[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-samtecspg--articulate":3,"tool-samtecspg--articulate":64},[4,17,25,39,48,56],{"id":5,"name":6,"github_repo":7,"description_zh":8,"stars":9,"difficulty_score":10,"last_commit_at":11,"category_tags":12,"status":16},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",138956,2,"2026-04-05T11:33:21",[13,14,15],"开发框架","Agent","语言模型","ready",{"id":18,"name":19,"github_repo":20,"description_zh":21,"stars":22,"difficulty_score":10,"last_commit_at":23,"category_tags":24,"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",[13,15],{"id":26,"name":27,"github_repo":28,"description_zh":29,"stars":30,"difficulty_score":10,"last_commit_at":31,"category_tags":32,"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",[33,34,35,36,14,37,15,13,38],"图像","数据工具","视频","插件","其他","音频",{"id":40,"name":41,"github_repo":42,"description_zh":43,"stars":44,"difficulty_score":45,"last_commit_at":46,"category_tags":47,"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。",77062,3,"2026-04-04T04:44:48",[14,33,13,15,37],{"id":49,"name":50,"github_repo":51,"description_zh":52,"stars":53,"difficulty_score":45,"last_commit_at":54,"category_tags":55,"status":16},519,"PaddleOCR","PaddlePaddle\u002FPaddleOCR","PaddleOCR 是一款基于百度飞桨框架开发的高性能开源光学字符识别工具包。它的核心能力是将图片、PDF 等文档中的文字提取出来，转换成计算机可读取的结构化数据，让机器真正“看懂”图文内容。\n\n面对海量纸质或电子文档，PaddleOCR 解决了人工录入效率低、数字化成本高的问题。尤其在人工智能领域，它扮演着连接图像与大型语言模型（LLM）的桥梁角色，能将视觉信息直接转化为文本输入，助力智能问答、文档分析等应用场景落地。\n\nPaddleOCR 适合开发者、算法研究人员以及有文档自动化需求的普通用户。其技术优势十分明显：不仅支持全球 100 多种语言的识别，还能在 Windows、Linux、macOS 等多个系统上运行，并灵活适配 CPU、GPU、NPU 等各类硬件。作为一个轻量级且社区活跃的开源项目，PaddleOCR 既能满足快速集成的需求，也能支撑前沿的视觉语言研究，是处理文字识别任务的理想选择。",74913,"2026-04-05T10:44:17",[15,33,13,37],{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":45,"last_commit_at":62,"category_tags":63,"status":16},2181,"OpenHands","OpenHands\u002FOpenHands","OpenHands 是一个专注于 AI 驱动开发的开源平台，旨在让智能体（Agent）像人类开发者一样理解、编写和调试代码。它解决了传统编程中重复性劳动多、环境配置复杂以及人机协作效率低等痛点，通过自动化流程显著提升开发速度。\n\n无论是希望提升编码效率的软件工程师、探索智能体技术的研究人员，还是需要快速原型验证的技术团队，都能从中受益。OpenHands 提供了灵活多样的使用方式：既可以通过命令行（CLI）或本地图形界面在个人电脑上轻松上手，体验类似 Devin 的流畅交互；也能利用其强大的 Python SDK 自定义智能体逻辑，甚至在云端大规模部署上千个智能体并行工作。\n\n其核心技术亮点在于模块化的软件智能体 SDK，这不仅构成了平台的引擎，还支持高度可组合的开发模式。此外，OpenHands 在 SWE-bench 基准测试中取得了 77.6% 的优异成绩，证明了其解决真实世界软件工程问题的能力。平台还具备完善的企业级功能，支持与 Slack、Jira 等工具集成，并提供细粒度的权限管理，适合从个人开发者到大型企业的各类用户场景。",70612,"2026-04-05T11:12:22",[15,14,13,36],{"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":79,"owner_website":79,"owner_url":80,"languages":81,"stars":101,"forks":102,"last_commit_at":103,"license":104,"difficulty_score":45,"env_os":105,"env_gpu":105,"env_ram":105,"env_deps":106,"category_tags":113,"github_topics":114,"view_count":45,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":119,"updated_at":120,"faqs":121,"releases":151},707,"samtecspg\u002Farticulate","articulate","A platform for building conversational interfaces with intelligent agents (chatbots)","Articulate 是一款专为构建智能对话界面而设计的开源平台，核心目标是帮助用户轻松打造具备自然语言理解能力的聊天机器人。在开发过程中，许多团队常遇到对话逻辑复杂、意图识别不准等挑战，Articulate 正是为了解决这些痛点而生。\n\n技术上，它建立在 Rasa NLU 之上，内部融合了 Duckling、spaCy 和 TensorFlow 等主流组件。其独特亮点在于实现了自定义的对话管理方案，既支持深度复杂的对话流程，又兼顾了使用的简洁性，有效降低了开发门槛。\n\n这个项目非常适合全栈开发者、机器学习工程师以及关注企业数据规模应用的 UX 设计师。如果你正在寻找一个灵活且高效的框架来优化客户服务体验，或者希望探索智能代理在业务场景中的落地，Articulate 都是一个值得尝试的选择。