||
git status -s
|
||||
|
||||
# 查看分支信息
|
||||
git branch -a
|
||||
|
||||
# 查看提交历史
|
||||
git log --oneline --graph
|
||||
```
|
||||
|
||||
### 删除已跟踪的文件
|
||||
|
||||
如果某个文件已经被 git 跟踪，想要从版本控制中移除：
|
||||
|
||||
```bash
|
||||
# 从 Git 中移除但保留本地文件
|
||||
git rm --cached <file>
|
||||
|
||||
# 从 Git 和本地都删除
|
||||
git rm <file>
|
||||
|
||||
# 从 Git 中移除整个文件夹
|
||||
git rm -r --cached <directory>
|
||||
```
|
||||
|
||||
## 📋 快速检查清单
|
||||
|
||||
提交前检查：
|
||||
|
||||
- [ ] 是否包含 `.env` 文件？（不应包含）
|
||||
- [ ] 是否包含 `venv/` 或 `node_modules/`？（不应包含）
|
||||
- [ ] 是否包含大文件？（不应包含）
|
||||
- [ ] 是否包含临时文件？（不应包含）
|
||||
- [ ] 是否包含日志文件？（不应包含）
|
||||
- [ ] 是否包含个人配置？（不应包含）
|
||||
|
||||
## 🚨 常见问题
|
||||
|
||||
### 问题 1: 文件已经在 .gitignore 中，但仍然被跟踪
|
||||
|
||||
**原因**: 文件在添加 .gitignore 规则之前就已经被 git 跟踪了
|
||||
|
||||
**解决方案**:
|
||||
```bash
|
||||
# 从 Git 中移除但保留本地文件
|
||||
git rm --cached <file>
|
||||
|
||||
# 然后提交
|
||||
git commit -m "chore: remove tracked file from version control"
|
||||
```
|
||||
|
||||
### 问题 2: 添加了不该添加的文件
|
||||
|
||||
**解决方案**:
|
||||
```bash
|
||||
# 1. 撤回添加
|
||||
git reset
|
||||
|
||||
# 2. 更新 .gitignore
|
||||
|
||||
# 3. 重新添加
|
||||
git add .
|
||||
```
|
||||
|
||||
### 问题 3: 如何只提交特定文件
|
||||
|
||||
**解决方案**:
|
||||
```bash
|
||||
# 只提交代码文件
|
||||
git add *.py *.vue *.js
|
||||
|
||||
# 只提交特定目录
|
||||
git add backend/app/ frontend/src/
|
||||
|
||||
# 交互式添加
|
||||
git add -p
|
||||
```
|
||||
|
||||
## 📚 相关资源
|
||||
|
||||
- [Git 官方文档](https://git-scm.com/doc)
|
||||
- [.gitignore 模板集合](https://github.com/github/gitignore)
|
||||
- [Git Flow 工作流](https://www.atlassian.com/git/tutorials/comparing-workflows/gitflow-workflow)
|
||||
|
||||
---
|
||||
|
||||
**更新时间**: 2026-03-21
|
||||
289
docs/IMPLEMENTATION_REPORT.md
Normal file
289
docs/IMPLEMENTATION_REPORT.md
Normal file
@@ -0,0 +1,289 @@
|
||||
# ERP AI Assistant - Phase 1 实施完成报告
|
||||
|
||||
## 📋 项目概述
|
||||
|
||||
已完成 Phase 1 的所有核心任务，建立了 ERP AI 助手的基础架构和核心功能。
|
||||
|
||||
## ✅ 已完成任务
|
||||
|
||||
### 后端基础设施 (Tasks 1-7)
|
||||
|
||||
1. **项目初始化和配置管理** ✓
|
||||
- 创建 `backend/requirements.txt` - 所有 Python 依赖
|
||||
- 创建 `backend/.env.example` - 环境变量模板
|
||||
- 创建 `backend/app/config.py` - Pydantic v2 配置管理
|
||||
- 实现配置验证和安全编码
|
||||
|
||||
2. **Pytest 配置和测试基础设施** ✓
|
||||
- 创建 `backend/pytest.ini` - pytest 配置
|
||||
- 创建 `backend/tests/conftest.py` - 测试固件和 mocks
|
||||
- 配置 asyncio 支持和覆盖率报告
|
||||
|
||||
3. **数据库引擎实现** ✓
|
||||
- 创建 `backend/app/core/db_engine.py`
|
||||
- 实现连接池管理 (pool_size=20, max_overflow=10)
|
||||
- 实现上下文管理器会话管理
|
||||
- **安全加固**: 使用参数化查询防止 SQL 注入
|
||||
|
||||
4. **AI 引擎基础实现** ✓
|
||||
- 创建 `backend/app/core/ai_engine.py`
|
||||
- 集成 Claude API (Anthropic SDK)
|
||||
- 实现 JSON 响应解析（支持纯 JSON、markdown 代码块、{} 块）
|
||||
|
||||
5. **Prompt 模板设计** ✓
|
||||
- 创建 `backend/app/core/prompts.py`
|
||||
- 定义系统 Prompt 和分析/生成模板
|
||||
|
||||
6. **RAG 引擎基础实现** ✓
|
||||
- 创建 `backend/app/core/rag_engine.py`
|
||||
- 集成 ChromaDB 向量数据库
|
||||
- 集成 sentence-transformers 嵌入模型
|
||||
- 实现文档分块、嵌入和语义搜索
|
||||
|
||||
7. **需求解析服务实现** ✓
|
||||
- 创建 `backend/app/services/requirement_service.py`
|
||||
- 整合 AI 引擎 + RAG 引擎 + 数据库引擎
|
||||
- 实现需求分析流程（知识检索 → 表结构查询 → AI 分析）
|
||||
|
||||
8. **执行引擎实现** ✓
|
||||
- 创建 `backend/app/core/executor.py`
|
||||
- 实现 SQL 安全验证（拦截 DROP/TRUNCATE/DELETE 等）
|
||||
- 实现事务执行和错误处理
|
||||
|
||||
### API 层实现 (Tasks 8-10)
|
||||
|
||||
9. **API 基础结构** ✓
|
||||
- 创建 `backend/app/models/request.py` - 请求模型
|
||||
- 创建 `backend/app/models/response.py` - 响应模型
|
||||
- 创建 `backend/app/main.py` - FastAPI 应用入口
|
||||
- 配置 CORS 中间件
|
||||
|
||||
10. **需求解析 API** ✓
|
||||
- 创建 `backend/app/api/analyze.py`
|
||||
- POST `/api/v1/analyze` - 分析用户需求
|
||||
|
||||
### 前端实现 (Tasks 11-12)
|
||||
|
||||
11. **前端项目初始化** ✓
|
||||
- 创建 `frontend/package.json` - Vue 3 + Vite
|
||||
- 创建 `frontend/vite.config.js` - 开发服务器和代理配置
|
||||
- 创建 `frontend/src/main.js` - 应用入口
|
||||
- 创建 `frontend/src/App.vue` - 根组件
|
||||
|
||||
12. **前端路由和布局** ✓
|
||||
- 创建 `frontend/src/router/index.js` - 路由配置
|
||||
- 创建 `frontend/src/views/Layout.vue` - 主布局（侧边栏 + 头部）
|
||||
- 创建 `frontend/src/views/CreateFunction.vue` - 功能创建页面
|
||||
- 创建 `frontend/src/views/History.vue` - 历史记录页面
|
||||
|
||||
### 执行和配置服务 (Tasks 13-15)
|
||||
|
||||
13. **配置生成服务** ✓
|
||||
- 创建 `backend/app/services/config_service.py`
|
||||
- 创建 `backend/tests/test_config_service.py`
|
||||
- 实现基于需求的 SQL 配置生成
|
||||
|
||||
14. **执行配置 API** ✓
