[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-h1st-ai--h1st":3,"tool-h1st-ai--h1st":64},[4,17,27,35,43,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},3808,"stable-diffusion-webui","AUTOMATIC1111\u002Fstable-diffusion-webui","stable-diffusion-webui 是一个基于 Gradio 构建的网页版操作界面，旨在让用户能够轻松地在本地运行和使用强大的 Stable Diffusion 图像生成模型。它解决了原始模型依赖命令行、操作门槛高且功能分散的痛点，将复杂的 AI 绘图流程整合进一个直观易用的图形化平台。\n\n无论是希望快速上手的普通创作者、需要精细控制画面细节的设计师，还是想要深入探索模型潜力的开发者与研究人员，都能从中获益。其核心亮点在于极高的功能丰富度：不仅支持文生图、图生图、局部重绘（Inpainting）和外绘（Outpainting）等基础模式，还独创了注意力机制调整、提示词矩阵、负向提示词以及“高清修复”等高级功能。此外，它内置了 GFPGAN 和 CodeFormer 等人脸修复工具，支持多种神经网络放大算法，并允许用户通过插件系统无限扩展能力。即使是显存有限的设备，stable-diffusion-webui 也提供了相应的优化选项，让高质量的 AI 艺术创作变得触手可及。",162132,3,"2026-04-05T11:01:52",[13,14,15],"开发框架","图像","Agent","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":23,"last_commit_at":24,"category_tags":25,"status":16},1381,"everything-claude-code","affaan-m\u002Feverything-claude-code","everything-claude-code 是一套专为 AI 编程助手（如 Claude Code、Codex、Cursor 等）打造的高性能优化系统。它不仅仅是一组配置文件，而是一个经过长期实战打磨的完整框架，旨在解决 AI 代理在实际开发中面临的效率低下、记忆丢失、安全隐患及缺乏持续学习能力等核心痛点。\n\n通过引入技能模块化、直觉增强、记忆持久化机制以及内置的安全扫描功能，everything-claude-code 能显著提升 AI 在复杂任务中的表现，帮助开发者构建更稳定、更智能的生产级 AI 代理。其独特的“研究优先”开发理念和针对 Token 消耗的优化策略，使得模型响应更快、成本更低，同时有效防御潜在的攻击向量。\n\n这套工具特别适合软件开发者、AI 研究人员以及希望深度定制 AI 工作流的技术团队使用。无论您是在构建大型代码库，还是需要 AI 协助进行安全审计与自动化测试，everything-claude-code 都能提供强大的底层支持。作为一个曾荣获 Anthropic 黑客大奖的开源项目，它融合了多语言支持与丰富的实战钩子（hooks），让 AI 真正成长为懂上",140436,2,"2026-04-05T23:32:43",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":80,"owner_twitter":81,"owner_website":82,"owner_url":83,"languages":84,"stars":93,"forks":94,"last_commit_at":95,"license":96,"difficulty_score":23,"env_os":97,"env_gpu":98,"env_ram":98,"env_deps":99,"category_tags":104,"github_topics":105,"view_count":23,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":124,"updated_at":125,"faqs":126,"releases":157},1317,"h1st-ai\u002Fh1st","h1st","Power Tools for AI Engineers With Deadlines","h1st 是一个面向 AI 工程师的开源工具，旨在帮助开发者更高效地构建和部署人工智能系统。它基于“以人为本的 AI”理念（Human-First AI），强调将人类洞察力与 AI 技术相结合，以解决实际应用中的复杂问题。\n\nh1st 主要解决了三个关键问题：首先，在数据不足的情况下，如何利用人类知识提升 AI 模型的效果；其次，如何通过协作工具提高数据科学家之间的合作效率；最后，如何增强 AI 模型的透明度和可信度，以满足监管和用户信任的需求。\n\n它适合需要快速构建 AI 解决方案的开发者和研究人员使用，尤其适用于工业 AI 领域，如预测性维护、故障检测等场景。h1st 提供了模块化建模方式、规则引擎与机器学习模型的结合能力，以及可视化建模工具，使 AI 开发过程更加直观和高效。\n\n其独特之处在于支持多种模型融合，允许用户在没有足够数据时引入领域知识，并通过清晰的模型描述和解释功能提升 AI 的可解释性。对于希望将 AI 应用于实际业务并确保技术包容性和透明度的团队来说，h1st 是一个值得尝试的工具。","## Join the Human-First AI revolution\n_“We humans have .. insight that can then be mixed with powerful AI .. to help move society forward. Second, we also have to build trust directly into our technology .. And third, all of the technology we build must be inclusive and respectful to everyone.”_\n\u003Cbr\u002F>— Satya Nadella, Microsoft CEO\n\nAs trail-blazers in Industrial AI, our team at Arimo-Panasonic has found Satya Nadella‘s observations to be powerful and prescient. Many hard-won lessons from the field have led us to adopt this approach which we call Human-First AI (`H1st` AI). \n\nToday, we‘re excited to share these ideas and concrete implementation of `H1st` AI with you and the open-source data science community!