它采用 Apache License 2.0 协议，完全开放，方便社区协作与二次开发。","![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsamtecspg_articulate_readme_0e6bfb1c3ef8.png)\n\n# Introducing Articulate\n## A platform for building conversational interfaces with intelligent agents\n\n[![Join the chat at https:\u002F\u002Fgitter.im\u002Fsamtecspg\u002Farticulate](https:\u002F\u002Fbadges.gitter.im\u002Fsamtecspg\u002Farticulate.svg)](https:\u002F\u002Fgitter.im\u002Fsamtecspg\u002Farticulate?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)\n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fsamtecspg\u002Farticulate.svg)\n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fsamtecspg\u002Farticulate\u002Ftotal.svg)\n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Ftag\u002Fsamtecspg\u002Farticulate.svg)\n\nArticulate is a platform for building conversational interfaces with intelligent agents. It is built primarily on top of Rasa NLU, which internally uses Duckling, spaCy, and tensorFlow. It implements a custom dialogue management solution capable of deep complex dialog, but with a focus on simplicity in use.\n\nIf you're ready to get started then jump straight to [basic installation](.\u002Fdocs\u002Fgetting-started\u002Fbasic-installation.md)\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsamtecspg_articulate_readme_32ff1c16ebe3.png)\n\n## The Team\n\n### Smart Platform Group\n\nSPG is a team of full stack developers, machine learning engineers, and UX designers working to solve the problem of Enterprise data at scale. We love Open Source and are pleased to be able to build open source projects along our journey.\n\n### Samtec, Inc.\n\nSamtec is our mothership. Nearly all members of the SPG team got started as engineers, developers, or business users inside of Samtec. Recognizing problems faced by Samtec, and likely by other enterprises of the same scale, SPG was created to address some of those needs. We are driven by our love for Samtec as a company and family to build products that improve the experiences and services of Samtec's customers.\n\n## License\n\nCopyright 2018 Samtec.\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at\n\n    http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License.\n\n","![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsamtecspg_articulate_readme_0e6bfb1c3ef8.png)\n\n# 介绍 Articulate\n## 一个用于构建智能体对话界面的平台\n\n[![Join the chat at https:\u002F\u002Fgitter.im\u002Fsamtecspg\u002Farticulate](https:\u002F\u002Fbadges.gitter.im\u002Fsamtecspg\u002Farticulate.svg)](https:\u002F\u002Fgitter.im\u002Fsamtecspg\u002Farticulate?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)\n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fsamtecspg\u002Farticulate.svg)\n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdownloads\u002Fsamtecspg\u002Farticulate\u002Ftotal.svg)\n![](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Ftag\u002Fsamtecspg\u002Farticulate.svg)\n\nArticulate 是一个用于构建智能体（intelligent agents）对话界面的平台。它主要基于 Rasa NLU（自然语言理解）构建，其内部使用了 Duckling、spaCy 和 tensorFlow（深度学习框架）。它实现了一个自定义的对话管理（dialogue management）解决方案，能够处理深度复杂的对话，但侧重于使用的简便性。\n\n如果您准备开始使用，请直接跳转到 [基本安装](.\u002Fdocs\u002Fgetting-started\u002Fbasic-installation.md)\n\n![](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsamtecspg_articulate_readme_32ff1c16ebe3.png)\n\n## 团队\n\n### 智能平台组 (Smart Platform Group)\n\nSPG 是一个由全栈开发人员（full stack developers）、机器学习工程师（machine learning engineers）和 UX（用户体验）设计师组成的团队，致力于解决企业级数据规模化的问题。