|
||||
- 创建 `backend/app/api/generate.py` - POST `/api/v1/generate`
|
||||
- 创建 `backend/app/api/execute.py` - POST `/api/v1/execute`
|
||||
- 更新 `backend/app/main.py` 注册路由
|
||||
|
||||
## 📁 项目结构
|
||||
|
||||
```
|
||||
/data/erp-ass/
|
||||
├── backend/
|
||||
│ ├── app/
|
||||
│ │ ├── api/
|
||||
│ │ │ ├── __init__.py
|
||||
│ │ │ ├── analyze.py
|
||||
│ │ │ ├── generate.py
|
||||
│ │ │ └── execute.py
|
||||
│ │ ├── core/
|
||||
│ │ │ ├── __init__.py
|
||||
│ │ │ ├── db_engine.py
|
||||
│ │ │ ├── ai_engine.py
|
||||
│ │ │ ├── prompts.py
|
||||
│ │ │ ├── rag_engine.py
|
||||
│ │ │ └── executor.py
|
||||
│ │ ├── models/
|
||||
│ │ │ ├── __init__.py
|
||||
│ │ │ ├── request.py
|
||||
│ │ │ └── response.py
|
||||
│ │ ├── services/
|
||||
│ │ │ ├── __init__.py
|
||||
│ │ │ ├── requirement_service.py
|
||||
│ │ │ └── config_service.py
|
||||
│ │ ├── config.py
|
||||
│ │ └── main.py
|
||||
│ ├── tests/
|
||||
│ │ ├── conftest.py
|
||||
│ │ ├── test_db_engine.py
|
||||
│ │ ├── test_ai_engine.py
|
||||
│ │ ├── test_prompts.py
|
||||
│ │ ├── test_rag_engine.py
|
||||
│ │ ├── test_requirement_service.py
|
||||
│ │ ├── test_config_service.py
|
||||
│ │ └── test_executor.py
|
||||
│ ├── knowledge_base/
|
||||
│ │ └── documents/
|
||||
│ ├── scripts/
|
||||
│ ├── requirements.txt
|
||||
│ ├── pytest.ini
|
||||
│ └── .env.example
|
||||
└── frontend/
|
||||
├── src/
|
||||
│ ├── router/
|
||||
│ │ └── index.js
|
||||
│ ├── views/
|
||||
│ │ ├── Layout.vue
|
||||
│ │ ├── CreateFunction.vue
|
||||
│ │ └── History.vue
|
||||
│ ├── main.js
|
||||
│ └── App.vue
|
||||
├── index.html
|
||||
├── vite.config.js
|
||||
└── package.json
|
||||
```
|
||||
|
||||
## 🔐 安全特性
|
||||
|
||||
1. **SQL 注入防护**
|
||||
- 所有数据库查询使用参数化查询
|
||||
- 危险 SQL 操作拦截（DROP、TRUNCATE、DELETE without WHERE）
|
||||
|
||||
2. **配置安全**
|
||||
- 数据库密码 URL 编码（支持特殊字符）
|
||||
- 环境变量管理敏感信息
|
||||
- Pydantic 配置验证
|
||||
|
||||
3. **事务保护**
|
||||
- 自动提交/回滚机制
|
||||
- 上下文管理器管理会话
|
||||
|
||||
## 🚀 后续步骤
|
||||
|
||||
### 立即需要完成
|
||||
|
||||
1. **安装依赖**
|
||||
```bash
|
||||
cd backend
|
||||
python3 -m venv venv
|
||||
source venv/bin/activate
|
||||
pip install -r requirements.txt
|
||||
|
||||
cd ../frontend
|
||||
npm install
|
||||
```
|
||||
|
||||
2. **配置环境变量**
|
||||
```bash
|
||||
cd backend
|
||||
cp .env.example .env
|
||||
# 编辑 .env 文件，填入真实的数据库和 Claude API 配置
|
||||
```
|
||||
|
||||
3. **局域网访问配置** ✅ 已完成
|
||||
- 前端已配置 `host: '0.0.0.0'`
|
||||
- 后端已配置 `host="0.0.0.0"` 和 CORS 策略
|
||||
- 详细配置参考: [docs/LAN_ACCESS.md](LAN_ACCESS.md)
|
||||
|
||||
4. **初始化知识库**
|
||||
- 将平台文档放入 `backend/knowledge_base/documents/`
|
||||
- 运行知识库初始化脚本（需要创建）
|
||||
|
||||
5. **Git 版本控制**
|
||||
```bash
|
||||
git init
|
||||
git add .
|
||||
git commit -m "feat: implement Phase 1 - ERP AI Assistant foundation"
|
||||
```
|
||||
|
||||
### Phase 2 功能增强
|
||||
|
||||
1. **执行日志和审计系统**
|
||||
- 创建 ExecutionLog 数据模型
|
||||
- 实现审计服务记录所有操作
|
||||
- 前端展示执行历史
|
||||
|
||||
2. **数据库元数据 API**
|
||||
- 提供表结构查询接口
|
||||
- 支持智能表推荐
|
||||
|
||||
3. **知识库管理界面**
|
||||
- 文档上传和管理
|
||||
- 知识库更新和版本控制
|
||||
|
||||
4. **配置预览组件**
|
||||
- SQL 高亮显示
|
||||
- Monaco Editor 集成
|
||||
- 配置对比和修改
|
||||
|
||||
5. **执行监控组件**
|
||||
- 实时进度显示
|
||||
- 错误详情展示
|
||||
- 回滚功能实现
|
||||
|
||||
### Phase 3 高级功能
|
||||
|
||||
1. **错误排查系统**
|
||||
- SQL 日志监控
|
||||
- 智能错误诊断
|
||||
- 修复建议生成
|
||||
|
||||
2. **系统优化**
|
||||
- 性能分析
|
||||
- 缓存管理
|
||||
- 权限优化
|
||||
|
||||
## 📝 注意事项
|
||||
|
||||
1. **环境限制**
|
||||
- 当前环境无法执行 bash 命令（权限超时）
|
||||
- 需要手动执行依赖安装和测试
|
||||
|
||||
2. **数据库配置**
|
||||
- 需要 SQL Server 数据库连接
|
||||
- 确保数据库有 SYS_FORM、SYS_MENU 等系统表
|
||||
|
||||
3. **Claude API**
|
||||
- 需要有效的 Anthropic API Key
|
||||
- 推荐使用 `claude-sonnet-4-6` 模型
|
||||
|
||||
4. **测试覆盖**
|
||||
- 所有测试文件已创建
|
||||
- 使用 mock 避免真实 API 调用
|
||||
- 需要配置环境后运行集成测试
|
||||
|
||||
## 🎯 技术栈总结
|
||||
|
||||
**后端:**
|
||||
- Python 3.10+
|
||||
- FastAPI 0.104.1
|
||||
- SQLAlchemy 2.0.23
|
||||
- Anthropic SDK 0.18.1
|
||||
- ChromaDB 0.4.18
|
||||
- sentence-transformers 2.2.2
|
||||
- Pydantic 2.5.0
|
||||
|
||||
**前端:**
|
||||
- Vue 3.3.8
|
||||
- Vite 5.0.4
|
||||
- Vue Router 4.2.5
|
||||
- Pinia 2.1.7
|
||||
- Element Plus 2.4.3
|
||||
- Axios 1.6.2
|
||||
|
||||
**数据库:**
|
||||
- SQL Server (通过 pyodbc 5.0.1)
|
||||
- ChromaDB (向量数据库)
|
||||
|
||||
**AI 引擎:**
|
||||
- Claude Sonnet 4.6
|
||||
- all-MiniLM-L6-v2 (嵌入模型)
|
||||
|
||||
---
|
||||
|
||||
**实施日期:** 2026-03-21
|
