[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-bentoml--Yatai":3,"tool-bentoml--Yatai":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":79,"owner_twitter":80,"owner_website":81,"owner_url":82,"languages":83,"stars":122,"forks":123,"last_commit_at":124,"license":125,"difficulty_score":126,"env_os":127,"env_gpu":128,"env_ram":128,"env_deps":129,"category_tags":137,"github_topics":138,"view_count":126,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":145,"updated_at":146,"faqs":147,"releases":175},1384,"bentoml\u002FYatai","Yatai","Model Deployment at Scale on Kubernetes 🦄️","Yatai 是一款专为 BentoML 设计的 Kubernetes 部署操作符，旨在实现机器学习模型的大规模部署。其名称源自日语“屋台”，寓意着灵活便捷的服务交付能力。Yatai 有效解决了机器学习服务在生产环境中难以统一管理、弹性扩展的难题。通过它，DevOps 团队能将模型服务无缝融入 GitOps 工作流，在任意 Kubernetes 集群上轻松完成部署与扩缩容。\n\nYatai 非常适合需要构建稳定 AI 基础设施的开发者、运维工程师及 AI 研究人员。技术上，它坚持云原生路线，利用 Kubernetes 自定义资源定义（CRD）机制，使模型服务管理体验与传统应用保持一致。此外，它还针对 CI\u002FCD 流程进行了深度优化，支持高效自动化发布。当前 Yatai 社区活跃，正持续推动版本迭代，致力于为机器学习工程化提供坚实支撑。","# 🦄️ Yatai: Model Deployment at Scale on Kubernetes\n\n[![actions_status](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Fworkflows\u002FRelease\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Factions)\n[![join_slack](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fbentoml_Yatai_readme_deb044809ed4.png)](https:\u002F\u002Fjoin.slack.bentoml.org)\n\n⚠️ Yatai for [BentoML 1.2](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002Freleases\u002Ftag\u002Fv1.2.0) is currently under construction. See [Yatai 2.0 Proposal](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fissues\u002F504) for more details. \n\n---\n\nYatai (屋台, food cart) is the Kubernetes deployment operator for [BentoML](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fbentoml).\n\nIt let DevOps teams to seamlessly integrate BentoML into their GitOps workflow, for deploying and scaling Machine Learning services on any Kubernetes cluster.\n\n👉 [Join our Slack community today!](https:\u002F\u002Fl.bentoml.com\u002Fjoin-slack)\n\n---\n\n## Why Yatai?\n\nYatai empowers developers to deploy [BentoML](https:\u002F\u002Fgithub.com\u002Fbentoml) on Kubernetes, optimized for CI\u002FCD and DevOps workflow.\n\nYatai is Cloud native and DevOps friendly. Via its Kubernetes-native workflow, specifically the [BentoDeployment CRD](https:\u002F\u002Fdocs.yatai.io\u002Fen\u002Flatest\u002Fconcepts\u002Fbentodeployment_crd.html) (Custom Resource Definition), DevOps teams can easily fit BentoML powered services into their existing workflow.\n\n\n## Getting Started\n\n- 📖 [Documentation](https:\u002F\u002Fdocs.yatai.io\u002F) - Overview of the Yatai docs and related resources\n- ⚙️ [Installation](https:\u002F\u002Fdocs.yatai.io\u002Fen\u002Flatest\u002Finstallation\u002Findex.html) - Hands-on instruction on how to install Yatai for production use\n- 👉 [Join Community Slack](https:\u002F\u002Fl.linklyhq.com\u002Fl\u002FktPW) - Get help from our community and maintainers\n\n\n## Quick Tour\n\nLet's try out Yatai locally in a minikube cluster!\n\n### ⚙️ Prerequisites:\n  * Install latest minikube: https:\u002F\u002Fminikube.sigs.k8s.io\u002Fdocs\u002Fstart\u002F\n  * Install latest Helm: https:\u002F\u002Fhelm.sh\u002Fdocs\u002Fintro\u002Finstall\u002F\n  * Start a minikube Kubernetes cluster: `minikube start --cpus 4 --memory 4096`, if you are using macOS, you should use [hyperkit](https:\u002F\u002Fminikube.sigs.k8s.io\u002Fdocs\u002Fdrivers\u002Fhyperkit\u002F) driver to prevent the macOS docker desktop [network limitation](https:\u002F\u002Fdocs.docker.com\u002Fdesktop\u002Fnetworking\u002F#i-cannot-ping-my-containers)\n  * Check that minikube cluster status is \"running\": `minikube status`\n  * Make sure your `kubectl` is configured with `minikube` context: `kubectl config current-context`\n  * Enable ingress controller: `minikube addons enable ingress`\n\n### 🚧 Install Yatai\n\nInstall Yatai with the following script:\n\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai\u002Fmain\u002Fscripts\u002Fquick-install-yatai.sh\")\n```\n\nThis script will install Yatai along with its dependencies (PostgreSQL and MinIO) on\nyour minikube cluster. \n\nNote that this installation script is made for development and testing use only.\nFor production deployment, check out the [Installation Guide](https:\u002F\u002Fdocs.yatai.io\u002Fen\u002Flatest\u002Finstallation\u002Findex.html).\n\nTo access Yatai web UI, run the following command and keep the terminal open:\n\n```bash\nkubectl --namespace yatai-system port-forward svc\u002Fyatai 8080:80\n```\n\nIn a separate terminal, run:\n\n```bash\nYATAI_INITIALIZATION_TOKEN=$(kubectl get secret yatai-env --namespace yatai-system -o jsonpath=\"{.data.YATAI_INITIALIZATION_TOKEN}\" | base64 --decode)\necho \"Open in browser: http:\u002F\u002F127.0.0.1:8080\u002Fsetup?token=$YATAI_INITIALIZATION_TOKEN\"\n``` \n\nOpen the URL printed above from your browser to finish admin account setup.