我们热爱开源 (Open Source)，很高兴能在我们的旅程中构建开源项目。\n\n### Samtec, Inc.\n\nSamtec 是我们的母公司。SPG 团队的几乎所有成员最初都是在 Samtec 内部作为工程师、开发人员或业务用户起步的。认识到 Samtec 面临的问题，以及可能同样面临这些问题的大型企业，SPG 应运而生，旨在解决其中的一些需求。我们出于对 Samtec 这家公司和家庭的热爱，致力于构建能够提升 Samtec 客户体验和服务的产品。\n\n## 许可证\n\n版权所有 2018 Samtec。\n\n根据 Apache 许可证版本 2.0（“许可证”）授权；\n除非符合许可证要求，否则不得使用此文件。\n您可以在以下位置获取许可证副本：\n\n    http:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0\n\n除非适用法律要求或书面同意，否则软件\n在许可证下分发的软件是“按原样”提供的，\n没有任何形式的担保或条件，无论是明示的还是暗示的。\n请参阅许可证以了解管理权限的具体语言，以及\n许可证下的限制。","# Articulate 快速上手指南\n\n## 简介\nArticulate 是一个用于构建带有智能代理（Intelligent Agents）的对话界面的平台。它主要基于 Rasa NLU 构建，内部集成了 Duckling、spaCy 和 TensorFlow。该平台实现了自定义的对话管理解决方案，能够处理深度复杂对话，同时注重使用的简便性。\n\n## 环境准备\n根据项目技术栈，建议准备以下运行环境：\n- **操作系统**：支持 Linux \u002F macOS \u002F Windows\n- **开发语言**：Python（依赖 TensorFlow, spaCy 等库）\n- **核心组件**：\n  - Rasa NLU\n  - Duckling\n  - spaCy\n  - TensorFlow\n\n## 安装步骤\n1. **获取源代码**\n   从 GitHub 克隆项目仓库：\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Fsamtecspg\u002Farticulate.git\n   ```\n\n2. **执行安装**\n   具体的安装配置命令和依赖处理，请直接参考官方文档中的基础安装章节：\n   [basic installation](.\u002Fdocs\u002Fgetting-started\u002Fbasic-installation.md)\n\n## 基本使用\n启动并配置完成后，您可以开始构建智能对话代理。Articulate 专注于简化对话管理的使用流程，支持复杂的对话逻辑。具体的意图识别、实体提取及对话流设计，请参照安装目录下的详细文档进行操作。\n\n## 开源协议\nCopyright 2018 Samtec.\nLicensed under the Apache License, Version 2.0.","某大型制造企业的技术支持团队每天面临海量关于连接器规格的重复咨询，急需引入自动化解决方案来减轻人力负担。\n\n### 没有 articulate 时\n- 人工客服处理速度慢，高峰期客户排队等待时间常超过半小时。\n- 不同工程师对产品参数理解不一，导致回复内容经常发生冲突或错误。\n- 传统脚本只能匹配固定关键词，无法理解“兼容型号”等自然语义表达。\n- 每次新增产品知识都需要修改底层代码，上线周期长达数周，灵活性差。\n\n### 使用 articulate 后\n- articulate 基于 Rasa NLU 精准识别用户意图，实现全天候秒级自动应答。\n- 统一的知识库驱动对话流程，确保所有用户获取的产品信息完全一致。\n- 自定义对话管理支持多轮深度交互，轻松处理复杂的业务逻辑查询。\n- 低代码配置方式让运营人员直接更新话术，版本迭代效率提升十倍有余。\n\narticulate 通过简化智能对话构建流程，帮助企业以更低成本实现大规模客户服务自动化。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fsamtecspg_articulate_0e6bfb1c.png","samtecspg","Samtec Smart Platform Group Archive","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fsamtecspg_86bf0504.png","The SPG team is no more! Some of these projects will likely live on elsewhere, but no further updates will be happening here.",null,"https:\u002F\u002Fgithub.com\u002Fsamtecspg",[82,86,90,94,98],{"name":83,"color":84,"percentage":85},"JavaScript","#f1e05a",97.2,{"name":87,"color":88,"percentage":89},"CSS","#663399",1.9,{"name":91,"color":92,"percentage":93},"HTML","#e34c26",0.5,{"name":95,"color":96,"percentage":97},"Shell","#89e051",0.2,{"name":99,"color":100,"percentage":97},"Dockerfile","#384d54",593,156,"2026-04-02T08:36:11","Apache-2.0","未说明",{"notes":107,"python":105,"dependencies":108},"该工具基于 Rasa NLU 构建，内部依赖 Duckling、spaCy 和 TensorFlow。具体的运行环境配置（如操作系统、Python 版本、GPU 需求等）未在提供的 README 片段中明确列出，建议查看链接中的 basic-installation 文档获取详细安装指南。",[109,110,111,112],"Rasa NLU","Duckling","spaCy","tensorFlow",[15],[115,116,117,118],"nlu","nlp","chatbot","react","2026-03-27T02:49:30.150509","2026-04-06T05:35:38.146078",[122,127,132,137,142,147],{"id":123,"question_zh":124,"answer_zh":125,"source_url":126},2970,"Webhook 在槽位填充时被调用两次且收到双重响应怎么办？","这通常是环境配置问题。请确保拉取最新代码并清理 Docker 环境。执行以下命令：\n1. docker-compose down\n2. docker-compose pull\n3. docker-compose up -d\n确保已清理所有旧的 Docker 配置并使用最新版本。","https:\u002F\u002Fgithub.com\u002Fsamtecspg\u002Farticulate\u002Fissues\u002F967",{"id":128,"question_zh":129,"answer_zh":130,"source_url":131},2971,"新 UI 中训练过程时间过长且不自动停止是否正常？","这是正常现象，需要等待训练完成。