||||
**完成状态:** Phase 1 全部完成 ✓
|
||||
**下一阶段:** Phase 2 - 功能增强
|
||||
319
docs/LAN_ACCESS.md
Normal file
319
docs/LAN_ACCESS.md
Normal file
@@ -0,0 +1,319 @@
|
||||
# 局域网访问配置指南
|
||||
|
||||
## 🌐 配置说明
|
||||
|
||||
本项目已配置支持局域网访问，允许团队在同一局域网内访问前端和后端服务。
|
||||
|
||||
## ✅ 已完成的配置
|
||||
|
||||
### 1. 前端配置 (Vite)
|
||||
|
||||
**文件**: `frontend/vite.config.js`
|
||||
|
||||
```javascript
|
||||
server: {
|
||||
host: '0.0.0.0', // 监听所有网络接口，允许局域网访问
|
||||
port: 5173,
|
||||
proxy: {
|
||||
'/api': {
|
||||
target: 'http://localhost:8000',
|
||||
changeOrigin: true
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### 2. 后端配置 (FastAPI)
|
||||
|
||||
**文件**: `backend/app/main.py`
|
||||
|
||||
- **服务监听**: `host="0.0.0.0"` (已配置，监听所有网络接口)
|
||||
- **CORS 策略**:
|
||||
- 开发模式 (`DEBUG=True`): 允许所有来源 (`allow_origins=["*"]`)
|
||||
- 生产模式: 仅允许 localhost
|
||||
|
||||
## 🚀 使用步骤
|
||||
|
||||
### 1. 获取服务器 IP 地址
|
||||
|
||||
在运行服务的机器上执行：
|
||||
|
||||
**Windows:**
|
||||
```bash
|
||||
ipconfig
|
||||
```
|
||||
查找 "IPv4 地址"，例如：`192.168.1.100`
|
||||
|
||||
**Linux/Mac:**
|
||||
```bash
|
||||
ifconfig
|
||||
# 或
|
||||
ip addr show
|
||||
```
|
||||
查找 `inet` 地址，例如：`inet 192.168.1.100`
|
||||
|
||||
### 2. 启动服务
|
||||
|
||||
**启动后端:**
|
||||
```bash
|
||||
cd backend
|
||||
source venv/bin/activate # Windows: venv\Scripts\activate
|
||||
python -m app.main
|
||||
```
|
||||
|
||||
后端将监听：
|
||||
- `http://0.0.0.0:8000` (所有网络接口)
|
||||
- 可通过 `http://localhost:8000` 或 `http://192.168.1.100:8000` 访问
|
||||
|
||||
**启动前端:**
|
||||
```bash
|
||||
cd frontend
|
||||
npm run dev
|
||||
```
|
||||
|
||||
Vite 将输出：
|
||||
```
|
||||
VITE v5.0.4 ready in xxx ms
|
||||
|
||||
➜ Local: http://localhost:5173/
|
||||
➜ Network: http://192.168.1.100:5173/
|
||||
```
|
||||
|
||||
### 3. 局域网访问
|
||||
|
||||
在同一局域网的其他设备上，使用服务器 IP 地址访问：
|
||||
|
||||
- **前端**: `http://192.168.1.100:5173`
|
||||
- **后端 API**: `http://192.168.1.100:8000`
|
||||
- **API 文档**: `http://192.168.1.100:8000/docs`
|
||||
|
||||
## 🔥 防火墙配置
|
||||
|
||||
如果局域网内无法访问，需要检查防火墙设置。
|
||||
|
||||
### Windows 防火墙
|
||||
|
||||
**方法 1: 允许端口**
|
||||
```powershell
|
||||
# 以管理员身份运行 PowerShell
|
||||
netsh advfirewall firewall add rule name="ERP AI Assistant - Frontend" dir=in action=allow protocol=tcp localport=5173
|
||||
netsh advfirewall firewall add rule name="ERP AI Assistant - Backend" dir=in action=allow protocol=tcp localport=8000
|
||||
```
|
||||
|
||||
**方法 2: 允许应用**
|
||||
1. 打开 "Windows Defender 防火墙"
|
||||
2. 点击 "允许应用通过防火墙"
|
||||
3. 添加 `node.exe` 和 `python.exe`
|
||||
|
||||
### Linux 防火墙
|
||||
|
||||
**UFW (Ubuntu):**
|
||||
```bash
|
||||
sudo ufw allow 5173/tcp
|
||||
sudo ufw allow 8000/tcp
|
||||
sudo ufw reload
|
||||
```
|
||||
|
||||
**Firewalld (CentOS/RHEL):**
|
||||
```bash
|
||||
sudo firewall-cmd --permanent --add-port=5173/tcp
|
||||
sudo firewall-cmd --permanent --add-port=8000/tcp
|
||||
sudo firewall-cmd --reload
|
||||
```
|
||||
|
||||
### 云服务器安全组
|
||||
|
||||
如果运行在云服务器上，需要在安全组中开放端口：
|
||||
- 入站规则: 允许 TCP 端口 5173 和 8000
|
||||
|
||||
## 📱 测试访问
|
||||
|
||||
### 1. 本地测试
|
||||
|
||||
在服务器机器上测试：
|
||||
|
||||
```bash
|
||||
# 测试后端
|
||||
curl http://localhost:8000/health
|
||||
|
||||
# 测试前端（浏览器访问）
|
||||
http://localhost:5173
|
||||
```
|
||||
|
||||
### 2. 局域网测试
|
||||
|
||||
在其他设备上测试：
|
||||
|
||||
```bash
|
||||
# 测试后端（替换为实际 IP）
|
||||
curl http://192.168.1.100:8000/health
|
||||
|
||||
# 测试前端（浏览器访问）
|
||||
http://192.168.1.100:5173
|
||||
```
|
||||
|
||||
## ⚠️ 安全注意事项
|
||||
|
||||
### 开发环境
|
||||
|
||||
当前配置适合开发环境：
|
||||
- ✅ CORS 允许所有来源 (`allow_origins=["*"]`)
|
||||
- ✅ 方便团队协作和测试
|
||||
|
||||
### 生产环境
|
||||
|
||||
**强烈建议**生产环境进行以下调整：
|
||||
|
||||
1. **设置 `DEBUG=False`**
|
||||
```bash
|
||||
# .env
|
||||
DEBUG=False
|
||||
```
|
||||
|
||||
2. **配置具体允许的域名**
|
||||
修改 `backend/app/main.py`:
|
||||
```python
|
||||
allow_origins=[
|
||||
"https://your-domain.com",
|
||||
"https://erp.your-company.com",
|
||||
]
|
||||
```
|
||||
|
||||
3. **使用 HTTPS**
|
||||
- 配置 SSL 证书
|
||||
- 使用 Nginx 反向代理
|
||||
|
||||
4. **使用环境变量管理 CORS**
|
||||
在 `.env` 中配置：
|
||||
```bash
|
||||
ALLOWED_ORIGINS=https://domain1.com,https://domain2.com
|
||||
```
|
||||
|
||||
## 🔧 高级配置
|
||||
|
||||
### 自定义端口
|
||||
|
||||
如果默认端口被占用，可以修改：
|
||||
|
||||
**前端** (`frontend/vite.config.js`):
|
||||
```javascript
|
||||
server: {
|
||||
host: '0.0.0.0',
|
||||
port: 3000, // 自定义端口
|
||||
// ...