\n\n## Learn the Key Concepts\nHuman-First AI (`H1st` AI) solves three critical challenges in real-world data science:\n\n1. __Industrial AI needs human insight:__ In so many important applications, there isn‘t enough data for ML. For example, last year‘s product‘s data does not apply to this year‘s new model. Or, equipment not yet shipped obviously have no data history to speak of. `H1st` combines human knowledge and any available data to enable intelligent systems, and companies can achieve earlier time-to-market.\n\n2. __Data scientists need human tools:__ Today‘s tools are to compete rather than to collaborate. When multiple data scientists work on the same project, they are effectively competing to see who can build the better model. `H1st` breaks a large modeling problem into smaller, easier parts. This allows true collaboration and high productivity, in ways similar to well-established software engineering methodology. \n\n3. __AI needs human trust:__ AI models can't be deployed when they lack user trust. AI increasingly face regulatory challenges. `H1st` supports model description and explanation at multiple layers, enabling transparent and trustworthy AI.\n\n\n## Get started\n`H1st` runs on Python 3.8 or above. Install with \n```\npip install --upgrade pip\npip3 install h1st\n```\nFor Windows, please use 64bit version and install [VS Build Tools](https:\u002F\u002Fvisualstudio.microsoft.com\u002Fdownloads\u002F) before installing H1st.\n\nStart by reading about our [philosophy](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Fmanifesto\u002FREADME.html) and [Object Model](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Fconcepts\u002Fobject-model.html)\n\nSee the [Quick Start](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fquick-start\u002FREADME.html) for simple \"Hello world\" examples of using [H1st rule-based model](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fquick-start\u002FREADME.html#rule-based-model) & [H1st ML model](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fquick-start\u002FREADME.html#mlmodeler-and-mlmodel) and using [H1st Graph](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fquick-start\u002FREADME.html#h1st-graph).\n\n\n## Read the Documentation, Tutorials, and API Documentation\n\nGo over [the Concepts](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Fconcepts\u002FREADME.html)\n\nFor a simple real-world data science example using H1st Modeler and Model API, take a look at\n- [Modeler and Model with Iris dataset](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fexamples\u002Fmodeler-model.html).\n- [H1st Oracle: Combine Encoded Domain Knowledge with Machine Learning](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fexamples\u002Foracle-iot.html) in which we used Microsoft Azure Predictive Maintenance dataset to demonstrate the power of the Oracle.\n\nTo fully understand H1st philosophy and power, check out the [Use-case examples](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fuse-cases\u002FREADME.html).