标准操作流程为：将 Agent 保存为 JSON 文件 -> 在 UI 中点击 Import -> 加载文件 -> 进入 Agent -> 点击 Train -> 等待训练结束。关于磁盘空间，建议预留更多余量（3GB 可能偏紧）。","https:\u002F\u002Fgithub.com\u002Fsamtecspg\u002Farticulate\u002Fissues\u002F536",{"id":133,"question_zh":134,"answer_zh":135,"source_url":136},2972,"遇到 'calling Articulate's converse service' 错误该如何排查？","该错误可能与删除 Agent 的操作有关。建议捕获错误发生时的终端日志或视频以便进一步分析。如果是更新后出现的问题，可以尝试从开发环境导出 Agent 并在生产环境导入测试。","https:\u002F\u002Fgithub.com\u002Fsamtecspg\u002Farticulate\u002Fissues\u002F1013",{"id":138,"question_zh":139,"answer_zh":140,"source_url":141},2973,"启动后出现 'agent head missing' 或无法连接 API 如何解决？","请检查 API 端口配置是否正确。参考官方文档中的配置说明进行验证。如果是在本地运行，请确保遵循详细的安装文档，而不仅仅是阅读 README，因为文档链接可能会有所更新。","https:\u002F\u002Fgithub.com\u002Fsamtecspg\u002Farticulate\u002Fissues\u002F281",{"id":143,"question_zh":144,"answer_zh":145,"source_url":146},2974,"为什么高并发下 Articulate 会出现会话崩溃或无法终止？","Rasa 是系统的瓶颈。当并发请求过多时，单实例 Rasa 无法处理会导致崩溃。建议不要依赖单一 Rasa 实例处理大量用户，并关注会话清理机制的实现情况。","https:\u002F\u002Fgithub.com\u002Fsamtecspg\u002Farticulate\u002Fissues\u002F998",{"id":148,"question_zh":149,"answer_zh":150,"source_url":146},2975,"如何配置 Rasa 并发数以提升 Articulate 的稳定性？","应将并发 Rasa 请求数设置为等于分配给 Rasa 的 CPU 核心数。例如，如果有 8 核 CPU 专门用于 Rasa，建议将并发设置调整为 8。也可以考虑使用 Master 分支上的多 Rasa 实例功能来扩展服务。",[152,157,162,167,172,177,182,187,192,197,202,207,212,217,222,227,232,237,242,247],{"id":153,"version":154,"summary_zh":155,"released_at":156},102484,"v0.22.0","#### ADDED\r\n- Agent icons and colors\r\n- validation to avoid empty training sets\r\n- UI internationalization (Spanish, let us know if want to help add more languages)\r\n- reverse proxy built into UI server\r\n- help videos for most pages\r\n- auto-highlight of keywords based on keyword value list\r\n- ability to clone responses\r\n- can edit responses in place\r\n\r\n#### CHANGED\r\n- Upgraded to Rasa 0.14.4\r\n- slots can now use the same entities multiple times\r\n- changed API Dockerfile to use LTS base image\r\n- category select for review page when using multi-actions\r\n- material icon package to reduce size\r\n- actions are now sorted by name in dropdowns\r\n- updated lodash\r\n- migrated UI backend to Api from Express\r\n- sayings categories can now be changed\r\n- moved saying and keyword to dialogue tab on main interface\r\n\r\n#### FIXED\r\n - webhook response bug resulting in \"a converse error has occurred\"\r\n - regex keyword bug\r\n - chained actions not being added to the queue\r\n - Many more...\r\n\r\n","2019-04-17T20:50:56",{"id":158,"version":159,"summary_zh":160,"released_at":161},102485,"v0.21.2","#### FIXED\r\n- Chained action slot filling","2019-03-06T11:47:20",{"id":163,"version":164,"summary_zh":165,"released_at":166},102486,"v0.21.1","#### FIXED\r\n- Multi Actions with prompts\r\n- Fallback and out of vocabulary words","2019-02-27T02:49:18",{"id":168,"version":169,"summary_zh":170,"released_at":171},102487,"v0.21.0","#### ADDED\r\n- Internationalization support\r\n- API location auto-discovery\r\n- Review page is now live\r\n- Auto highlighting of keywords under certain conditions\r\n- new entity color randomization\r\n\r\n#### CHANGED\r\n- Swagger configuration\r\n- Upgrade compose to 3.0\r\n- Changed from