|
||||
}
|
||||
```
|
||||
|
||||
**后端** (`backend/app/main.py`):
|
||||
```python
|
||||
uvicorn.run(
|
||||
"app.main:app",
|
||||
host="0.0.0.0",
|
||||
port=8888, # 自定义端口
|
||||
reload=settings.DEBUG
|
||||
)
|
||||
```
|
||||
|
||||
### 使用 Nginx 反向代理
|
||||
|
||||
生产环境推荐使用 Nginx：
|
||||
|
||||
```nginx
|
||||
server {
|
||||
listen 80;
|
||||
server_name erp.your-company.com;
|
||||
|
||||
# 前端
|
||||
location / {
|
||||
proxy_pass http://127.0.0.1:5173;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
}
|
||||
|
||||
# 后端 API
|
||||
location /api/ {
|
||||
proxy_pass http://127.0.0.1:8000/api/;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
## 📊 访问日志
|
||||
|
||||
查看访问日志，确认服务正常运行：
|
||||
|
||||
**前端日志:**
|
||||
```bash
|
||||
# Vite 会显示访问日志
|
||||
npm run dev
|
||||
```
|
||||
|
||||
**后端日志:**
|
||||
```bash
|
||||
# FastAPI/Uvicorn 会显示请求日志
|
||||
python -m app.main
|
||||
```
|
||||
|
||||
## 🐛 故障排查
|
||||
|
||||
### 问题 1: 无法访问
|
||||
|
||||
**症状**: 局域网内其他设备无法访问
|
||||
|
||||
**检查清单:**
|
||||
- ✅ 服务器 IP 地址是否正确
|
||||
- ✅ 防火墙是否开放端口
|
||||
- ✅ 服务是否正在运行
|
||||
- ✅ 是否在同一局域网内
|
||||
|
||||
**诊断命令:**
|
||||
```bash
|
||||
# 测试端口是否开放
|
||||
telnet 192.168.1.100 5173
|
||||
telnet 192.168.1.100 8000
|
||||
|
||||
# 或使用 nc
|
||||
nc -zv 192.168.1.100 5173
|
||||
nc -zv 192.168.1.100 8000
|
||||
```
|
||||
|
||||
### 问题 2: CORS 错误
|
||||
|
||||
**症状**: 浏览器控制台显示 CORS 错误
|
||||
|
||||
**解决方案:**
|
||||
- 确认 `DEBUG=True` 在 `.env` 中
|
||||
- 检查后端 CORS 配置
|
||||
- 查看浏览器控制台错误详情
|
||||
|
||||
### 问题 3: API 代理失败
|
||||
|
||||
**症状**: 前端无法调用后端 API
|
||||
|
||||
**解决方案:**
|
||||
- 检查后端是否在 `localhost:8000` 运行
|
||||
- 确认 Vite proxy 配置正确
|
||||
- 查看浏览器网络请求
|
||||
|
||||
## 📝 快速命令参考
|
||||
|
||||
```bash
|
||||
# 查看本机 IP
|
||||
ipconfig # Windows
|
||||
ifconfig # Linux/Mac
|
||||
ip addr show # Linux
|
||||
|
||||
# 测试端口
|
||||
netstat -an | grep 5173 # Linux/Mac
|
||||
netstat -an | findstr 5173 # Windows
|
||||
|
||||
# 开放防火墙端口
|
||||
sudo ufw allow 5173/tcp # Ubuntu
|
||||
sudo firewall-cmd --add-port=5173/tcp # CentOS
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
**更新时间**: 2026-03-21
|
||||
**适用版本**: v1.0.0+
|
||||
58
docs/QUICK_REFERENCE.md
Normal file
58
docs/QUICK_REFERENCE.md
Normal file
@@ -0,0 +1,58 @@
|
||||
# 快速配置卡片
|
||||
|
||||
## 🎯 局域网访问配置
|
||||
|
||||
### ✅ 已配置项目
|
||||
|
||||
1. **前端** - `frontend/vite.config.js`
|
||||
```javascript
|
||||
host: '0.0.0.0' // ✓ 已添加
|
||||
```
|
||||
|
||||
2. **后端** - `backend/app/main.py`
|
||||
```python
|
||||
host="0.0.0.0" // ✓ 已配置
|
||||
allow_origins=["*"] if settings.DEBUG // ✓ 开发模式允许所有来源
|
||||
```
|
||||
|
||||
### 📋 使用步骤
|
||||
|
||||
```bash
|
||||
# 1. 查看服务器 IP
|
||||
ipconfig # Windows
|
||||
ifconfig # Linux/Mac
|
||||
|
||||
# 2. 启动后端
|
||||
cd backend && python -m app.main
|
||||
|
||||
# 3. 启动前端
|
||||
cd frontend && npm run dev
|
||||
|
||||
# 4. 局域网访问
|
||||
# 前端: http://192.168.1.100:5173
|
||||
# 后端: http://192.168.1.100:8000
|
||||
```
|
||||
|
||||
### 🔥 防火墙快速配置
|
||||
|
||||
**Windows:**
|
||||
```powershell
|
||||
# 管理员 PowerShell
|
||||
netsh advfirewall firewall add rule name="ERP Frontend" dir=in action=allow protocol=tcp localport=5173
|
||||
netsh advfirewall firewall add rule name="ERP Backend" dir=in action=allow protocol=tcp localport=8000
|
||||
```
|
||||
|
||||
**Linux (Ubuntu):**
|
||||
```bash
|
||||
sudo ufw allow 5173/tcp
|
||||
sudo ufw allow 8000/tcp
|
||||
```
|
||||
|
||||
### ⚠️ 安全提醒
|
||||
|
||||
- **开发环境**: `DEBUG=True` (允许所有来源)
|
||||
- **生产环境**: `DEBUG=False` + 配置具体域名
|
||||
|
||||
---
|
||||
|
||||
详细说明: [docs/LAN_ACCESS.md](LAN_ACCESS.md)
|
||||
386
docs/QUICK_START.md
Normal file
386
docs/QUICK_START.md
Normal file
@@ -0,0 +1,386 @@
|
||||
# 🚀 快速上手指南
|
||||
|
||||
## 📋 前置条件
|
||||
|
||||
### 1. 后端配置
|
||||
|
||||
确保已完成后端配置和依赖安装：
|
||||
|
||||
```bash
|
||||
cd backend
|
||||
|
||||
# 安装依赖（如果遇到问题，参考 docs/DEPENDENCY_FIXES.md）
|
||||
pip install -r requirements.txt
|
||||
|
||||
# 配置环境变量
|
||||
cp .env.example .env
|
||||
# 编辑 .env 文件，配置数据库和 Claude API
|
||||
```
|
||||
|
||||
**关键配置项:**
|
||||
```bash
|
||||
# 数据库配置
|
||||
DB_SERVER=192.168.120.19
|
||||
DB_PORT=1433
|
||||
DB_NAME=DMPF_HY
|
||||
DB_USER=sa
|
||||
DB_PASSWORD=your-password
|
||||
|
||||
# Claude API 配置
|
||||
ANTHROPIC_API_KEY=your-claude-api-key
|
||||
# 可选：使用自定义 API 端点
|
||||
# ANTHROPIC_BASE_URL=https://your-proxy.com/v1
|
||||
```
|
||||
|
||||
### 2. 前端配置
|
||||
|
||||
```bash
|
||||
cd frontend
|
||||
|
||||
# 安装依赖
|
||||
npm install
|
||||
```
|
||||
|
||||
## 🎯 启动服务
|
||||
|
||||
### 启动后端
|
||||
|
||||
```bash
|
||||
cd backend
|
||||
source venv/bin/activate # Windows: venv\Scripts\activate
|
||||
python -m app.main
|
||||
```
|
||||
|
||||
**成功输出:**
|
||||
```
|
||||
INFO: Uvicorn running on http://0.0.0.0:8000
|
||||
INFO: Application startup complete.
|
||||
```
|
||||
|
||||
### 启动前端
|
||||
|
||||
**新终端窗口:**
|
||||
```bash
|
||||
cd frontend
|
||||
npm run dev
|
||||
```
|
||||
|
||||
**成功输出:**
|
||||
```
|
||||
➜ Local: http://localhost:5173/
|
||||
➜ Network: http://192.168.1.100:5173/
|
||||
```
|
||||
|
||||
## 📱 使用流程
|
||||
|
||||
### 步骤 1: 访问应用
|
||||
|
||||
打开浏览器访问：
|
||||
- **本地**: http://localhost:5173
|
||||
- **局域网**: http://192.168.1.100:5173 （替换为实际 IP）
|
||||
|
||||
### 步骤 2: 输入需求
|
||||
|
||||
在"步骤 1: 输入需求"卡片中，输入自然语言需求，例如：
|
||||
|
||||
```
|
||||
创建一个销售订单管理页面，包含订单号、客户、订单日期、金额、备注字段
|
||||
```
|
||||
|
||||
**示例需求:**
|
||||
|
||||
**简单示例:**
|
||||
```
|
||||
创建一个部门管理页面，包含部门名称、负责人、联系电话
|
||||
```
|
||||
|
||||
**中等复杂度:**
|
||||
```
|
||||
创建一个客户档案管理页面，包含客户名称、联系人、电话、地址、客户类型，支持按客户类型筛选
|
||||
```
|
||||
|
||||
**复杂示例:**
|
||||
```
|
||||
创建一个采购申请单，单据类型，包含申请单号、申请日期、申请人、部门、总金额，明细表包含物料编码、物料名称、数量、单价、金额
|
||||
```
|
||||
|
||||
### 步骤 3: 分析需求
|
||||
|
||||
点击 **"开始分析需求"** 按钮：
|
||||
|
||||
- ⏳ 等待 1-3 秒（取决于 API 响应时间）
|
||||
- ✅ 成功后显示结构化分析结果
|
||||
- 📊 包含：功能名称、功能类型、窗体类型、字段列表等
|
||||
|
||||
**示例输出:**
|
||||
```
|
||||
功能名称: 销售订单管理
|
||||
功能类型: 列表页面
|
||||
功能号建议: 11-001
|
||||
窗体类型: 5
|
||||
|
||||
主表字段:
|
||||
- 订单号 (varchar(50), 必填)
|
||||
- 客户 (varchar(100), 必填)
|
||||
- 订单日期 (datetime, 必填)
|
||||
- 金额 (decimal(18,2), 必填)
|
||||
- 备注 (varchar(500), 选填)
|
||||
```
|
||||
|
||||
### 步骤 4: 生成配置
|
||||
|
||||
确认分析结果无误后，点击 **"生成配置方案"** 按钮：
|
||||
|
||||
- ⏳ 等待 2-5 秒
|
||||
- ✅ 成功后显示生成的 SQL 配置
|
||||
- 📝 可以预览所有 SQL 语句
|
||||
|
||||
**SQL 预览示例:**
|
||||
```sql
|
||||
-- 创建功能号
|
||||
INSERT INTO SYS_FUNCTION (FUNCTION_ID, FUNCTION_NAME, ...)