\n\nFor a deep dive into the components, please refer to our full [API Documentation](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Fapi\u002FREADME.html).\n\n## Join and Learn from Our Open-Source Community\nWe are collaborating with the open-source community. For Arimo-Panasonic, use cases include industrial applications such as Cybersecurity, Predictive Maintenance, Fault Prediction, Home Automation, Avionic & Automotive Experience Management, etc.\n\nWe'd love to see your use cases and your contributions to open-source `H1st` AI. \n","## 加入以人为本的AI革命\n_“我们人类拥有……能够与强大的人工智能相结合的洞见……从而推动社会向前发展。其次，我们还必须将信任直接嵌入我们的技术之中……第三，我们所构建的每一项技术都必须具有包容性，并尊重每一个人。”_\n\u003Cbr\u002F>——微软首席执行官萨蒂亚·纳德拉\n\n作为工业人工智能领域的先行者，我们在Arimo-Panasonic的团队发现，萨蒂亚·纳德拉的这些见解既深刻又富有远见。多年来在一线积累的诸多宝贵经验促使我们采纳了一种名为“以人为本的AI”（`H1st` AI）的方法。\n\n今天，我们非常高兴与您以及开源数据科学社区分享这些理念及`H1st` AI的具体实践！\n\n## 了解核心概念\n“以人为本的AI”（`H1st` AI）解决了现实世界数据科学中的三大关键挑战：\n\n1. __工业人工智能需要人类洞见：__ 在许多重要应用中，用于机器学习的数据往往不足。例如，去年产品的数据并不适用于今年的新模型；又或者，尚未发货的设备显然没有任何历史数据可循。`H1st`将人类知识与任何可用数据相结合，以赋能智能系统，帮助企业更早实现产品上市。\n\n2. __数据科学家需要人性化的工具：__ 当今的工具更多是用于竞争而非协作。当多名数据科学家在同一项目上工作时，他们实际上是在比拼谁能构建出更好的模型。而`H1st`则将一个庞大的建模问题拆解为更小、更易处理的部分，从而实现真正的协作与高效率，其方式与成熟的软件工程方法论如出一辙。\n\n3. __AI需要人类的信任：__ 如果缺乏用户信任，AI模型就无法部署。同时，AI也日益面临监管方面的挑战。`H1st`支持在多个层面进行模型描述与解释，从而实现透明且值得信赖的AI。\n\n\n## 开始使用\n`H1st`运行于Python 3.8及以上版本。安装命令如下：\n```\npip install --upgrade pip\npip3 install h1st\n```\n对于Windows系统，请使用64位版本，并在安装H1st之前先安装[VS Build Tools](https:\u002F\u002Fvisualstudio.microsoft.com\u002Fdownloads\u002F)。\n\n首先，请阅读我们的[理念宣言](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Fmanifesto\u002FREADME.html)和[对象模型](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Fconcepts\u002Fobject-model.html)。\n\n随后，您可以参考[快速入门](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fquick-start\u002FREADME.html)，其中提供了使用[H1st规则型模型](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fquick-start\u002FREADME.html#rule-based-model)与[H1st ML模型](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fquick-start\u002FREADME.html#mlmodeler-and-mlmodel)以及[H1st图谱](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fquick-start\u002FREADME.html#h1st-graph)的简单“Hello world”示例。\n\n\n## 阅读文档、教程与API文档\n\n请浏览[概念指南](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Fconcepts\u002FREADME.html)。\n\n若想了解一个基于H1st Modeler与Model API的简单真实世界数据科学案例，可以参阅：\n- [使用Iris数据集的Modeler与Model](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fexamples\u002Fmodeler-model.html)。\n- [H1st Oracle：将编码的领域知识与机器学习相结合](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fexamples\u002Foracle-iot.html)，其中我们使用了微软Azure预测性维护数据集来展示Oracle的强大功能。\n\n要全面理解H1st的理念与优势，请查看[用例示例](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Ftutorials\u002Fuse-cases\u002FREADME.html)。\n\n如需深入了解各个组件，请查阅我们的完整[API文档](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002Fapi\u002FREADME.html)。\n\n## 加入并从我们的开源社区中学习\n我们正与开源社区开展合作。对于Arimo-Panasonic而言，应用场景涵盖工业领域，例如网络安全、预测性维护、故障预测、家居自动化、航空与汽车体验管理等。\n\n我们非常期待您的用例以及您对开源`H1st` AI的贡献！","# h1st 快速上手指南\n\n## 环境准备\n\n- **系统要求**：支持 Python 3.8 或更高版本\n- **前置依赖**：\n  - Windows 用户需安装 64 位 Python，并提前安装 [VS Build Tools](https:\u002F\u002Fvisualstudio.microsoft.com\u002Fdownloads\u002F)。