health checks to Dockerize\r\n- Cleaned up the compose file\r\n- notification dot is now blue, error dot is red\r\n- notifications timeout after 10s, errors do not\r\n- Webhook errors are now returned to articulate for handling\r\n\r\n#### FIXED\r\n- Allow refreshing pages through Articulate\r\n- multi model generation on TF pipeline\r\n- plain text responses from Webhook are now placed in `webhookResponse.text`\r\n- recursive action chaining\r\n- Frame generation with multi actions and action chaining\r\n\r\n\r\n","2019-02-19T13:43:58",{"id":173,"version":174,"summary_zh":175,"released_at":176},102488,"v0.20.3","A few warnings about this release:\r\n - This release represents a complete overhaul of the Articulate UI and API.\r\n - This project is under active and heavy development. APIs and Interfaces are very likely to change.\r\n - Docs are non-existent for this release, but we are working to get them in place.\r\n\r\n#### FIXED\r\n- Plain text webhook responses are now placed in `webhookResponse.text`\r\n","2019-02-08T16:36:33",{"id":178,"version":179,"summary_zh":180,"released_at":181},102489,"v0.20.2","A few warnings about this release:\r\n - This release represents a complete overhaul of the Articulate UI and API.\r\n - This project is under active and heavy development. APIs and Interfaces are very likely to change.\r\n - Docs are non-existent for this release, but we are working to get them in place.\r\n\r\n#### ADDED\r\n- **LOTS**\r\n- Multi-Actions which allow for sayings like `Hey, can I get a pizza` to be tagged with multiple actions\r\n- Action chains which allow the fulfillment of one action to start the fulfillment of subsequent actions\r\n- Modifiers which are built to handle slot prompt responses and more slot value manipulation\r\n- Review page for reviewing how users are chatting with your agent and adding their utterance to training\r\n- Webhook headers to enable basic auth and more\r\n\r\n#### CHANGED\r\n- **EVERYTHING**\r\n- Verbiage - intents are now called actions\r\n- Verbiage - entities are now called keywords\r\n- Verbiage - domains are now called categories\r\n- Rasa training pipeline now defaults to TensorFlow\r\n- Fast-forward Rasa NLU version (0.14.1)\r\n\r\n#### FIXED\r\n- we probably broke more than we fixed, but there's a lot of new good stuff.\r\n","2019-02-07T13:27:55",{"id":183,"version":184,"summary_zh":185,"released_at":186},102490,"v0.13.0","#### ADDED\r\n- structured text parseing for debug\u002Fsocial platform buttons. `\u002ForderPizza@0.35{\"entity\": \"value\"}`\r\n- sessionId to ubqiuity object for Twilio\r\n\r\n#### CHANGED\r\n- PUT context require slots to have one child\r\n- Fastforward Rasa NLU version\r\n\r\n#### FIXED\r\n- entitiesCombination not found when generating extra training data for single domains\r\n- Auto highlight of Duckling entity values\r\n- typos\r\n\r\n## Documentation\r\nFor additional information or help getting started head over to our [documentation](https:\u002F\u002Fsamtecspg.github.io\u002Farticulate\u002F). ","2018-10-13T23:16:22",{"id":188,"version":189,"summary_zh":190,"released_at":191},102491,"v0.12.3","### ADDED\r\n- numeral.js handlebar helpers. It can be used to format numbers using `{{numeral webhookResponse.value '0a'}}` as the format. For more information on the format specification see the numeral.js website.