docs:再次更新了文档，这次可能会更好？？#473
Conversation
|
Codex usage limits have been reached for code reviews. Please check with the admins of this repo to increase the limits by adding credits. |
![fennoai[bot]](https://avatars.githubusercontent.com/in/1924301?s=60&v=4){kind=small}
| @@ -115,6 +113,7 @@ export default defineConfig({ | |||
| text: "深入阅读", | |||
There was a problem hiding this comment.
Checked the navigation/documentation reshuffle here; no issues found from quality, performance, security, or doc-accuracy perspectives.
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
| # 配置指南 | ||
|
|
||
| ## 总原则 | ||
| NeoCode 的配置目标很简单：把常用选择保存下来，把密钥留在环境变量里。第一次使用只需要配置 Provider、模型和 Shell；其他能力按需打开。 |
There was a problem hiding this comment.
其实都不需要说特地配置provider和模型吧，内置的是只需要配一个环境变量里的密钥就行了，现在这样说好像有点误导
There was a problem hiding this comment.
不是，一般都是好吧，你见过我们的顾客直接用内置的provider？
There was a problem hiding this comment.
我的角度是说，可能会让还没开始用的用户觉得我们是需要特地去配置的，不过这倒也无伤大雅
| |---|---| | ||
| | OpenAI | `OPENAI_API_KEY` | | ||
| | Gemini | `GEMINI_API_KEY` | | ||
| | OpenLL | `AI_API_KEY` | |
There was a problem hiding this comment.
倒是提醒我了，那个openll没啥用，该删了
| ## 自定义 Provider | ||
|
|
||
| 如果你用的模型服务不在内置列表里，可以通过配置文件接入。 | ||
| 如果你的模型服务不在内置列表里，可以添加 OpenAI 兼容 Provider。 |
There was a problem hiding this comment.
其实Gemini和anthropic都是支持的，不过这两个我没测试过，不补充上去也没关系
There was a problem hiding this comment.
对，就是自定义的也支持Gemini和anthropic兼容的
2 participants
更新页面的文档，或许更好了