\n\n\n### 🍱 Push Bento to Yatai\n\nFirst, get an API token and login to the BentoML CLI:\n\n* Keep the `kubectl port-forward` command in the step above running\n* Go to Yatai's API tokens page: http:\u002F\u002F127.0.0.1:8080\u002Fapi_tokens\n* Create a new API token from the UI, making sure to assign \"API\" access under \"Scopes\"\n* Copy the login command upon token creation and run as a shell command, e.g.:\n\n    ```bash\n    bentoml yatai login --api-token {YOUR_TOKEN} --endpoint http:\u002F\u002F127.0.0.1:8080\n    ```\n\nIf you don't already have a Bento built, run the following commands from the [BentoML Quickstart Project](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002Ftree\u002Fmain\u002Fexamples\u002Fquickstart) to build a sample Bento:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fbentoml.git && cd .\u002Fexamples\u002Fquickstart\npip install -r .\u002Frequirements.txt\npython train.py\nbentoml build\n```\n\nPush your newly built Bento to Yatai:\n\n```bash\nbentoml push iris_classifier:latest\n```\n\n\n### 🔧 Install yatai-image-builder component\n\nYatai's image builder feature comes as a separate component, you can install it via the following\nscript:\n\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai-image-builder\u002Fmain\u002Fscripts\u002Fquick-install-yatai-image-builder.sh\")\n```\n\nThis will install the `BentoRequest` CRD([Custom Resource Definition](https:\u002F\u002Fkubernetes.io\u002Fdocs\u002Fconcepts\u002Fextend-kubernetes\u002Fapi-extension\u002Fcustom-resources\u002F)) and `Bento` CRD\nin your cluster. Similarly, this script is made for development and testing purposes only.\n\n### 🔧 Install yatai-deployment component\n\nYatai's Deployment feature comes as a separate component, you can install it via the following\nscript:\n\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai-deployment\u002Fmain\u002Fscripts\u002Fquick-install-yatai-deployment.sh\")\n```\n\nThis will install the `BentoDeployment` CRD([Custom Resource Definition](https:\u002F\u002Fkubernetes.io\u002Fdocs\u002Fconcepts\u002Fextend-kubernetes\u002Fapi-extension\u002Fcustom-resources\u002F))\nin your cluster and enable the deployment UI on Yatai. Similarly, this script is made for development and testing purposes only.\n\n### 🚢 Deploy Bento!\n\nOnce the `yatai-deployment` component was installed, Bentos pushed to Yatai can be deployed to your \nKubernetes cluster and exposed via a Service endpoint. \n\nA Bento Deployment can be created via applying a BentoDeployment resource:\n\nDefine your Bento deployment in a `my_deployment.yaml` file:\n\n```yaml\napiVersion: resources.yatai.ai\u002Fv1alpha1\nkind: BentoRequest\nmetadata:\n    name: iris-classifier\n    namespace: yatai\nspec:\n    bentoTag: iris_classifier:3oevmqfvnkvwvuqj  # check the tag by `bentoml list iris_classifier`\n---\napiVersion: serving.yatai.ai\u002Fv2alpha1\nkind: BentoDeployment\nmetadata:\n    name: my-bento-deployment\n    namespace: yatai\nspec:\n    bento: iris-classifier\n    ingress:\n        enabled: true\n    resources:\n        limits:\n            cpu: \"500m\"\n            memory: \"512Mi\"\n        requests:\n            cpu: \"250m\"\n            memory: \"128Mi\"\n    autoscaling:\n        maxReplicas: 10\n        minReplicas: 2\n    runners:\n        - name: iris_clf\n          resources:\n              limits:\n                  cpu: \"1000m\"\n                  memory: \"1Gi\"\n              requests:\n                  cpu: \"500m\"\n                  memory: \"512Mi\"\n          autoscaling:\n              maxReplicas: 4\n              minReplicas: 1\n```\n\nApply the deployment to your minikube cluster:\n```bash\nkubectl apply -f my_deployment.yaml\n```\n\nNow you can check the deployment status via `kubectl get BentoDeployment -n my-bento-deployment`\n\n\n\n## Community\n\n-   To report a bug or suggest a feature request, use [GitHub Issues](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Fissues\u002Fnew\u002Fchoose).\n-   For other discussions, use [GitHub Discussions](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002Fdiscussions) under the [BentoML repo](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002F)\n-   To receive release announcements and get support, join us on [Slack](https:\u002F\u002Fjoin.slack.bentoml.org).\n\n## Contributing\n\nThere are many ways to contribute to the project:\n\n-   If you have any feedback on the project, share it with the community in [GitHub Discussions](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002Fdiscussions) under the [BentoML repo](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002F).\n-   Report issues you're facing and \"Thumbs up\" on issues and feature requests that are relevant to you.