{"id":13460355,"url":"https://github.com/phodal/aigc","last_synced_at":"2025-04-08T06:37:31.476Z","repository":{"id":176448630,"uuid":"657179506","full_name":"phodal/aigc","owner":"phodal","description":"《构筑大语言模型应用：应用开发与架构设计》一本关于 LLM 在真实世界应用的开源电子书，介绍了大语言模型的基础知识和应用，以及如何构建自己的模型。其中包括Prompt的编写、开发和管理，探索最好的大语言模型能带来什么，以及LLM应用开发的模式和架构设计。","archived":false,"fork":false,"pushed_at":"2024-01-23T10:02:45.000Z","size":21201,"stargazers_count":1501,"open_issues_count":1,"forks_count":175,"subscribers_count":27,"default_branch":"master","last_synced_at":"2025-04-01T04:53:20.531Z","etag":null,"topics":["aigc","chatgpt","ebook","llm","opensource"],"latest_commit_sha":null,"homepage":"https://aigc.phodal.com/","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/phodal.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-06-22T13:42:41.000Z","updated_at":"2025-03-30T06:11:58.000Z","dependencies_parsed_at":null,"dependency_job_id":"68e80482-9d47-4aa1-907c-2e7663312188","html_url":"https://github.com/phodal/aigc","commit_stats":{"total_commits":107,"total_committers":7,"mean_commits":"15.285714285714286","dds":"0.19626168224299068","last_synced_commit":"e6db1ebe9003dc96da0d99290cf0edcce8f9d295"},"previous_names":["phodal/aigc"],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phodal%2Faigc","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phodal%2Faigc/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phodal%2Faigc/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/phodal%2Faigc/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/phodal","download_url":"https://codeload.github.com/phodal/aigc/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247792900,"owners_count":20996892,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["aigc","chatgpt","ebook","llm","opensource"],"created_at":"2024-07-31T10:00:40.334Z","updated_at":"2025-04-08T06:37:31.393Z","avatar_url":"https://github.com/phodal.png","language":"Rust","funding_links":[],"categories":["A01_文本生成_文本对话","Rust","语言资源库","Prompts","Summary"],"sub_categories":["大语言对话模型及数据","rust"],"readme":"# 构筑大语言模型应用：应用开发与架构设计\n\n\u003e aka. Unlocking the Potential of Large Language Models: Real-World Use Cases\n\n2023 年的上半年里，我（@phodal）和 Thoughtworks\n的同事们（如：@[tianweiliu](https://github.com/tianweiliu)、@[teobler](https://github.com/teobler)、@[mutoe](https://github.com/mutoe)\n等）、\n开源社区的同伴们（如：\n卷王@[CGQAQ](https://github.com/CGQAQ)、@[genffy](https://github.com/genffy)、 @[liruifengv](https://github.com/liruifengv)\n等)\n一起，创建了一系列的流行的或者不流行的开源项目。它们涉及了：\n\n- LLM 能力的充分运用\n  - Prompt 编写：Prompt 学习与编写模式\n  - Prompt 管理：Prompt 即代码\n- LLM 下的软件开发工序及应用架构设计\n  - 新的交互设计：Chat 模式\n  - 大模型友好的工序：基于 AI 2.0 （ChatGPT + Copilot）如何去设计软件开发流程\n  - LLM 应用架构的设计与落地：Unit Mesh\n- 面向特定场景的 LLM 应用\n  - 基于开源模型构建自己的模型：特定场景的模型微调 + LLMOps\n  - 上下文工程（prompt 工程）：LLM 应用的核心\n\n围绕于上述的一系列内容，我们也在思考软件开发能给我们带来了什么。所以，我重新整理了过去半年的一些思考、文章，重新编写了这本开源电子书，希望能够帮助到大家。\n\n关注我的微信公众号（搜索 phodal-weixin），获得更多及时的更新：\n\n![微信公众号](src/images/qrcode.jpg)\n\n我们发起的相关开源项目如下（包括但是不限于）：\n\n| 名称                                                                         | 描述                                                                                       | 类型          | Stars                                                                                          |\n|----------------------------------------------------------------------------|------------------------------------------------------------------------------------------|-------------|------------------------------------------------------------------------------------------------|\n| [理解 Prompt](https://github.com/prompt-engineering/understand-prompt)       | 基于编程、绘画、写作的 AI 探索与总结。                                                                    | 文档          | ![GitHub Repo stars](https://img.shields.io/github/stars/prompt-engineering/understand-prompt) |\n| [Prompt 编写模式](https://github.com/prompt-engineering/prompt-patterns)       | 如何将思维框架赋予机器，以设计模式的形式来思考 prompt。                                                          | 文档          | ![GitHub Repo stars](https://img.shields.io/github/stars/prompt-engineering/prompt-patterns)   |\n| [ClickPrompt](https://github.com/prompt-engineering/click-prompt)          | 用于一键轻松查看、分享和执行您的 Prompt。                                                                 | 应用          | ![GitHub Repo stars](https://img.shields.io/github/stars/prompt-engineering/click-prompt)      |\n| [ChatVisualNovel](https://github.com/prompt-engineering/chat-visual-novel) | 基于 ChatGPT 的定制化视觉小说引擎                                                                    | 应用          | ![GitHub Repo stars](https://img.shields.io/github/stars/prompt-engineering/chat-visual-novel) |\n| [ChatFlow](https://github.com/prompt-engineering/chat-flow)                | 打造个性化 ChatGPT 流程，构建自动化之路。                                                                | 框架          | ![GitHub Repo stars](https://img.shields.io/github/stars/prompt-engineering/chat-flow)         |\n| [Unit Mesh](https://github.com/unit-mesh/unit-mesh)                        | 基于 AI 为核心的软件 2.0 思想的软件架构。                                                                | 架构          | ![GitHub Repo stars](https://img.shields.io/github/stars/unit-mesh/unit-mesh)                  |\n| [Unit Minions](https://github.com/unit-mesh/unit-minions)                  | AI 研发提效研究：自己动手训练 LoRA                                                                    | 微调教程、指南、数据集 | ![GitHub Repo stars](https://img.shields.io/github/stars/unit-mesh/unit-minions)               |\n| [Unit Runtime](https://github.com/unit-mesh/unit-runtime)                  | 一个 ChatGPT 等 AI 代码的运行环境，可一键启动并实时交互，帮助您快速构建和测试 AI 代码。                                     | 基础设施        | ![GitHub Repo stars](https://img.shields.io/github/stars/unit-mesh/unit-runtime)               |\n| [DevTi](https://github.com/unit-mesh/devti)                                | 基于 LLM 的微调来提供全面智能化解决方案，助力开发人员高效完成开发任务，以实现自动化用户任务拆解、用户故事生成、自动化代码生成、自动化测试生成等等。             | 微调代码        | ![GitHub Repo stars](https://img.shields.io/github/stars/unit-mesh/devti)                      |\n| [AutoDev](https://github.com/unit-mesh/auto-dev)                           | 一款 Intellij IDEA 的 LLM/AI 辅助编程插件。AutoDev 能够与您的需求管理系统（例如 Jira、Trello、Github Issue 等）直接对接。 | IDEA 插件     | ![GitHub Repo stars](https://img.shields.io/github/stars/unit-mesh/auto-dev)                   |\n| [ArchGuard Co-mate](https://github.com/archguard/co-mate)                  | 基于人工智能技术的架构副驾驶、设计和治理工具                                                                   | 架构协同应用      | ![GitHub Repo stars](https://img.shields.io/github/stars/archguard/co-mate)                    |\n\n我们在 QCon\n上的演讲：[演讲：探索软件开发新工序：LLM 赋能研发效能提升](https://qcon.infoq.cn/2023/guangzhou/presentation/5319)\n\n\u003e LLM（如 ChatGPT + GitHub\n\u003e Copilot）作为一种创新的工具组合，为我们带来了全新的机遇。它能够帮助业务人员和开发者在需求、架构、编码、测试等环节提高效率和质量，实现从设计到验证的端到端流程。在本次分享中，我将向大家介绍\n\u003e LLM 在研发效能方面的应用场景和实践案例，展示它是如何在各个环节中发挥作用的。同时，我们还将分享如何构建私有化的 LLM\n\u003e 工程化方式，使其更好地适应组织的需求。欢迎对 LLM + 研发效能感兴趣的朋友们参加本次分享，与我们一起探讨研发效能的未来。\n\n我们在 Bilibili 上的大语言模型微调相关的视频：\n\n- LLaMA\n  系列在线视频： 《[代码辅助生成](https://www.bilibili.com/video/BV1Rh411u74H/)》 、《[测试代码生成](https://www.bilibili.com/video/BV1jg4y1G7Xc/)》 、《[详细需求生成](https://www.bilibili.com/video/BV1Us4y1N7rd/)》 、《[文本转 SQL](https://www.bilibili.com/video/BV1uv4y1H7bg/)》\n- ChatGLM 系列在线视频： 《[LoRA 大比拼：ChatGLM vs LLaMA，谁更会写需求文档？](https://www.bilibili.com/video/BV1fv4y1n7Y3/)》\n\n欢迎大家一起来参与我们的开源项目，一起来探索 LLM + 软件开发的未来。\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphodal%2Faigc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fphodal%2Faigc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fphodal%2Faigc/lists"}