|
||||
VALUES ('11-001', '销售订单管理', ...);
|
||||
|
||||
-- 创建页面配置
|
||||
INSERT INTO SYS_FORM (FORM_ID, FORM_NAME, ...)
|
||||
VALUES (...);
|
||||
|
||||
-- 创建表结构
|
||||
CREATE TABLE SA_ORDER (
|
||||
IKEY INT IDENTITY(1,1) PRIMARY KEY,
|
||||
ORDER_NO VARCHAR(50) NOT NULL,
|
||||
...
|
||||
);
|
||||
```
|
||||
|
||||
### 步骤 5: 执行配置
|
||||
|
||||
仔细检查 SQL 语句后，点击 **"确认并执行"** 按钮：
|
||||
|
||||
1. **安全警告对话框**
|
||||
- ⚠️ 阅读警告信息
|
||||
- ✅ 确认无误后点击"确认执行"
|
||||
|
||||
2. **执行过程**
|
||||
- ⏳ 等待执行完成
|
||||
- 📊 实时显示执行结果
|
||||
|
||||
3. **执行结果**
|
||||
- ✅ 成功: 显示"执行成功"消息
|
||||
- ❌ 失败: 显示错误详情
|
||||
|
||||
### 步骤 6: 完成
|
||||
|
||||
- 🎉 查看执行结果
|
||||
- 🔄 点击"创建新功能"开始下一个功能
|
||||
|
||||
## 🎨 界面说明
|
||||
|
||||
### 步骤指示器
|
||||
|
||||
顶部显示当前进度：
|
||||
```
|
||||
○ 需求分析 → ○ 配置生成 → ○ 执行配置
|
||||
```
|
||||
|
||||
- **当前步骤**: 高亮显示
|
||||
- **已完成**: 绿色勾选
|
||||
- **未完成**: 灰色
|
||||
|
||||
### 卡片区域
|
||||
|
||||
#### 需求输入卡片
|
||||
- 文本框：输入自然语言需求
|
||||
- "开始分析需求"按钮
|
||||
|
||||
#### 分析结果卡片
|
||||
- 基本信息：功能名称、类型等
|
||||
- 字段列表：表格展示
|
||||
- 操作按钮：重新分析、生成配置
|
||||
|
||||
#### 配置方案卡片
|
||||
- SQL 预览：只读文本框
|
||||
- 操作按钮：返回修改、确认执行
|
||||
|
||||
#### 执行结果卡片
|
||||
- 成功/失败图标
|
||||
- 详细消息
|
||||
- "创建新功能"按钮
|
||||
|
||||
## ⚠️ 注意事项
|
||||
|
||||
### 1. 需求描述建议
|
||||
|
||||
**✅ 好的描述:**
|
||||
- 清晰说明功能目的
|
||||
- 列出主要字段
|
||||
- 说明特殊需求
|
||||
|
||||
**示例:**
|
||||
```
|
||||
创建一个库存预警设置页面，包含物料编码、物料名称、安全库存、预警阈值，
|
||||
当库存低于预警阈值时自动标记为红色
|
||||
```
|
||||
|
||||
**❌ 不好的描述:**
|
||||
```
|
||||
做一个库存页面
|
||||
```
|
||||
（太模糊，缺少关键信息）
|
||||
|
||||
### 2. 检查分析结果
|
||||
|
||||
在生成配置前，务必检查：
|
||||
- ✅ 功能名称是否正确
|
||||
- ✅ 字段是否完整
|
||||
- ✅ 字段类型是否合理
|
||||
- ✅ 必填项标记是否正确
|
||||
|
||||
如有问题，点击"重新分析"修改需求。
|
||||
|
||||
### 3. SQL 审查
|
||||
|
||||
执行前必须检查：
|
||||
- ✅ 表名是否合理
|
||||
- ✅ 字段名是否符合规范
|
||||
- ✅ 数据类型是否正确
|
||||
- ✅ 外键关联是否正确
|
||||
|
||||
### 4. 数据库备份
|
||||
|
||||
**强烈建议：**
|
||||
- 在生产环境执行前备份数据库
|
||||
- 先在测试环境验证
|
||||
- 记录执行的 SQL 语句
|
||||
|
||||
## 🐛 常见问题
|
||||
|
||||
### 问题 1: 分析需求超时
|
||||
|
||||
**现象:** 点击按钮后一直加载
|
||||
|
||||
**可能原因:**
|
||||
- Claude API 响应慢
|
||||
- 网络连接问题
|
||||
- API Key 无效
|
||||
|
||||
**解决方案:**
|
||||
1. 检查网络连接
|
||||
2. 验证 `ANTHROPIC_API_KEY` 是否有效
|
||||
3. 查看后端日志：`tail -f backend/logs/app.log`
|
||||
4. 尝试更简单的需求
|
||||
|
||||
### 问题 2: 数据库执行失败
|
||||
|
||||
**现象:** 执行配置时显示失败
|
||||
|
||||
**可能原因:**
|
||||
- 数据库连接失败
|
||||
- SQL 语法错误
|
||||
- 权限不足
|
||||
- 表已存在
|
||||
|
||||
**解决方案:**
|
||||
1. 检查 `.env` 数据库配置
|
||||
2. 确认数据库服务运行中
|
||||
3. 检查 SQL Server 日志
|
||||
4. 使用数据库管理工具测试 SQL
|
||||
|
||||
### 问题 3: 前端无法连接后端
|
||||
|
||||
**现象:** 前端显示网络错误
|
||||
|
||||
**解决方案:**
|
||||
1. 确认后端已启动：访问 http://localhost:8000/health
|
||||
2. 检查前端代理配置：`frontend/vite.config.js`
|
||||
3. 查看浏览器控制台网络请求
|
||||
4. 确认 CORS 配置：后端 `DEBUG=True`
|
||||
|
||||
### 问题 4: 分析结果不准确
|
||||
|
||||
**现象:** 生成的字段或类型不符合预期
|
||||
|
||||
**解决方案:**
|
||||
- 更详细地描述需求
|
||||
- 在需求中明确字段类型
|
||||
- 使用更具体的业务术语
|
||||
- 多次尝试不同的描述方式
|
||||
|
||||
## 📚 进阶使用
|
||||
|
||||
### 自定义 API 端点
|
||||
|
||||
如需使用代理或自托管服务：
|
||||
|
||||
```bash
|
||||
# .env
|
||||
ANTHROPIC_BASE_URL=https://your-proxy.com/v1
|
||||
```
|
||||
|
||||
参考 [Claude API 配置指南](./CLAUDE_API_CONFIG.md)
|
||||
|
||||
### 局域网访问
|
||||
|
||||
团队成员可通过局域网访问：
|
||||
|
||||
```bash
|
||||
# 查看服务器 IP
|
||||
ipconfig # Windows
|
||||
ifconfig # Linux/Mac
|
||||
|
||||
# 其他设备访问
|
||||
http://192.168.1.100:5173
|
||||
```
|
||||
|
||||
参考 [局域网访问配置](./LAN_ACCESS.md)
|
||||
|
||||
### 查看历史记录
|
||||
|
||||
"历史记录"页面（即将推出）:
|
||||
- 查看所有执行记录
|
||||
- 重新执行历史配置
|
||||
- 导出配置方案
|
||||
|
||||
## 🎓 最佳实践
|
||||
|
||||
### 1. 开发流程
|
||||
|
||||
```
|
||||
需求分析 → 代码评审 → 测试环境验证 → 生产环境执行
|
||||
```
|
||||
|
||||
### 2. 命名规范
|
||||
|
||||
建议在需求中说明：
|
||||
- 功能号格式：`模块-序号` (如：`11-001`)
|
||||
- 表名前缀：业务含义 (如：`SA_` 销售)
|
||||
- 字段名：有意义的英文
|
||||
|
||||
### 3. 版本管理
|
||||
|
||||
使用 Git 记录配置变更：
|
||||
|
||||
```bash
|
||||
# 执行成功后
|
||||
git add .