\n-   Investigate bugs and review other developers' pull requests.\n-   Contributing code or documentation to the project by submitting a GitHub pull request. See the [development guide](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Fblob\u002Fmain\u002FDEVELOPMENT.md).\n\n\n\n\n## Licence\n\n[Elastic License 2.0 (ELv2)](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Fblob\u002Fmain\u002FLICENSE.md)\n","# 🦄️ Yatai：在 Kubernetes（容器编排系统）上大规模部署模型\n\n[![actions_status](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Fworkflows\u002FRelease\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Factions)\n[![join_slack](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fbentoml_Yatai_readme_deb044809ed4.png)](https:\u002F\u002Fjoin.slack.bentoml.org)\n\n⚠️ 适用于 [BentoML 1.2](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002Freleases\u002Ftag\u002Fv1.2.0) 的 Yatai 目前正在建设中。更多详情请参阅 [Yatai 2.0 Proposal](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fissues\u002F504)。 \n\n---\n\nYatai（屋台，意为食品车）是 [BentoML](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fbentoml) 的 Kubernetes（容器编排系统）部署操作符。\n\n它让 DevOps（开发运维）团队能够无缝地将 BentoML 集成到他们的 GitOps（基于 Git 的工作流）中，以便在任何 Kubernetes 集群上部署和扩展机器学习服务。\n\n👉 [今天加入我们的 Slack 社区！](https:\u002F\u002Fl.bentoml.com\u002Fjoin-slack)\n\n---\n\n## 为什么选择 Yatai？\n\nYatai 赋能开发者在 Kubernetes（容器编排系统）上部署 [BentoML](https:\u002F\u002Fgithub.com\u002Fbentoml)，针对 CI\u002FCD（持续集成\u002F持续交付）和 DevOps（开发运维）工作流进行了优化。\n\nYatai 是云原生且对 DevOps（开发运维）友好的。通过其 Kubernetes 原生工作流，特别是 [BentoDeployment CRD](https:\u002F\u002Fdocs.yatai.io\u002Fen\u002Flatest\u002Fconcepts\u002Fbentodeployment_crd.html)（自定义资源定义），DevOps 团队可以轻松地将由 BentoML 驱动的服务融入现有工作流。\n\n\n## 开始使用\n\n- 📖 [文档](https:\u002F\u002Fdocs.yatai.io\u002F) - Yatai 文档及相关资源的概述\n- ⚙️ [安装](https:\u002F\u002Fdocs.yatai.io\u002Fen\u002Flatest\u002Finstallation\u002Findex.html) - 关于如何为生产环境安装 Yatai 的手把手指南\n- 👉 [加入社区 Slack](https:\u002F\u002Fl.linklyhq.com\u002Fl\u002FktPW) - 从我们的社区和维护者那里获得帮助\n\n\n## 快速体验\n\n让我们在一个 minikube 集群中本地尝试一下 Yatai！\n\n### ⚙️ 前置条件：\n  * 安装最新版本的 minikube：https:\u002F\u002Fminikube.sigs.k8s.io\u002Fdocs\u002Fstart\u002F\n  * 安装最新版本的 Helm：https:\u002F\u002Fhelm.sh\u002Fdocs\u002Fintro\u002Finstall\u002F\n  * 启动一个 minikube Kubernetes 集群：`minikube start --cpus 4 --memory 4096`，如果你使用的是 macOS，你应该使用 [hyperkit](https:\u002F\u002Fminikube.sigs.k8s.io\u002Fdocs\u002Fdrivers\u002Fhyperkit\u002F) 驱动程序来防止 macOS docker desktop [网络限制](https:\u002F\u002Fdocs.docker.com\u002Fdesktop\u002Fnetworking\u002F#i-cannot-ping-my-containers)\n  * 检查 minikube 集群状态是否为“运行中”：`minikube status`\n  * 确保你的 `kubectl` 已配置为 `minikube` 上下文：`kubectl config current-context`\n  * 启用 ingress 控制器（入口控制器）：`minikube addons enable ingress`\n\n### 🚧 安装 Yatai\n\n使用以下脚本安装 Yatai：\n\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai\u002Fmain\u002Fscripts\u002Fquick-install-yatai.sh\")\n```\n\n此脚本将在你的 minikube 集群上安装 Yatai 及其依赖项（PostgreSQL 和 MinIO）。 \n\n注意，此安装脚本仅用于开发和测试用途。\n对于生产部署，请查看 [安装指南](https:\u002F\u002Fdocs.yatai.io\u002Fen\u002Flatest\u002Finstallation\u002Findex.html)。\n\n要访问 Yatai Web UI（Web 用户界面），运行以下命令并保持终端打开：\n\n```bash\nkubectl --namespace yatai-system port-forward svc\u002Fyatai 8080:80\n```\n\n在另一个终端中运行：\n\n```bash\nYATAI_INITIALIZATION_TOKEN=$(kubectl get secret yatai-env --namespace yatai-system -o jsonpath=\"{.data.YATAI_INITIALIZATION_TOKEN}\" | base64 --decode)\necho \"Open in browser: http:\u002F\u002F127.0.0.1:8080\u002Fsetup?token=$YATAI_INITIALIZATION_TOKEN\"\n``` \n\n从浏览器打开上面打印的 URL 以完成管理员账户设置。\n\n\n### 🍱 推送 Bento 到 Yatai\n\n首先，获取 API 令牌并登录 BentoML CLI（命令行界面）：\n\n* 保持上述步骤中的 `kubectl port-forward` 命令正在运行\n* 转到 Yatai 的 API 令牌页面：http:\u002F\u002F127.0.0.1:8080\u002Fapi_tokens\n* 从 UI 创建一个新的 API 令牌，确保在\"Scopes\"下分配\"API\"访问权限\n* 复制创建令牌时的登录命令并作为 shell 命令运行，例如：\n\n    ```bash\n    bentoml yatai login --api-token {YOUR_TOKEN} --endpoint http:\u002F\u002F127.0.0.1:8080\n    ```\n\n如果你尚未构建好 Bento，请从 [BentoML Quickstart Project](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002Ftree\u002Fmain\u002Fexamples\u002Fquickstart) 运行以下命令来构建示例 Bento：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fbentoml.git && cd .\u002Fexamples\u002Fquickstart\npip install -r .\u002Frequirements.txt\npython train.py\nbentoml build\n```\n\n将你新构建的 Bento 推送到 Yatai：\n\n```bash\nbentoml push iris_classifier:latest\n```\n\n\n### 🔧 安装 yatai-image-builder 组件\n\nYatai 的镜像构建器功能作为一个单独的组件提供，你可以通过以下脚本安装它：\n\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai-image-builder\u002Fmain\u002Fscripts\u002Fquick-install-yatai-image-builder.sh\")\n```\n\n这将在你的集群中安装 `BentoRequest` CRD（[自定义资源定义](https:\u002F\u002Fkubernetes.io\u002Fdocs\u002Fconcepts\u002Fextend-kubernetes\u002Fapi-extension\u002Fcustom-resources\u002F)）和 `Bento` CRD。同样，此脚本仅用于开发和测试目的。