![Lagrange.RagBot](https://socialify.git.ci/LSTM-Kirigaya/Lagrange.RagBot/image?description=1&font=Jost&forks=1&issues=1&language=1&logo=https%3A%2F%2Fpicx.zhimg.com%2F0%2Fv2-bdae55043d61d7bcfeeabead6e953959_1440w.jpeg&name=1&pulls=1&stargazers=1&theme=Light)
> 简体中文 < | English
## 环境搭建 ```bash git clone xxxxxx npm install pm2 -g yarn pip install -r requirements.txt ``` 下载最新版本的 Lagrange.core ,并完成初始化。完成后根目录为 ``` 📁bot 📁rag 📁app ├─📁publish │ ├─🏷️... │ ├─🏷️appsettings.json │ └─🪛Lagrange.OneBot └─🎗️... ``` --- ## 架构 ```mermaid graph TB core(Lagrage.Core) onebot(Lagrange.onebot) vecdb(vecdb) llm(LLM) intent(intent tree) core(Lagrange.Core) --> onebot(Lagrange.onebot) onebot -->|query| intent intent -->|intent| onebot subgraph Intent Recognition intent -->|query| vecdb vecdb -->|ktop| intent intent -->|ktop,query| llm llm -->|intent| intent end subgraph execution onebot --> command{intent} command --> query command --> upload command --> ... end subgraph third party LLM Google server end query --> LLM query --> Google upload --> server ``` - `Lagrange.onebot` --> 📁bot - `vecdb` --> 📁rag - `intent tree` --> 📁prompt --- ## 接口规范 http 接口满足 `HttpResponse` 所示。 ```typescript interface HttpResponse { code: number, data: CommonResponse } interface CommonResponse { code: number, data?: T, msg?: string } ``` --- ## 开发须知 - 非必要,请不要随意宣传本项目。 - 虽然曾经无数个 QQ 相关的项目都死了,但是基本的 API 端口算是传承了下来。拉格朗日的返回类型,请参考 [go-cqhttp 帮助中心 - API 篇](https://docs.go-cqhttp.org/api/) 中的内容。