|
||||
git commit -m "feat: add 销售订单管理功能"
|
||||
```
|
||||
|
||||
### 4. 团队协作
|
||||
|
||||
- 使用相同的测试数据库
|
||||
- 共享需求模板
|
||||
- 定期同步配置规范
|
||||
|
||||
## 📞 获取帮助
|
||||
|
||||
遇到问题时：
|
||||
|
||||
1. 📖 查看本文档
|
||||
2. 🔍 检查日志文件
|
||||
3. 📋 查看后端 API 文档: http://localhost:8000/docs
|
||||
4. 💬 联系项目负责人
|
||||
|
||||
---
|
||||
|
||||
**祝您使用愉快！🎉**
|
||||
2460
docs/superpowers/plans/2026-03-21-erp-ai-assistant-phase1.md
Normal file
2460
docs/superpowers/plans/2026-03-21-erp-ai-assistant-phase1.md
Normal file
File diff suppressed because it is too large
Load Diff
1077
docs/superpowers/specs/2026-03-21-erp-ai-assistant-design.md
Normal file
1077
docs/superpowers/specs/2026-03-21-erp-ai-assistant-design.md
Normal file
File diff suppressed because it is too large
Load Diff
13
frontend/index.html
Normal file
13
frontend/index.html
Normal file
@@ -0,0 +1,13 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="zh-CN">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<link rel="icon" href="/favicon.ico">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>ERP AI Assistant</title>
|
||||
</head>
|
||||
<body>
|
||||
<div id="app"></div>
|
||||
<script type="module" src="/src/main.js"></script>
|
||||
</body>
|
||||
</html>
|
||||
1750
frontend/package-lock.json
generated
Normal file
1750
frontend/package-lock.json
generated
Normal file
File diff suppressed because it is too large
Load Diff
23
frontend/package.json
Normal file
23
frontend/package.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"name": "erp-ai-assistant-frontend",
|
||||
"version": "1.0.0",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"scripts": {
|
||||
"dev": "vite",
|
||||
"build": "vite build",
|
||||
"preview": "vite preview"
|
||||
},
|
||||
"dependencies": {
|
||||
"vue": "^3.3.8",
|
||||
"vue-router": "^4.2.5",
|
||||
"pinia": "^2.1.7",
|
||||
"axios": "^1.6.2",
|
||||
"element-plus": "^2.4.3",
|
||||
"@element-plus/icons-vue": "^2.3.1"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@vitejs/plugin-vue": "^4.5.1",
|
||||
"vite": "^5.0.4"
|
||||
}
|
||||
}
|
||||
22
frontend/src/App.vue
Normal file
22
frontend/src/App.vue
Normal file
@@ -0,0 +1,22 @@
|
||||
<template>
|
||||
<div id="app">
|
||||
<router-view />
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
</script>
|
||||
|
||||
<style>
|
||||
* {
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
#app {
|
||||
font-family: 'Microsoft YaHei', -apple-system, BlinkMacSystemFont, 'Segoe UI', sans-serif;
|
||||
height: 100vh;
|
||||
margin: 0;
|
||||
}
|
||||
</style>
|
||||
52
frontend/src/api/index.js
Normal file
52
frontend/src/api/index.js
Normal file
@@ -0,0 +1,52 @@
|
||||
import axios from 'axios'
|
||||
|
||||
const api = axios.create({
|
||||
baseURL: '/api/v1',
|
||||
timeout: 60000,
|
||||
headers: {
|
||||
'Content-Type': 'application/json'
|
||||
}
|
||||
})
|
||||
|
||||
// 响应拦截器
|
||||
api.interceptors.response.use(
|
||||
response => response.data,
|
||||
error => {
|
||||
console.error('API Error:', error)
|
||||
return Promise.reject(error)
|
||||
}
|
||||
)
|
||||
|
||||
/**
|
||||
* 分析用户需求
|
||||
*/
|
||||
export const analyzeRequirement = (data) => {
|
||||
return api.post('/analyze', {
|
||||
input_type: 'natural_language',
|
||||
content: data.content,
|
||||
session_id: data.session_id
|
||||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* 生成配置
|
||||
*/
|
||||
export const generateConfig = (data) => {
|
||||
return api.post('/generate', {
|
||||
session_id: data.session_id,
|
||||
requirements: data.requirements
|
||||
})
|
||||
}
|
||||
|
||||
/**
|
||||
* 执行配置
|
||||
*/
|
||||
export const executeConfig = (data) => {
|
||||
return api.post('/execute', {
|
||||
session_id: data.session_id,
|
||||
confirmed: data.confirmed || true,
|
||||
backup_enabled: data.backup_enabled || true
|
||||
})
|
||||
}
|
||||
|
||||
export default api
|
||||
14
frontend/src/main.js
Normal file
14
frontend/src/main.js
Normal file
@@ -0,0 +1,14 @@
|
||||
import { createApp } from 'vue'
|
||||
import { createPinia } from 'pinia'
|
||||
import ElementPlus from 'element-plus'
|
||||
import 'element-plus/dist/index.css'
|
||||
import App from './App.vue'
|
||||
import router from './router'
|
||||
|
||||
const app = createApp(App)
|
||||
|
||||
app.use(createPinia())
|
||||
app.use(router)
|
||||
app.use(ElementPlus)
|
||||
|
||||
app.mount('#app')
|
||||
31
frontend/src/router/index.js
Normal file
31
frontend/src/router/index.js
Normal file
@@ -0,0 +1,31 @@
|
||||
import { createRouter, createWebHistory } from 'vue-router'
|
||||
|
||||
const routes = [
|
||||
{
|
||||
path: '/',
|
||||
component: () => import('../views/Layout.vue'),
|
||||
children: [
|
||||
{
|
||||
path: '',
|
||||
redirect: '/create'
|
||||
},
|
||||
{
|
||||
path: 'create',
|
||||
name: 'CreateFunction',
|
||||
component: () => import('../views/CreateFunction.vue')
|
||||
},
|
||||
{
|
||||
path: 'history',
|
||||
name: 'History',
|
||||
component: () => import('../views/History.vue')
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
|
||||
const router = createRouter({
|
||||
history: createWebHistory(),
|
||||
routes
|
||||
})
|
||||
|
||||
export default router
|
||||
61
frontend/src/stores/function.js
Normal file
61
frontend/src/stores/function.js
Normal file
@@ -0,0 +1,61 @@
|
||||
import { defineStore } from 'pinia'
|
||||
import { ref } from 'vue'
|
||||
|
||||
export const useFunctionStore = defineStore('function', () => {
|
||||
// 状态
|
||||
const currentSession = ref(null)
|
||||
const analysisResult = ref(null)
|
||||
const configResult = ref(null)
|
||||
const executeResult = ref(null)
|
||||
const loading = ref({
|
||||
analyzing: false,
|
||||
generating: false,
|
||||
executing: false
|
||||
})
|
||||
|
||||
// 重置状态
|
||||
const reset = () => {
|
||||
currentSession.value = null
|
||||
analysisResult.value = null
|
||||
configResult.value = null
|
||||
executeResult.value = null
|
||||
loading.value = {
|
||||
analyzing: false,
|
||||
generating: false,
|
||||
executing: false
|
||||
}
|
||||
}
|
||||
|
||||
// 设置会话
|
||||
const setSession = (sessionId) => {
|
||||
currentSession.value = sessionId
|
||||
}
|
||||
|
||||
// 设置分析结果
|
||||
const setAnalysisResult = (result) => {
|
||||
analysisResult.value = result
|
||||
}
|
||||
|
||||
// 设置配置结果
|
||||
const setConfigResult = (result) => {
|
||||
configResult.value = result
|
||||
}
|
||||
|
||||
// 设置执行结果
|
||||
const setExecuteResult = (result) => {
|
||||
executeResult.value = result
|
||||
}
|
||||
|
||||
return {
|
||||
currentSession,
|
||||
analysisResult,
|
||||
configResult,
|
||||
executeResult,
|
||||
loading,
|
||||
reset,
|
||||
setSession,
|
||||
setAnalysisResult,
|