\n\n### 🔧 安装 yatai-deployment 组件\n\nYatai 的部署功能作为一个单独的组件提供，你可以通过以下脚本安装它：\n\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai-deployment\u002Fmain\u002Fscripts\u002Fquick-install-yatai-deployment.sh\")\n```\n\n这将在你的集群中安装 `BentoDeployment` CRD（[自定义资源定义](https:\u002F\u002Fkubernetes.io\u002Fdocs\u002Fconcepts\u002Fextend-kubernetes\u002Fapi-extension\u002Fcustom-resources\u002F)）并在 Yatai 上启用部署 UI。同样，此脚本仅用于开发和测试目的。\n\n### 🚢 部署 Bento!\n\n一旦安装了 `yatai-deployment` 组件，推送到 Yatai 的 Bento 就可以部署到你的 Kubernetes 集群并通过 Service 端点（服务端点）暴露。 \n\n可以通过应用 BentoDeployment 资源来创建 Bento 部署：\n\n在 `my_deployment.yaml` 文件中定义你的 Bento 部署：\n\n```yaml\napiVersion: resources.yatai.ai\u002Fv1alpha1\nkind: BentoRequest\nmetadata:\n    name: iris-classifier\n    namespace: yatai\nspec:\n    bentoTag: iris_classifier:3oevmqfvnkvwvuqj  # check the tag by `bentoml list iris_classifier`\n---\napiVersion: serving.yatai.ai\u002Fv2alpha1\nkind: BentoDeployment\nmetadata:\n    name: my-bento-deployment\n    namespace: yatai\nspec:\n    bento: iris-classifier\n    ingress:\n        enabled: true\n    resources:\n        limits:\n            cpu: \"500m\"\n            memory: \"512Mi\"\n        requests:\n            cpu: \"250m\"\n            memory: \"128Mi\"\n    autoscaling:\n        maxReplicas: 10\n        minReplicas: 2\n    runners:\n        - name: iris_clf\n          resources:\n              limits:\n                  cpu: \"1000m\"\n                  memory: \"1Gi\"\n              requests:\n                  cpu: \"500m\"\n                  memory: \"512Mi\"\n          autoscaling:\n              maxReplicas: 4\n              minReplicas: 1\n```\n\n将部署应用到你的 minikube 集群：\n```bash\nkubectl apply -f my_deployment.yaml\n```\n\n现在你可以通过 `kubectl get BentoDeployment -n my-bento-deployment` 检查部署状态\n\n## 社区\n\n-   若要报告错误或提出功能建议，请使用 [GitHub Issues](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Fissues\u002Fnew\u002Fchoose)。\n-   对于其他讨论，请在 [BentoML 仓库](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002F) 下的 [GitHub Discussions](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002Fdiscussions) 中进行。\n-   若要接收版本发布通知并获得支持，请加入我们的 [Slack](https:\u002F\u002Fjoin.slack.bentoml.org)。\n\n## 贡献\n\n有多种方式可以为该项目做出贡献：\n\n-   如果您对项目有任何反馈，请在 [BentoML 仓库](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002F) 下的 [GitHub Discussions](https:\u002F\u002Fgithub.com\u002Fbentoml\u002FBentoML\u002Fdiscussions) 中与社区分享。\n-   报告您遇到的问题，并对与您相关的问题和功能建议“点赞”。\n-   调查错误并审查其他开发者的拉取请求 (Pull Request)。\n-   通过提交 GitHub 拉取请求向项目贡献代码或文档。请参阅 [开发指南](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Fblob\u002Fmain\u002FDEVELOPMENT.md)。\n\n## 许可\n\n[Elastic License 2.0 (ELv2)](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fyatai\u002Fblob\u002Fmain\u002FLICENSE.md)","# 🦄️ Yatai 快速上手指南\n\nYatai 是 [BentoML](https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fbentoml) 在 Kubernetes 上的部署操作符，专为 CI\u002FCD 和 DevOps 工作流优化。通过 Kubernetes 原生工作流（如 `BentoDeployment` CRD），您可以轻松将机器学习服务集成到现有基础设施中。\n\n> ⚠️ **注意**：当前版本主要用于开发和测试。生产环境部署请参考官方文档。\n\n## 环境准备\n\n在开始之前，请确保本地环境满足以下要求：\n\n- **Minikube**: 安装最新版并启动集群（建议配置 4 CPU \u002F 4GB 内存）。\n- **Helm**: 安装最新版。\n- **Kubectl**: 确保已配置与 Minikube 的上下文连接。\n- **Ingress Controller**: 需在集群中启用。\n\n执行以下命令初始化环境：\n\n```bash\n# 启动 Minikube (macOS 用户建议使用 hyperkit 驱动)\nminikube start --cpus 4 --memory 4096\n\n# 检查集群状态\nminikube status\n\n# 确认 kubectl 上下文\nkubectl config current-context\n\n# 启用 Ingress 控制器\nminikube addons enable ingress\n```\n\n## 安装步骤\n\n### 1. 安装 Yatai 核心组件\n\n运行以下脚本安装 Yatai 及其依赖（PostgreSQL 和 MinIO）：\n\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai\u002Fmain\u002Fscripts\u002Fquick-install-yatai.sh\")\n```\n\n### 2. 访问 Web UI 并设置管理员账户\n\n保持终端运行，执行端口转发：\n\n```bash\nkubectl --namespace yatai-system port-forward svc\u002Fyatai 8080:80\n```\n\n在另一个终端获取初始化令牌并打开浏览器：\n\n```bash\nYATAI_INITIALIZATION_TOKEN=$(kubectl get secret yatai-env --namespace yatai-system -o jsonpath=\"{.data.YATAI_INITIALIZATION_TOKEN}\" | base64 --decode)\necho \"Open in browser: http:\u002F\u002F127.0.0.1:8080\u002Fsetup?token=$YATAI_INITIALIZATION_TOKEN\"\n```\n\n复制输出的 URL 在浏览器中完成管理员账号设置。\n\n### 3. 安装扩展组件\n\n为了支持镜像构建和部署功能，需额外安装以下组件：\n\n**安装 Image Builder：**\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai-image-builder\u002Fmain\u002Fscripts\u002Fquick-install-yatai-image-builder.sh\")\n```\n\n**安装 Deployment 组件：**\n```bash\nbash \u003C(curl -s \"https:\u002F\u002Fraw.githubusercontent.com\u002Fbentoml\u002Fyatai-deployment\u002Fmain\u002Fscripts\u002Fquick-install-yatai-deployment.sh\")\n```\n\n## 基本使用\n\n### 1. 登录 BentoML CLI\n\n在 Yatai UI 的 API Tokens 页面创建新令牌（Scope 选择 \"API\"），然后运行：\n\n```bash\nbentoml yatai login --api-token {YOUR_TOKEN} --endpoint http:\u002F\u002F127.0.0.1:8080\n```\n\n### 2. 构建并推送模型\n\n如果没有现成的 Bento，可克隆示例项目构建：\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fbentoml\u002Fbentoml.git && cd .\u002Fexamples\u002Fquickstart\npip install -r .