- Notifications
You must be signed in to change notification settings - Fork20
ChocoBuilder (Chocolate Factory) is a cutting-edge LLM toolkit designed to empower you in creating your very own AI assistant.Chocolate Factory 是一款开源的 LLM 应用开发框架,旨在帮助您轻松打造强大的软件开发 SDLC + LLM 生成助手。无论您是需要生成前端页面、后端 API、SQL 图表,还是测试用例数据,Chocolate Factory 都能满足您的需求。
License
unit-mesh/choco-builder
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
ChocoBuilder (origin Chocolate Factory) 是一款开源的 LLM 应用开发框架,旨在帮助您轻松打造强大的软件开发 SDLC + LLM 生成助手。
For native (Android/iOS/Embedded device) SDK:see inhttps://github.com/unit-mesh/edge-infer
方式 1:集成到 JVM 项目中
模块列表:https://central.sonatype.com/namespace/cc.unitmesh
dependencies {// 核心模块 implementation'cc.unitmesh:cocoa-core:1.0.0'// Pinecone implementation'cc.unitmesh:store-pinecone:1.0.0'// ElasticSearch implementation'cc.unitmesh:store-elasticsearch:1.0.0'//...其它模块}
更多示例见:examples/
方式 2:使用 RAGScript
@file:DependsOn("cc.unitmesh:rag-script:1.0.0")importcc.unitmesh.rag.*rag { indexing {val chunks= document("README.md").split() store.indexing(chunks) } querying { store.findRelevant("workflow dsl design") .lowInMiddle() .also {println(it) } }}
方式 3:本地部署示例
git clone https://github.com/unit-mesh/chocolate-factory# modify OPENAI_API_KEY and OPENAI_HOST in docker-compose.ymldocker-compose up
Desktop/IDE:
- https://github.com/unit-mesh/auto-dev - The AI-powered coding wizard with multilingual support 🌐, auto code generation 🏗️, and a helpful bug-slaying assistant
- https://github.com/phodal/shire - AI Coding Agent Language
Server:
Android:
See inhttps://framework.unitmesh.cc/ or see indocuments
The key concepts of ChocoBuilder are:
(PS: Origin made by Michael PlödatAligning organization and architecture with strategic DDD)
A user's problem is processed by the following steps:
- Online Demo:https://framework.unitmesh.cc/ (TODO)
- Video Demo:https://www.bilibili.com/video/BV1T14y1C7p2
- Gif Demo:
- 步骤 1:ProblemClarifier:使用响应式布局,编写一个聊天页面
- 步骤 1.1:ProblemClarifier:左边是一个导航,中间是聊天区,聊天区的下方是一个输入按钮。
- 步骤 2:SolutionDesigner:请确认以下的设计是否符合您的要求。如果符合,请回复"YES",如果不符合,请提出你的要求。
- 步骤 3:SolutionExecutor:生成一个聊天页面
- 步骤 1:ProblemAnalyzer 分析用户的需求,转为成多个语义化的查询
- 中文、英文、HyDE 模式
- 步骤 2:SolutionExecutor:根据用户的需求,从数据库中检索出最相关的代码片段,由 ChatGPT 做总结
示例输入:Semantic Workflow 是如何实现的?
最终输出:
- 步骤 1:ProblemAnalyzer 分析用户的需求,确认是否是一个测试用例生成的需求
- 多 Temperature 模式:TemperatureMode.Default, TemperatureMode.Creative
- 步骤 2:SolutionDesigner 设计测试用例生成的方案
- 步骤 3:SolutionReviewer 确认方案是否符合用户的需求
示例输入:用户发表文章
最终输出:
- 步骤 1:SolutionExecutor
输出示例:
1 2 3 4 5 6 7 8 92 4 6 8 10 12 14 16 183 6 9 12 15 18 21 24 274 8 12 16 20 24 28 32 365 10 15 20 25 30 35 40 456 12 18 24 30 36 42 48 547 14 21 28 35 42 49 56 638 16 24 32 40 48 56 64 729 18 27 36 45 54 63 72 81
生成一个 2023 年上半年电费图,信息如下:###1~6 月:201.2,222,234.3,120.2,90,90.4###
过程代码:
%use lets-plotimport kotlin.math.PIimport kotlin.random.Randomval incomeData = mapOf( "x" to listOf("一月", "二月", "三月", "四月", "五月", "六月"), "y" to listOf(201.2, 222, 234.3, 120.2, 90, 94.4))letsPlot(incomeData) { x = "x"; y = "y" } + geomBar(stat = Stat.identity) + geomText(labelFormat = "\${.2f}") { label = "y"; } + ggtitle("2023 年上半年电费")
最终输出:
RAG relevant modules were inspired by
Some RAG modules based on LangChain4j and Spring AI which is licensed under the Apache License 2.0.
This code is distributed under the MPL 2.0 license. SeeLICENSE
in this directory.
About
ChocoBuilder (Chocolate Factory) is a cutting-edge LLM toolkit designed to empower you in creating your very own AI assistant.Chocolate Factory 是一款开源的 LLM 应用开发框架,旨在帮助您轻松打造强大的软件开发 SDLC + LLM 生成助手。无论您是需要生成前端页面、后端 API、SQL 图表,还是测试用例数据,Chocolate Factory 都能满足您的需求。