||||
setConfigResult,
|
||||
setExecuteResult
|
||||
}
|
||||
})
|
||||
3
frontend/src/stores/index.js
Normal file
3
frontend/src/stores/index.js
Normal file
@@ -0,0 +1,3 @@
|
||||
import { createPinia } from 'pinia'
|
||||
|
||||
export const pinia = createPinia()
|
||||
380
frontend/src/views/CreateFunction.vue
Normal file
380
frontend/src/views/CreateFunction.vue
Normal file
@@ -0,0 +1,380 @@
|
||||
<template>
|
||||
<div class="create-function">
|
||||
<!-- 步骤指示器 -->
|
||||
<el-steps :active="currentStep" finish-status="success" simple class="steps">
|
||||
<el-step title="需求分析" />
|
||||
<el-step title="配置生成" />
|
||||
<el-step title="执行配置" />
|
||||
</el-steps>
|
||||
|
||||
<!-- 步骤 1: 需求输入 -->
|
||||
<el-card v-if="currentStep === 0" class="section-card">
|
||||
<template #header>
|
||||
<div class="card-header">
|
||||
<span>步骤 1: 输入需求</span>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<el-form :model="form" label-width="120px">
|
||||
<el-form-item label="需求描述">
|
||||
<el-input
|
||||
v-model="form.requirement"
|
||||
type="textarea"
|
||||
:rows="6"
|
||||
placeholder="请输入功能需求，例如：创建一个销售订单管理页面，包含订单号、客户、订单日期、金额等字段"
|
||||
/>
|
||||
</el-form-item>
|
||||
|
||||
<el-form-item>
|
||||
<el-button
|
||||
type="primary"
|
||||
@click="handleAnalyze"
|
||||
:loading="functionStore.loading.analyzing"
|
||||
:disabled="!form.requirement.trim()"
|
||||
>
|
||||
开始分析需求
|
||||
</el-button>
|
||||
</el-form-item>
|
||||
</el-form>
|
||||
</el-card>
|
||||
|
||||
<!-- 步骤 2: 分析结果 -->
|
||||
<el-card v-if="functionStore.analysisResult" class="section-card">
|
||||
<template #header>
|
||||
<div class="card-header">
|
||||
<span>需求分析结果</span>
|
||||
<el-tag type="success">已完成</el-tag>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<el-descriptions :column="2" border>
|
||||
<el-descriptions-item label="功能名称">
|
||||
{{ functionStore.analysisResult.功能名称 || '-' }}
|
||||
</el-descriptions-item>
|
||||
<el-descriptions-item label="功能类型">
|
||||
{{ functionStore.analysisResult.功能类型 || '-' }}
|
||||
</el-descriptions-item>
|
||||
<el-descriptions-item label="功能号建议">
|
||||
{{ functionStore.analysisResult.功能号建议 || '-' }}
|
||||
</el-descriptions-item>
|
||||
<el-descriptions-item label="窗体类型">
|
||||
{{ functionStore.analysisResult.窗体类型 || '-' }}
|
||||
</el-descriptions-item>
|
||||
</el-descriptions>
|
||||
|
||||
<div v-if="functionStore.analysisResult.主表字段" class="field-list">
|
||||
<h4>主表字段：</h4>
|
||||
<el-table :data="functionStore.analysisResult.主表字段" border size="small">
|
||||
<el-table-column prop="字段名" label="字段名" />
|
||||
<el-table-column prop="字段类型" label="字段类型" />
|
||||
<el-table-column prop="必填" label="必填">
|
||||
<template #default="{ row }">
|
||||
<el-tag :type="row.必填 ? 'danger' : 'info'" size="small">
|
||||
{{ row.必填 ? '是' : '否' }}
|
||||
</el-tag>
|
||||
</template>
|
||||
</el-table-column>
|
||||
</el-table>
|
||||
</div>
|
||||
|
||||
<div class="button-group">
|
||||
<el-button @click="resetAll">重新分析</el-button>
|
||||
<el-button
|
||||
type="primary"
|
||||
@click="handleGenerate"
|
||||
:loading="functionStore.loading.generating"
|
||||
>
|
||||
生成配置方案
|
||||
</el-button>
|
||||
</div>
|
||||
</el-card>
|
||||
|
||||
<!-- 步骤 3: 配置方案 -->
|
||||
<el-card v-if="functionStore.configResult" class="section-card">
|
||||
<template #header>
|
||||
<div class="card-header">
|
||||
<span>配置方案</span>
|
||||
<el-tag type="success">已生成</el-tag>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<el-alert
|
||||
title="请仔细检查以下 SQL 配置，确认无误后执行"
|
||||
type="warning"
|
||||
:closable="false"
|
||||
show-icon
|
||||
class="alert-box"
|
||||
/>
|
||||
|
||||
<div v-if="functionStore.configResult.配置方案" class="config-section">
|
||||
<h4>SQL 配置语句：</h4>
|
||||
<el-input
|
||||
v-model="sqlDisplay"
|
||||
type="textarea"
|
||||
:rows="15"
|
||||
readonly
|
||||
class="sql-textarea"
|
||||
/>
|
||||
</div>
|
||||
|
||||
<div class="button-group">
|
||||
<el-button @click="backToAnalysis">返回修改</el-button>
|
||||
<el-button
|
||||
type="danger"
|
||||
@click="showExecuteConfirm"
|
||||
:loading="functionStore.loading.executing"
|
||||
>
|
||||
确认并执行
|
||||
</el-button>
|
||||
</div>
|
||||
</el-card>
|
||||
|
||||
<!-- 执行结果 -->
|
||||
<el-card v-if="functionStore.executeResult" class="section-card">
|
||||
<template #header>
|
||||
<div class="card-header">
|
||||
<span>执行结果</span>
|
||||
<el-tag :type="functionStore.executeResult.status === 'success' ? 'success' : 'danger'">
|
||||
{{ functionStore.executeResult.status === 'success' ? '执行成功' : '执行失败' }}
|
||||
</el-tag>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<el-result
|
||||
:icon="functionStore.executeResult.status === 'success' ? 'success' : 'error'"
|
||||
:title="functionStore.executeResult.message"
|
||||
>
|
||||
<template #extra>
|
||||
<el-button type="primary" @click="resetAll">创建新功能</el-button>
|
||||
</template>
|
||||
</el-result>
|
||||
</el-card>
|
||||
|
||||
<!-- 执行确认对话框 -->
|
||||
<el-dialog
|
||||
v-model="executeDialogVisible"
|
||||
title="确认执行"
|
||||
width="500px"
|
||||
>
|
||||
<el-alert
|
||||
type="warning"
|
||||
:closable="false"
|
||||
show-icon
|
||||
>
|
||||
<template #title>
|
||||
<strong>警告：此操作将直接修改数据库</strong>
|
||||
</template>
|
||||
<div style="margin-top: 10px;">
|
||||
<p>• 请确认已仔细检查所有 SQL 语句</p>
|
||||
<p>• 建议在生产环境执行前先备份数据库</p>
|
||||
<p>• 执行后可通过历史记录查看详情</p>
|
||||
</div>
|
||||
</el-alert>
|
||||
|
||||
<template #footer>
|
||||
<el-button @click="executeDialogVisible = false">取消</el-button>
|
||||
<el-button type="danger" @click="handleExecute">
|
||||
确认执行
|
||||
</el-button>
|
||||
</template>
|
||||
</el-dialog>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { ref, computed } from 'vue'
|
||||
import { ElMessage } from 'element-plus'
|
||||
import { useFunctionStore } from '@/stores/function'
|
||||
import { analyzeRequirement, generateConfig, executeConfig } from '@/api'
|
||||
|
||||
const functionStore = useFunctionStore()
|
||||
|
||||
const form = ref({
|
||||
requirement: ''
|
||||
})
|
||||
|
||||
const executeDialogVisible = ref(false)
|
||||
|
||||
// 当前步骤
|
||||
const currentStep = computed(() => {
|
||||
if (functionStore.executeResult) return 3
|
||||
if (functionStore.configResult) return 2
|
||||
if (functionStore.analysisResult) return 1
|
||||
return 0
|
||||
})
|
||||
|
||||
// SQL 显示
|
||||
const sqlDisplay = computed(() => {
|
||||
if (!functionStore.configResult?.配置方案?.sql_list) return ''
|
||||
return functionStore.configResult.配置方案.sql_list.join('\n\n')
|
||||
})
|
||||
|
||||
// 分析需求
|
||||
const handleAnalyze = async () => {
|
||||
if (!form.value.requirement.trim()) {
|
||||
ElMessage.warning('请输入需求描述')
|
||||
return
|
||||
