2025-11-16 04:34:40 +00:00
|
|
|
|
|
|
|
|
|
|
# DevStar AI+ DevOps
|
|
|
|
|
|
|
|
|
|
|
|
DevStar AI+ DevOps 是一个完整的AI驱动研发平台解决方案，通过集成 DevStar平台、代码大语言模型、Gitea MCP Server和 AI Code Tools（Cursor、Claude Code、iFlow等），为开发者提供智能化研发支撑体系。
|
|
|
|
|
|
|
|
|
|
|
|
## 🚀 快速部署
|
|
|
|
|
|
|
|
|
|
|
|
### 一、部署 DevStar 代码托管平台
|
|
|
|
|
|
|
2025-11-16 05:27:53 +00:00
|
|
|
|
Ubuntu-20.04下完成安装：
|
2025-11-16 04:34:40 +00:00
|
|
|
|
|
|
|
|
|
|
```
|
|
|
|
|
|
wget -c https://devstar.cn/assets/install.sh && chmod +x install.sh && sudo ./install.sh
|
|
|
|
|
|
sudo devstar start
|
|
|
|
|
|
```
|
2025-11-16 05:27:53 +00:00
|
|
|
|
|
|
|
|
|
|
安装完成后，我们得到DevStar代码托管平台的URL，比如http://172.16.94.26:80
|
|
|
|
|
|
|
|
|
|
|
|
### 二、Ollama私有部署代码大模型
|
|
|
|
|
|
|
|
|
|
|
|
Ubuntu-20.04下完成安装：
|
|
|
|
|
|
```
|
|
|
|
|
|
curl -fsSL https://ollama.com/install.sh | sh
|
|
|
|
|
|
|
|
|
|
|
|
# 验证是否安装成功
|
|
|
|
|
|
ollama --version
|
|
|
|
|
|
|
|
|
|
|
|
# 下载Qwen2.5-Coder大模型
|
|
|
|
|
|
ollama pull qwen2.5-coder:32b
|
|
|
|
|
|
|
|
|
|
|
|
# 列出已下载的模型
|
|
|
|
|
|
ollama list
|
|
|
|
|
|
|
|
|
|
|
|
# 测试模型
|
|
|
|
|
|
ollama run qwen2.5-coder:32b "Hello, can you help me code?"
|
|
|
|
|
|
|
|
|
|
|
|
# 启动Ollama服务 (默认端口11434)
|
|
|
|
|
|
ollama serve
|
|
|
|
|
|
|
|
|
|
|
|
# 验证服务状态
|
|
|
|
|
|
curl http://172.16.94.26:11434/api/tags
|
|
|
|
|
|
```
|
|
|
|
|
|
* 解决Ollama只能本地访问的问题
|
|
|
|
|
|
```
|
|
|
|
|
|
# 添加环境变量OLLAMA_HOST=0.0.0.0和OLLAMA_ORIGINS=*
|
|
|
|
|
|
sed -i '/\[Service\]/a Environment=OLLAMA_HOST=0.0.0.0' /etc/systemd/system/ollama.service
|
|
|
|
|
|
sed -i '/\[Service\]/a Environment=OLLAMA_ORIGINS=*' /etc/systemd/system/ollama.service
|
|
|
|
|
|
# 重新加载并重启
|
|
|
|
|
|
systemctl daemon-reexec
|
|
|
|
|
|
systemctl daemon-reload
|
|
|
|
|
|
systemctl restart ollama
|
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
|
|
安装完成后，我们得到API URL,比如http://172.16.94.26:11434/api/tags model比如qwen2.5-coder:32b token比如TOKEN***************
|
|
|
|
|
|
|
|
|
|
|
|
### 三、配置AI Code Review到CI/CD工作流中
|
|
|
|
|
|
|
|
|
|
|
|
在您的项目中添加.gitea/workflows/code-review.yml , 这里使用kekxv/AiReviewPR@v0.0.6来进行AI Code Review
|
|
|
|
|
|
```
|
|
|
|
|
|
name: ai-reviews
|
|
|
|
|
|
|
|
|
|
|
|
on:
|
|
|
|
|
|
pull_request:
|
|
|
|
|
|
types: [opened, synchronize]
|
|
|
|
|
|
|
|
|
|
|
|
jobs:
|
|
|
|
|
|
review:
|
|
|
|
|
|
runs-on: ubuntu-latest
|
|
|
|
|
|
|
|
|
|
|
|
steps:
|
|
|
|
|
|
- name: Checkout code
|
|
|
|
|
|
uses: actions/checkout@v4
|
|
|
|
|
|
with:
|
|
|
|
|
|
fetch-depth: 0
|
|
|
|
|
|
- name: Review code
|
|
|
|
|
|
uses: kekxv/AiReviewPR@v0.0.6
|
|
|
|
|
|
with:
|
|
|
|
|
|
model: ${{ vars.MODEL }}
|
|
|
|
|
|
host: ${{ vars.OLLAMA_HOST }}
|
|
|
|
|
|
REVIEW_PULL_REQUEST: false
|
|
|
|
|
|
```
|
|
|
|
|
|
DevStar代码托管平台中项目设置、用户设置和后台管理中都可以设置变量vars.MODEL、vars.OLLAMA_HOST等。
|
|
|
|
|
|
|
|
|
|
|
|
### 四、使用ai-develops项目模板完整演示DevStar AI+ DevOps的CI/CD工作流及AI Code Review
|
|
|
|
|
|
|
|
|
|
|
|
todo
|