\n  - 推荐使用国内镜像源加速安装，如清华源。\n\n## 安装步骤\n\n使用以下命令安装 `h1st`：\n\n```bash\npip install --upgrade pip\npip3 install h1st\n```\n\n> 如果你在国内，可以使用以下命令加速安装：\n\n```bash\npip install --upgrade pip -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\npip3 install h1st -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n```\n\n## 基本使用\n\n### 示例一：使用 H1st 规则模型（Rule-based Model）\n\n```python\nfrom h1st import RuleBasedModel\n\nmodel = RuleBasedModel()\nmodel.add_rule(\"if age > 60 then risk = high\")\nmodel.add_rule(\"if age \u003C= 60 and blood_pressure > 140 then risk = medium\")\nmodel.add_rule(\"else risk = low\")\n\nresult = model.predict({\"age\": 65, \"blood_pressure\": 130})\nprint(result)\n```\n\n### 示例二：使用 H1st 机器学习模型（MLModeler）\n\n```python\nfrom h1st import MLModeler\nfrom sklearn.datasets import load_iris\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.ensemble import RandomForestClassifier\n\n# 加载数据集\ndata = load_iris()\nX_train, X_test, y_train, y_test = train_test_split(data.data, data.target, test_size=0.2)\n\n# 创建并训练模型\nml_modeler = MLModeler()\nml_modeler.train(X_train, y_train, model_class=RandomForestClassifier)\n\n# 进行预测\nprediction = ml_modeler.predict(X_test)\nprint(prediction)\n```\n\n### 示例三：使用 H1st Graph 构建模型流程图\n\n```python\nfrom h1st import Graph\n\ngraph = Graph()\ngraph.add_node(\"rule_model\", RuleBasedModel())\ngraph.add_node(\"ml_model\", MLModeler())\ngraph.connect(\"rule_model.output\", \"ml_model.input\")\n\nresult = graph.run({\"input\": {\"age\": 65, \"blood_pressure\": 130}})\nprint(result)\n```\n\n以上是 `h1st` 的基本使用方式。更多高级用法和完整教程，请参考 [官方文档](https:\u002F\u002Fh1st.readthedocs.io\u002Fen\u002Flatest\u002F)。","某家电制造企业正在开发一款智能洗衣机，其目标是通过AI实现更精准的衣物污渍检测与洗涤程序推荐。研发团队由数据科学家、工程师和产品设计师组成，需要在短时间内完成模型开发并集成到产品中。\n\n### 没有 h1st 时  \n- 数据样本有限，尤其是针对新型面料和特殊污渍的数据不足，导致传统机器学习模型难以达到预期精度。  \n- 团队成员各自独立开发模型，缺乏协作机制，重复劳动严重，项目进度缓慢。  \n- 模型决策过程不透明，用户对AI推荐的洗涤方案缺乏信任，影响产品市场接受度。  \n- 需要手动编写大量规则逻辑来补充模型不足，开发效率低下且容易出错。  \n\n### 使用 h1st 后  \n- 结合领域专家的知识构建规则模型，并与少量真实数据结合训练混合模型，显著提升了在新场景下的泛化能力。  \n- 通过模块化建模方式将任务拆解为多个子问题，支持多人协作开发，提高了整体开发效率与代码复用率。  \n- 提供多层级的模型解释功能，使洗涤方案推荐具备可解释性，增强了用户对AI系统的信任感。  \n- 可直接在模型中嵌入业务规则，减少人工编码工作量，同时保证了系统逻辑的一致性和准确性。  \n\n核心价值：h1st 通过融合人类洞察与AI技术，帮助团队在数据有限、时间紧迫的情况下高效构建可信、可解释的智能系统。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fh1st-ai_h1st_4dd803eb.png","h1st-ai","Human-First AI—Because AI Needs The Human Eye","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fh1st-ai_797d29a5.png","☑ Can‘t Start: Industrial AI needs human insight. ☑ Can‘t Profit: DS needs human tools. ☑ Can‘t Deploy: AI needs human trust.",null,"help@h1st.ai","h1st_ai","https:\u002F\u002Fh1st.ai","https:\u002F\u002Fgithub.com\u002Fh1st-ai",[85,89],{"name":86,"color":87,"percentage":88},"Jupyter Notebook","#DA5B0B",97.6,{"name":90,"color":91,"percentage":92},"Python","#3572A5",2.4,795,85,"2026-03-16T16:45:13","NOASSERTION","Linux, macOS, Windows","未说明",{"notes":100,"python":101,"dependencies":102},"在 Windows 上需安装 64 位版本 Python 并提前安装 VS Build Tools。