}
|
||||
|
||||
functionStore.loading.analyzing = true
|
||||
|
||||
try {
|
||||
const result = await analyzeRequirement({
|
||||
content: form.value.requirement,
|
||||
session_id: null
|
||||
})
|
||||
|
||||
functionStore.setSession(result.session_id)
|
||||
functionStore.setAnalysisResult(result.data)
|
||||
|
||||
ElMessage.success('需求分析成功')
|
||||
} catch (error) {
|
||||
console.error('Analysis failed:', error)
|
||||
ElMessage.error(
|
||||
'需求分析失败: ' + (error.response?.data?.detail?.message || error.message)
|
||||
)
|
||||
} finally {
|
||||
functionStore.loading.analyzing = false
|
||||
}
|
||||
}
|
||||
|
||||
// 生成配置
|
||||
const handleGenerate = async () => {
|
||||
if (!functionStore.currentSession || !functionStore.analysisResult) {
|
||||
ElMessage.warning('请先完成需求分析')
|
||||
return
|
||||
}
|
||||
|
||||
functionStore.loading.generating = true
|
||||
|
||||
try {
|
||||
const result = await generateConfig({
|
||||
session_id: functionStore.currentSession,
|
||||
requirements: functionStore.analysisResult
|
||||
})
|
||||
|
||||
functionStore.setConfigResult(result.data)
|
||||
|
||||
ElMessage.success('配置生成成功')
|
||||
} catch (error) {
|
||||
console.error('Generation failed:', error)
|
||||
ElMessage.error(
|
||||
'配置生成失败: ' + (error.response?.data?.detail?.message || error.message)
|
||||
)
|
||||
} finally {
|
||||
functionStore.loading.generating = false
|
||||
}
|
||||
}
|
||||
|
||||
// 显示执行确认对话框
|
||||
const showExecuteConfirm = () => {
|
||||
executeDialogVisible.value = true
|
||||
}
|
||||
|
||||
// 执行配置
|
||||
const handleExecute = async () => {
|
||||
if (!functionStore.currentSession) {
|
||||
ElMessage.warning('会话信息丢失，请重新开始')
|
||||
return
|
||||
}
|
||||
|
||||
executeDialogVisible.value = false
|
||||
functionStore.loading.executing = true
|
||||
|
||||
try {
|
||||
const result = await executeConfig({
|
||||
session_id: functionStore.currentSession,
|
||||
confirmed: true,
|
||||
backup_enabled: true
|
||||
})
|
||||
|
||||
functionStore.setExecuteResult(result)
|
||||
|
||||
if (result.status === 'success') {
|
||||
ElMessage.success('配置执行成功')
|
||||
} else {
|
||||
ElMessage.error('配置执行失败')
|
||||
}
|
||||
} catch (error) {
|
||||
console.error('Execution failed:', error)
|
||||
ElMessage.error(
|
||||
'配置执行失败: ' + (error.response?.data?.detail?.message || error.message)
|
||||
)
|
||||
} finally {
|
||||
functionStore.loading.executing = false
|
||||
}
|
||||
}
|
||||
|
||||
// 返回分析步骤
|
||||
const backToAnalysis = () => {
|
||||
functionStore.setConfigResult(null)
|
||||
}
|
||||
|
||||
// 重置所有状态
|
||||
const resetAll = () => {
|
||||
functionStore.reset()
|
||||
form.value.requirement = ''
|
||||
}
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.create-function {
|
||||
max-width: 1200px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
.steps {
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
.section-card {
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
.card-header {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
font-size: 16px;
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
.field-list {
|
||||
margin-top: 20px;
|
||||
}
|
||||
|
||||
.field-list h4 {
|
||||
margin-bottom: 10px;
|
||||
color: #606266;
|
||||
}
|
||||
|
||||
.alert-box {
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
.config-section {
|
||||
margin-top: 20px;
|
||||
}
|
||||
|
||||
.config-section h4 {
|
||||
margin-bottom: 10px;
|
||||
color: #606266;
|
||||
}
|
||||
|
||||
.sql-textarea {
|
||||
font-family: 'Courier New', monospace;
|
||||
}
|
||||
|
||||
.sql-textarea :deep(textarea) {
|
||||
font-family: 'Courier New', monospace;
|
||||
font-size: 13px;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
.button-group {
|
||||
display: flex;
|
||||
gap: 10px;
|
||||
margin-top: 20px;
|
||||
justify-content: flex-end;
|
||||
}
|
||||
</style>
|
||||
28
frontend/src/views/History.vue
Normal file
28
frontend/src/views/History.vue
Normal file
@@ -0,0 +1,28 @@
|
||||
<template>
|
||||
<div class="history">
|
||||
<el-card>
|
||||
<template #header>
|
||||
<div class="card-header">
|
||||
<span>历史记录</span>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<el-empty description="暂无历史记录" />
|
||||
</el-card>
|
||||
</div>
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.history {
|
||||
max-width: 1200px;
|
||||
margin: 0 auto;
|
||||
}
|
||||
|
||||
.card-header {
|
||||
font-size: 16px;
|
||||
font-weight: bold;
|
||||
}
|
||||
</style>
|
||||
69
frontend/src/views/Layout.vue
Normal file
69
frontend/src/views/Layout.vue
Normal file
@@ -0,0 +1,69 @@
|
||||
<template>
|
||||
<el-container class="layout-container">
|
||||
<el-header class="header">
|
||||
<div class="logo">ERP智能助手</div>
|
||||
<div class="user-info">用户: Admin</div>
|
||||
</el-header>
|
||||
|
||||
<el-container>
|
||||
<el-aside width="200px" class="sidebar">
|
||||
<el-menu
|
||||
:default-active="$route.path"
|
||||
router
|
||||
>
|
||||
<el-menu-item index="/create">
|
||||
<el-icon><Edit /></el-icon>
|
||||
<span>新建功能</span>
|
||||
</el-menu-item>
|
||||
<el-menu-item index="/history">
|
||||
<el-icon><Document /></el-icon>
|
||||
<span>历史记录</span>
|
||||
</el-menu-item>
|
||||
</el-menu>
|
||||
</el-aside>
|
||||
|
||||
<el-main class="main-content">
|
||||
<router-view />
|
||||
</el-main>
|
||||
</el-container>
|
||||
</el-container>
|
||||
</template>
|
||||
|
||||
<script setup>
|
||||
import { Edit, Document } from '@element-plus/icons-vue'
|
||||
</script>
|
||||
|
||||
<style scoped>
|
||||
.layout-container {
|
||||
height: 100vh;
|
||||
}
|
||||
|
||||
.header {
|
||||
display: flex;
|
||||
justify-content: space-between;
|
||||
align-items: center;
|
||||
background: #409EFF;
|
||||
color: white;
|
||||
padding: 0 20px;
|
||||
}
|
||||
|
||||
.logo {
|
||||
font-size: 20px;
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
.user-info {
|
||||
font-size: 14px;
|
||||
}
|
||||
|
||||
.sidebar {
|
||||
background: #f5f7fa;
|
||||
overflow-y: auto;
|
||||
}
|
||||
|
||||
.main-content {
|
||||
background: #f0f2f5;
|
||||
padding: 20px;
|
||||
overflow-y: auto;
|
||||
}
|
||||
</style>
|
||||
17
frontend/vite.config.js
Normal file
17
frontend/vite.config.js
Normal file
@@ -0,0 +1,17 @@
|
||||
import { defineConfig } from 'vite'
|
||||
import vue from '@vitejs/plugin-vue'
|
||||
|
||||
// https://vitejs.dev/config/
|
||||
export default defineConfig({
|
||||
plugins: [vue()],
|
||||
server: {
|
||||
host: '0.0.0.0', // 允许局域网访问
|
||||
port: 5173,
|
||||
proxy: {
|
||||
'/api': {
|
||||
target: 'http://localhost:8000',
|
||||
changeOrigin: true
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
Reference in New Issue
Block a user