\u002Frequirements.txt\npython train.py\nbentoml build\n```\n\n将构建好的 Bento 推送到 Yatai：\n\n```bash\nbentoml push iris_classifier:latest\n```\n\n### 3. 部署到 Kubernetes\n\n创建一个名为 `my_deployment.yaml` 的文件，定义资源规格：\n\n```yaml\napiVersion: resources.yatai.ai\u002Fv1alpha1\nkind: BentoRequest\nmetadata:\n    name: iris-classifier\n    namespace: yatai\nspec:\n    bentoTag: iris_classifier:3oevmqfvnkvwvuqj  # 请使用 bentoml list iris_classifier 查看实际标签\n---\napiVersion: serving.yatai.ai\u002Fv2alpha1\nkind: BentoDeployment\nmetadata:\n    name: my-bento-deployment\n    namespace: yatai\nspec:\n    bento: iris-classifier\n    ingress:\n        enabled: true\n    resources:\n        limits:\n            cpu: \"500m\"\n            memory: \"512Mi\"\n        requests:\n            cpu: \"250m\"\n            memory: \"128Mi\"\n    autoscaling:\n        maxReplicas: 10\n        minReplicas: 2\n    runners:\n        - name: iris_clf\n          resources:\n              limits:\n                  cpu: \"1000m\"\n                  memory: \"1Gi\"\n              requests:\n                  cpu: \"500m\"\n                  memory: \"512Mi\"\n          autoscaling:\n              maxReplicas: 4\n              minReplicas: 1\n```\n\n应用部署配置：\n\n```bash\nkubectl apply -f my_deployment.yaml\n```\n\n最后检查部署状态：\n\n```bash\nkubectl get BentoDeployment -n yatai\n```","某电商公司算法团队负责核心推荐系统，面临每周多次迭代模型并部署至 Kubernetes 集群的高频需求。\n\n### 没有 Yatai 时\n- 工程师需手动维护大量 Kubernetes YAML 配置文件，细微参数修改极易引发部署故障。\n- 模型版本与容器镜像标签脱节，线上排查问题时难以快速定位具体代码版本。\n- 缺乏标准化自动化流水线，从模型训练完成到正式上线平均耗时超过两天。\n- 面对突发流量无法动态调整副本数，导致服务延迟增加甚至系统崩溃。\n\n### 使用 Yatai 后\n- Yatai 将复杂部署逻辑封装为自定义资源定义，开发人员只需关注模型本身而非底层设施。\n- 结合 GitOps 工作流实现严格版本控制，任何变更皆有记录，支持秒级快速回滚。\n- 内置 CI\u002FCD 深度集成，模型打包后自动推送至 Yatai 并无缝触发灰度发布流程。\n- 依据实时 CPU 和内存指标自动弹性伸缩，确保在大促期间推荐服务始终保持稳定运行。\n\nYatai 彻底打通了算法开发与运维的壁垒，实现了机器学习服务在云原生环境下的敏捷交付与规模化管控。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fbentoml_Yatai_6526c9ec.png","bentoml","BentoML","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fbentoml_c36be549.jpg","Build fast and reliable model serving systems",null,"bentomlai","https:\u002F\u002Fbentoml.com","https:\u002F\u002Fgithub.com\u002Fbentoml",[84,88,92,96,100,104,108,112,116,119],{"name":85,"color":86,"percentage":87},"TypeScript","#3178c6",54.3,{"name":89,"color":90,"percentage":91},"Go","#00ADD8",36.9,{"name":93,"color":94,"percentage":95},"CSS","#663399",2.9,{"name":97,"color":98,"percentage":99},"Shell","#89e051",2.8,{"name":101,"color":102,"percentage":103},"PLpgSQL","#336790",0.9,{"name":105,"color":106,"percentage":107},"Nix","#7e7eff",0.6,{"name":109,"color":110,"percentage":111},"Makefile","#427819",0.4,{"name":113,"color":114,"percentage":115},"Smarty","#f0c040",0.3,{"name":117,"color":118,"percentage":115},"JavaScript","#f1e05a",{"name":120,"color":121,"percentage":115},"HTML","#e34c26",837,76,"2026-03-28T15:26:30","NOASSERTION",4,"Linux, macOS","未说明",{"notes":130,"python":128,"dependencies":131},"Yatai 是 BentoML 的 Kubernetes 部署操作符。提供的快速安装脚本仅适用于开发和测试环境，生产环境请查阅官方安装指南。本地测试需要配置 Minikube、Helm 和 Ingress 控制器。包含 yatai-image-builder 和 yatai-deployment 等独立组件。",[132,133,134,135,136],"PostgreSQL","MinIO","Helm","kubectl","minikube",[13],[75,139,140,141,142,143,144],"kubernetes","mlops","model-deployment","model-serving","k8s","machine-learning","2026-03-27T02:49:30.150509","2026-04-06T08:40:10.322068",[148,153,157,161,166,170],{"id":149,"question_zh":150,"answer_zh":151,"source_url":152},2401,"执行 bento push 命令失败，提示无法获取 ingress yatai-docker-registry 怎么办？","这是由于 BentoML 1.0rc 与 Yatai 的兼容性问题导致的。建议暂时降级使用稳定版本组合：克隆 Gallery 仓库并切换到特定提交（commit: 418e93582145c4b07c2c63b11cd00b1061e674fa），在 quickstart\u002Frequirements.txt 中指定 bentoml==1.0.0-a7，并使用 helm install yatai yatai\u002Fyatai -n yatai-system --create-namespace --version v0.3.2 部署 Yatai。","https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fissues\u002F246",{"id":154,"question_zh":155,"answer_zh":156,"source_url":152},2402,"遇到 BentoML 与 Yatai 兼容性问题时，为什么推荐使用 1.0.0-a7 而不是 0.13 版本？","因为 1.0rc 与 Yatai 存在尚未解决的兼容性冲突。虽然降级到 0.13 可行，但需要大量的自定义配置才能使其与 Yatai 配合工作。使用 1.0.0-a7 可以更快地验证端到端功能，直到 rc 版本的问题被彻底修复。",{"id":158,"question_zh":159,"answer_zh":160,"source_url":152},2403,"在 Minikube 本地环境中运行 sudo minikube tunnel 报错找不到 Profile 如何处理？","可以尝试不加 sudo 直接运行 minikube tunnel，它会提示输入密码。同时请确认已运行 minikube start 启动了集群，并通过 minikube profile list 查看所有可用 profile 以确保环境配置正确。",{"id":162,"question_zh":163,"answer_zh":164,"source_url":165},2404,"使用自定义 Helm Chart 安装 Yatai 后，部署 Bento 时报连接拒绝（connection refused）错误如何解决？","这是因为 Yatai 的 Deployment CRD Controller 依赖 Helm Chart 名称来自动获取 Yatai 地址。解决方法是将你的自定义 Helm Chart 名称重命名为 yatai，并确保 Release Name 中包含 'yatai'，以满足系统对端点检测的假设条件。","https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fissues\u002F210",{"id":167,"question_zh":168,"answer_zh":169,"source_url":165},2405,"为什么 Yatai 安装对 Helm Chart 的名称和 Release Name 有特定限制？","目前 Yatai 部署逻辑基于两个假设：1) K8s 集群中只能安装一个 Yatai 实例；2) Yatai 必须通过官方 Helm Chart 安装，或者 Chart 名称\u002FRelease Name 必须包含 'yatai'。