首次使用时可能需要下载额外的模型文件。","3.8+",[103,67],"pip",[54,13,51,15],[106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123],"data-science","explainability","home-automation","time-series","collaboration","cybersecurity","cold-start","autonomous-vehicles","automl","avionics","human-in-the-loop","predictive-maintenance","ensemble-machine-learning","datascience-environment","industrial-iot","trustworthy-datascience","energy-optimization","hacktoberfest","2026-03-27T02:49:30.150509","2026-04-06T10:24:50.822712",[127,132,137,142,147,152],{"id":128,"question_zh":129,"answer_zh":130,"source_url":131},5691,"在 Windows 10 上使用 Python 3.9 安装 h1st 时出现错误怎么办？","安装 h1st 时遇到 UnicodeDecodeError 错误，是因为缺少必要的构建工具。请安装 VS Build Tools。具体步骤可以参考项目中更新的安装说明。","https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fissues\u002F56",{"id":133,"question_zh":134,"answer_zh":135,"source_url":136},5692,"如何解决示例 notebook 中数据缺失的问题？","示例 notebook 中的数据文件缺失会导致运行失败。请确保数据文件已正确放置在指定路径下，或者联系项目维护者以获取最新数据集。","https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fissues\u002F8",{"id":138,"question_zh":139,"answer_zh":140,"source_url":141},5693,"如何创建一个简单的 HelloWorld 图来演示 H1st 的使用？","可以通过查看项目中的示例代码和 Wiki 页面来了解如何创建一个简单的 HelloWorld 图。相关资源包括：https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fwiki\u002FHuman-First-AI-Graph-Explained 和 https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F51。","https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fissues\u002F20",{"id":143,"question_zh":144,"answer_zh":145,"source_url":146},5694,"如何移除 h1st 的 tensorflow 依赖？","由于 tensorflow 在不同平台和架构上的安装复杂性，建议将其从 h1st 的依赖列表中移除。此外，还可以考虑将其他未使用的库（如 pyarrow、shap 等）移到 h1st-extension 中。","https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fissues\u002F160",{"id":148,"question_zh":149,"answer_zh":150,"source_url":151},5695,"如何在不同操作系统和 Python 版本上预检 h1st 的安装和测试？","建议通过 GitHub Actions 在 Pull Request 中运行跨平台测试，覆盖 Python 3.8 到 3.10、MacOS、Windows 和 Linux 系统，并支持 ARM 或 x86 架构。目前暂不支持 Mac M1 和 Windows ARM，但未来可以扩展。","https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fissues\u002F159",{"id":153,"question_zh":154,"answer_zh":155,"source_url":156},5696,"如何为新用户提供更简单的入门示例？","项目中已经提供了 HelloWorld 示例，用于展示如何使用简单节点和决策节点。用户可以参考项目中的示例代码和 Wiki 页面进行学习。","https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fissues\u002F5",[158,163,168,173,178,183,188,193,198,203],{"id":159,"version":160,"summary_zh":161,"released_at":162},115369,"v2.1.7","## What's Changed\r\n* fix: use ~ in pyproject instead of >= by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F197\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002Fv2.1.6...v2.1.7","2023-06-30T13:56:13",{"id":164,"version":165,"summary_zh":166,"released_at":167},115370,"v2.1.6","## What's Changed\r\n* Fix\u002Fpersist issue by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F196\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002Fv2.1.5...v2.1.6","2023-06-29T16:05:56",{"id":169,"version":170,"summary_zh":171,"released_at":172},115371,"v2.1.5","## What's Changed\r\n* Fix\u002Fmodelrepository get model repo by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F195\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002Fv2.1.4...v2.1.5","2023-06-29T10:12:02",{"id":174,"version":175,"summary_zh":176,"released_at":177},115372,"v2.1.4","## What's