\r\n- basic authentication into the webhooks. This isn't exposed in the UI yet, but can be set in the API.\r\n\r\n## Documentation\r\nFor additional information or help getting started head over to our [documentation](https:\u002F\u002Fsamtecspg.github.io\u002Farticulate\u002F). ","2018-09-19T12:26:38",{"id":193,"version":194,"summary_zh":195,"released_at":196},102492,"v0.12.1","### Fixed\r\n- entitiesCombination not found when generating extra training data\r\n\r\n\r\n## Documentation\r\nFor additional information or help getting started head over to our [documentation](https:\u002F\u002Fsamtecspg.github.io\u002Farticulate\u002F). ","2018-09-12T12:22:56",{"id":198,"version":199,"summary_zh":200,"released_at":201},102493,"v0.12.0","### Changed\r\n- Updated to Rasa 0.13.1\r\n- Slowed Agent status polling\r\n- UI updates status in a few places\r\n- Simple UI color changes to indicate sample sayings and responses\r\n- Add `isActionComplete: false` when slot filling\r\n\r\n\r\n## Documentation\r\nFor additional information or help getting started head over to our [documentation](https:\u002F\u002Fsamtecspg.github.io\u002Farticulate\u002F). ","2018-09-11T02:40:48",{"id":203,"version":204,"summary_zh":205,"released_at":206},102474,"v1.0.0","Official 1.0 Release of Articulate. For a complete commit log of changes see [here](https:\u002F\u002Fgithub.com\u002Fsamtecspg\u002Farticulate\u002Fcompare\u002F0.31...1.0).\r\n\r\n## Added (high level):\r\n - Authentication (group based)\r\n - Cheat Sheet\r\n - Mutliple Rasa Instances\r\n - Slack Logging\r\n - Automatic Replies\r\n - Agent Versioning\r\n - Testing\r\n - Pre-Scripts","2020-06-01T23:12:27",{"id":208,"version":209,"summary_zh":210,"released_at":211},102475,"v0.31.1","#### FIXED\r\n - Fixed Accidental change to package version for Bell\r\n","2020-01-14T01:58:35",{"id":213,"version":214,"summary_zh":215,"released_at":216},102476,"v0.31.0","#### ADDED\r\n- Postscripts - execute code during action fulfillment\r\n- Free text slots - use carefully!!!\r\n- Log viewer in the UI\r\n- Added filter to sayings page\r\n- Support for welcome messages\r\n- Action responses now support different response types:\r\n  - Images\r\n  - Audio\r\n  - Cards\r\n  - Accordion\r\n  - Buttons\r\n  - Quick Responses\r\n  - Video\r\n\r\n#### CHANGED\r\n- Modified GitHub category to take advantage of newer features\r\n- Modified Weather category to take advantage of newer features\r\n- Modified Small Talk category to take advantage of newer features\r\n- Chat Widget code is now hosted on a CDN rather than Google Storage\r\n- Added back in keyword dialogue flow\r\n\r\n#### FIXED\r\n - Too many to type here, best just read the commits\r\n","2020-01-12T05:15:09",{"id":218,"version":219,"summary_zh":220,"released_at":221},102477,"v0.29.0","#### ADDED\r\n- Mattermost Connector\r\n- Copy prompt button\r\n- Prompt counts\r\n- Time selection for analytics\r\n- Side scroll indicators on main page\r\n- User List Screen\r\n\r\n#### CHANGED\r\n- Text prompts can be edited in line\r\n- Disabled fake pre-built categories\r\n\r\n#### FIXED\r\n - Too many to type here, best just read the commits\r\n","2019-08-29T02:23:29",{"id":223,"version":224,"summary_zh":225,"released_at":226},102478,"v0.28.2","#### CHANGED\r\n- Docker and script changes for cloud