这是为了确保能正确解析 YATAI_ENDPOINT 环境变量。",{"id":171,"question_zh":172,"answer_zh":173,"source_url":174},2406,"Yatai 部署过程中 Pod 卡在 ContainerCreating 状态或出现 Webhook 服务未找到错误如何排查？","建议优先检查部署操作符的日志以获取详细错误信息。运行命令 kubectl -n yatai-operators logs -f deploy\u002Fdeployment-yatai-deployment-comp-operator 查看具体报错，这通常能揭示挂载卷超时或控制器 reconciler 的错误原因。","https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fissues\u002F276",[176,181,186,191,196,201,206,211,216,221,226,231,236,241,246,251,256,261,266,271],{"id":177,"version":178,"summary_zh":179,"released_at":180},115628,"v1.1.1","## What's Changed\r\n* fix(doc): GPU resources by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F425\r\n* chores(doc): align the eksctl command style by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F426\r\n* fix(docs): fix the solution for yatai-image-builder-crds installation failure by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F427\r\n* feat(dashboard): update docs link by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F428\r\n* feat: show yatai components by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F429\r\n* feat(dashboard): show bento in deployment page by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F430\r\n* fix(api-server): use correct client to delete bentodeployment resource by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F433\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.0...v1.1.1","2023-01-10T11:13:43",{"id":182,"version":183,"summary_zh":184,"released_at":185},115616,"v1.1.13","## What's Changed\r\n* Fix(helm-chart): use a range finction instead of toYaml for commonLabels by @JohGirard in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F488\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.12...v1.1.13","2023-10-09T10:21:37",{"id":187,"version":188,"summary_zh":189,"released_at":190},115617,"v1.1.12","## What's Changed\r\n* Fix memory resource unit for CRD deployment example in README.md by @Curt-Park in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F485\r\n* feat(helm-chart): add commonLabels capability by @JohGirard in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F487\r\n\r\n## New Contributors\r\n* @Curt-Park made their first contribution in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F485\r\n* @JohGirard made their first contribution in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F487\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.11...v1.1.12","2023-09-27T09:19:03",{"id":192,"version":193,"summary_zh":194,"released_at":195},115618,"v1.1.11","## What's Changed\r\n* chore: add label length for label with OpenLLM built Bento by @aarnphm in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F484\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.10...v1.1.11","2023-09-01T02:20:53",{"id":197,"version":198,"summary_zh":199,"released_at":200},115619,"v1.1.10","## What's Changed\r\n* fix(doc): k8s version in installation by @bojiang in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F461\r\n* fix(doc): wrong indent in the example yaml by @bojiang in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F460\r\n* fix: the quick installation script will ignore the issue of S3 connection failure by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F462\r\n* chore(deps): update k8s packages to same version by @DavidSpek in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F464\r\n* chores: update installation requirements in docs by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F467\r\n* fix(doc): add missing download line for dashboard setup by @larme in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F469\r\n* doc: Update new documentation link by @jianshen92 in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F473\r\n* doc: Fix broken doc links by @frostming in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F476\r\n* feat: map not found error returned by gorm by @frostming in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F477\r\n* fix(api-server): report bento upload error by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F474\r\n\r\n## New Contributors\r\n* @DavidSpek made their first contribution in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F464\r\n* @larme made their first contribution in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F469\r\n* @jianshen92 made their first contribution in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F473\r\n* @frostming made their first contribution in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F476\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.9...v1.1.10","2023-08-01T02:41:11",{"id":202,"version":203,"summary_zh":204,"released_at":205},115620,"v1.1.9","**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.8...v1.1.9","2023-04-05T06:26:41",{"id":207,"version":208,"summary_zh":209,"released_at":210},115621,"v1.1.8","## What's