Changed\r\n* fix: remove logs in model_repository, add log to s3 storage, update v… by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F194\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002Fv2.1.3...v2.1.4","2023-06-29T08:55:40",{"id":179,"version":180,"summary_zh":181,"released_at":182},115373,"v2.1.3","## What's Changed\r\n* Add try exception to persist and load by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F193\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002Fv2.1.2...v2.1.3","2023-06-29T07:27:07",{"id":184,"version":185,"summary_zh":186,"released_at":187},115374,"v2.1.2","## What's Changed\r\n* Fix\u002Fadd persist log by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F192\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002F2.1.1...v2.1.2","2023-06-29T06:16:41",{"id":189,"version":190,"summary_zh":191,"released_at":192},115375,"2.1.1","## What's Changed\r\n* fix: remove Model as suffix in XGB model name, update version to 2.1.1 by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F191\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002F2.1.0...2.1.1","2023-05-05T01:56:12",{"id":194,"version":195,"summary_zh":196,"released_at":197},115376,"2.1.0","## What's Changed\r\n* feat: add function to get build param from XGB by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F190\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002F2.0.0...2.1.0","2023-05-03T05:16:56",{"id":199,"version":200,"summary_zh":201,"released_at":202},115377,"2.0.0","## What's Changed\r\n* doc: Update installation.rst.txt by @loc-aitomatic in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F153\r\n* Better CI pipeline with test matrix including all supported Python version and all supported OS by @vuonghoainam in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F158\r\n* Merge code from branch refactor\u002Fxg-boost-model to refactor\u002Fmajor_change_with_k1st  by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F186\r\n* Update h1st-graph.rst.txt by @Tqhuyen in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F185\r\n* [WIP] Refactor\u002Fmajor change with k1st by @vuonghoainam in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F183\r\n* Remove tensorflow from h1st dependencies by @vuonghoainam in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F161\r\n* Add model metrics and stats to Model class by @phamhoangtuan in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F188\r\n\r\n## New Contributors\r\n* @loc-aitomatic made their first contribution in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F153\r\n* @vuonghoainam made their first contribution in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F158\r\n* @Tqhuyen made their first contribution in https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fpull\u002F185\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fh1st-ai\u002Fh1st\u002Fcompare\u002F0.1.13...2.0.0","2023-03-01T15:35:23",{"id":204,"version":205,"summary_zh":206,"released_at":207},115378,"pre_ensemble_v2020.10.20","AutoCyber project (pre-ensemble refactoring) is using this.","2020-10-21T00:20:52"]