deployment","2019-08-20T19:47:38",{"id":228,"version":229,"summary_zh":230,"released_at":231},102479,"v0.28.1","#### ADDED\r\n- Added button\u002Fquick responses\r\n- Added back in keyword flow\r\n- Added Prompt copy button\r\n\r\n#### CHANGED\r\n- Conversation panel now uses web sockets\r\n- Quite a few Docker and compose changes\r\n- Slot prompts can now be edited inline responses\r\n- Removed empty pre-built categories\r\n\r\n#### FIXED\r\n - Too many to type here, best just read the commits\r\n","2019-08-20T01:59:19",{"id":233,"version":234,"summary_zh":235,"released_at":236},102480,"v0.27.2","#### CHANGED\r\n- Deployment Options for SSL and Basic Auth","2019-07-26T14:38:46",{"id":238,"version":239,"summary_zh":240,"released_at":241},102481,"v0.27.1","#### ADDED\r\n- SSL Init Script - docs to follow\r\n\r\n#### CHANGED\r\n- Moved ports to `docker-compose.override.yml`\r\n- Moved all compose override to compose folder\r\n\r\n#### FIXED\r\n - Too many to type here, best just read the commits\r\n","2019-07-22T19:30:29",{"id":243,"version":244,"summary_zh":245,"released_at":246},102482,"v0.27.0","#### ADDED\r\n- Basic Analytics - request, session, and fallback counts. Top Actions and request over time\r\n- Multiple messages - on platforms that support it messages will be split rather than concatenated\r\n- Session tab on review page - use to load session in the internal chat panel\r\n- Chat widget for embedding on your own site (https:\u002F\u002Fgithub.com\u002Fsamtecspg\u002Farticulate-webchat)\r\n- French and Portugese UI Translations (thanks @mordebip)\r\n\r\n\r\n#### CHANGED\r\n- Changed default pipeline for better emoji support\r\n- Webhook no longer requires toggle, keys off url\r\n- Improved dropdown menu for actions\r\n- Checkboxes instead of numbers for slot lifespans\r\n- Improved Channel grid\r\n- A lot of converse code 😱 let us know if something that used to work doesn't.\r\n\r\n#### FIXED\r\n - Too many to type here, best just read the commits\r\n\r\n#### BUGS\r\n - Loading sessions from review tab duplicates in chat panel\r\n - Error when replying with modifier for wrong slot\r\n - Conversation stalls when replying with a modifier after action is fulfilled\r\n - Duplicating actions is broken\r\n","2019-07-18T19:23:19",{"id":248,"version":249,"summary_zh":250,"released_at":251},102483,"v0.25.0","#### ADDED\r\n- Channels and Connections - together allow easy integration with social platforms like Facebook, Twilio, etc\r\n- Shared Chat Panel - allows you to share your agent easily for testing\r\n- Pre-Built Categories - quickly add functionality to your agent with pre-built categories\r\n- Added back numeral and moment handlebar helpers\r\n- Scaffolding for auth (coming soon)\r\n\r\n\r\n#### CHANGED\r\n- Changed web hook structure, what used to be `webhookResponse` is now `webhook.response`\r\n- Allow Conversation panel to be resized and docked back to default size.\r\n- Internal Chat panel can now recall full sessions\r\n- Train button now is animated when training\r\n- Restricted the UI to one training session at a time for better multi-user support\r\n- API root now returns useful information instead of 404\r\n- Can now create chained actions from inside action page\r\n\r\n\r\n#### FIXED\r\n - Too many to type here, best just read the commits\r\n","2019-06-18T02:15:21"]