Changed\r\n* ci: add spell checker and fix existing typo by @hezhizhen in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F456\r\n* fix: remove CDN dependency from JSON editor by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F459\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.7...v1.1.8","2023-03-27T13:45:21",{"id":212,"version":213,"summary_zh":214,"released_at":215},115622,"v1.1.7","## What's Changed\r\n* Update README.md by @timliubentoml in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F450\r\n* feat(api-server): add security for openapi by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F451\r\n* fix(helm-chart): specify the YATAI_SYSTEM_NAMESPACE environment variable by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F455\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.6...v1.1.7","2023-03-02T10:25:40",{"id":217,"version":218,"summary_zh":219,"released_at":220},115623,"v1.1.6","## What's Changed\r\n* fix(dashboard): envs and custom resources will be ignored during the deployment form merge phase by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F447\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.5...v1.1.6","2023-02-09T11:23:08",{"id":222,"version":223,"summary_zh":224,"released_at":225},115624,"v1.1.5","## What's Changed\r\n* fix(docs+scripts): fix loki and promtail version by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F443\r\n* fix(scripts+api-server): install new minio helm chart and use k8s ca.crt in minio client by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F444\r\n* fix(api-server): s3 cluster tls by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F445\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.4...v1.1.5","2023-02-03T15:13:20",{"id":227,"version":228,"summary_zh":229,"released_at":230},115625,"v1.1.4","## What's Changed\r\n* fix(scripts): make get-yatai-system-kubeconfig.sh compatible with kubernetes 1.24+ by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F441\r\n* fix(api-server): no correct conversion runner autoscaling by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F442\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.3...v1.1.4","2023-02-01T16:01:46",{"id":232,"version":233,"summary_zh":234,"released_at":235},115626,"v1.1.3","## What's Changed\r\n* feat(docs): upgrade migration docs by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F435\r\n* fix(api-server): the extraPodSpec of the runner is not updated by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F439\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.2...v1.1.3","2023-01-21T16:55:08",{"id":237,"version":238,"summary_zh":239,"released_at":240},115627,"v1.1.2","## What's Changed\r\n* feat: deployment json editor by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F434\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.1.1...v1.1.2","2023-01-12T18:04:29",{"id":242,"version":243,"summary_zh":244,"released_at":245},115629,"v1.1.0","🦄 Yatai `v1.1.0` is released with improved component modularization and cloud native capabilities.\r\n\r\n- Split `yatai-deployment` into two components, `yatai-image-builder` and `yatai-deployment`, for better separation of concerns. `yatai-image-builder` is responsible for building container images for bentos, and `yatai-deployment` is responsible for deploying the bentos to k8s. See how to upgrade from `v1.0.*` in the [documentation](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Fupgrade\u002Fmigration_yatai-deployment_from_1-0-x_to_1-1-x.html).\r\n- Added [BentoRequest](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Fconcepts\u002Fbentorequest_crd.html) CRD and [Bento](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Fconcepts\u002Fbento_crd.html) CRD. `yatai-image-builder` is responsible for reconciling the BentoRequest CR, building the container image, and generating the Bento CR. `yatai-deployment` continues to be responsible for reconciling the BentoDeployment CRD. However, the BentoDeployment CRD now requires a Bento CR  instead of a bento tag. Therefore, `yatai-deployment` can now function independently of `yatai` and `yatai-image-builder`. When using `yatai-deployment` independently, users must manually create the Bento CR. See Yatai [architecture](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Fconcepts\u002Farchitecture.html) documentation for more details.\r\n- Steps for deploying bentos from the Web UI remains unchanged. Updated the steps for deploying bentos with `kubectl`.\r\n    - Users can create a BentoRequest CR and BentoDeployment CR to deploy a bento. In the BentoDeployment CR, the name of the bento should be defined as the name of the BentoRequest CR. If this Bento CR not found, `yatai-deployment` will look for the BentoRequest CR by the same name and wait for the BentoRequest CR to generate the Bento CR. Using this option requires both `yatai-image-builder` and `yatai-deployment` installed.\r\n    - Users can also manually create a Bento CR with the image field defined as the already-built OCI image URI. Then create a BentoDeployment CR to reference the Bento CR previously created. Using this option requires only `yatai-deployment` installed.\r\n\r\n![image](https:\u002F\u002Fuser-images.githubusercontent.com\u002F861225\u002F210843969-205a37fb-ade9-4e8e-b9c7-8be725181420.png)\r\n\r\n- Supported components to be installed in the custom namespaces.\r\n\r\n💡 We continue to update the documentation and examples on every release to help the community unlock the full power of Yatai.\r\n\r\n- Check out the updated installation guides of [yatai-image-buider](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Finstallation\u002Fyatai_image_builder.html) and [yatai-deployment](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Finstallation\u002Fyatai_deployment.html).\r\n- Learn from the latest [architecture](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Fconcepts\u002Farchitecture.html) and [terminology](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Fconcepts\u002Fterminology.html) documentation.\r\n- Learn how to leverage GPUs in the cluster and [deploy with GPU](https:\u002F\u002Fdocs.bentoml.org\u002Fprojects\u002Fyatai\u002Fen\u002Flatest\u002Fadvanced_guides\u002Fgpu_deployment.html) enabled.\r\n\r\n## What's Changed\r\n* feat: integration with yatai-image-builder by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F388\r\n* feat(docs): install yatai-image-builder-crds by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F424\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.0.12...v1.1.0","2023-01-05T13:34:03",{"id":247,"version":248,"summary_zh":249,"released_at":250},115630,"v1.0.12","## What's Changed\r\n* fix(lint): github action unable to locate package libenchant-dev by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F422\r\n* Update papercups key by @yubozhao in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F421\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.0.11...v1.0.12","2022-12-23T04:46:35",{"id":252,"version":253,"summary_zh":254,"released_at":255},115631,"v1.0.11","## What's Changed\r\n* feat: add detail logs by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F418\r\n* fix: image builder pod namespace by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F419\r\n* fix(api-server): no image builder pod been selected by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F420\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.0.10...v1.0.11","2022-12-22T11:59:55",{"id":257,"version":258,"summary_zh":259,"released_at":260},115632,"v1.0.10","## What's Changed\r\n* feat(helm-chart): add hpa by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F413\r\n* feat: support deployment strategy by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F414\r\n* optimize(api-server): db open once by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F415\r\n* feat(api-server): upgrade bento debugger image version and use zsh in bento debugger container by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F416\r\n* fix(api-server): send empty events by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F417\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.0.9...v1.0.10","2022-12-20T20:24:48",{"id":262,"version":263,"summary_zh":264,"released_at":265},115633,"v1.0.9","## What's Changed\r\n* feat(dashboard): terminal heartbeat by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F411\r\n* feat: debugger image configurable by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F412\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.0.8...v1.0.9","2022-12-20T09:14:16",{"id":267,"version":268,"summary_zh":269,"released_at":270},115634,"v1.0.8","## What's Changed\r\n* fix(api-server): remove duplicate kube events by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F408\r\n* feat: ephemeral debugger container by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F409\r\n* feat(api-server): add ptrace capability to debugger container by default by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F410\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.0.7...v1.0.8","2022-12-19T15:08:36",{"id":272,"version":273,"summary_zh":274,"released_at":275},115635,"v1.0.7","## What's Changed\r\n* fix(api-server): do not override autoscaling by @yetone in https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fpull\u002F407\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002Fbentoml\u002FYatai\u002Fcompare\u002Fv1.0.6...v1.0.7","2022-12-15T15:57:08"]