[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-lumina-ai-inc--chunkr":3,"tool-lumina-ai-inc--chunkr":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":116,"forks":117,"last_commit_at":118,"license":119,"difficulty_score":10,"env_os":120,"env_gpu":121,"env_ram":122,"env_deps":123,"category_tags":126,"github_topics":79,"view_count":127,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":128,"updated_at":129,"faqs":130,"releases":160},530,"lumina-ai-inc\u002Fchunkr","chunkr","Vision infrastructure to turn complex documents into RAG\u002FLLM-ready data","Chunkr 是一款面向大模型应用的开源文档智能基础设施，致力于将复杂的 PDF、PPT、Word 及图片转化为 RAG（检索增强生成）就绪的结构化数据。面对非结构化文档难以被 AI 直接理解的痛点，Chunkr 通过先进的布局分析、高精度 OCR 以及语义分块技术，自动提取文本内容并保留原始排版信息，输出为整洁的 HTML 或 Markdown 格式。Chunkr 特别适合正在构建企业级知识库、开发 RAG 系统的开发者，以及希望进行本地化部署的研究人员。开源版本基于社区模型，允许用户完全掌控数据隐私与处理流程；而云端 API 则提供专有模型以追求更高的准确率与速度。其独特优势在于支持视觉语言模型处理，并能精准识别文档中的边界框，确保表格、图表等复杂元素不被误读。无论是快速验证想法还是投入生产环境，Chunkr 都能提供灵活可靠的解决方案，帮助团队高效打通从文档到智能问答的数据链路。","\u003Cbr \u002F>\n\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\">\n    \u003Cimg src=\"images\u002Flogo.svg\" alt=\"Chunkr Logo\" width=\"80\" height=\"80\">\n  \u003C\u002Fa>\n\n\u003Ch3 align=\"center\">Chunkr | Open Source Document Intelligence API\u003C\u002Fh3>\n\n  \u003Cp align=\"center\">\n    Production-ready service for document layout analysis, OCR, and semantic chunking.\u003Cbr \u002F>\n    Convert PDFs, PPTs, Word docs & images into RAG\u002FLLM-ready chunks.\n    \u003Cbr \u002F>\u003Cbr \u002F>\n    \u003Cb>Layout Analysis\u003C\u002Fb> | \u003Cb>OCR + Bounding Boxes\u003C\u002Fb> | \u003Cb>Structured HTML & Markdown\u003C\u002Fb> | \u003Cb>Vision-Language Model Processing\u003C\u002Fb>\n    \u003Cbr \u002F>\u003Cbr \u002F>\n    👉 \u003Cb>Note:\u003C\u002Fb> The \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\">open-source AGPL version\u003C\u002Fa> is **different** from our fully managed \u003Ca href=\"https:\u002F\u002Fwww.chunkr.ai\">Cloud API\u003C\u002Fa>.  \n    The open-source release uses community\u002Fopen-source models, while the Cloud API runs **proprietary in-house models** for higher accuracy, speed, and enterprise reliability.\n    \u003Cbr \u002F>\u003Cbr \u002F>\n    \u003Ca href=\"https:\u002F\u002Fwww.chunkr.ai\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTry_it_out-chunkr.ai-blue?style=flat&logo=rocket&height=20\" alt=\"Try it out\" height=\"20\">\u003C\u002Fa>\n       \n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002Fnew\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FReport_Bug-GitHub_Issues-red?style=flat&logo=github&height=20\" alt=\"Report Bug\" height=\"20\">\u003C\u002Fa>\n       \n    \u003Ca href=\"#connect-with-us\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FContact-Get_in_Touch-green?style=flat&logo=mail&height=20\" alt=\"Contact\" height=\"20\">\u003C\u002Fa>\n       \n    \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FXzKWFByKzW\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join_Community-5865F2?style=flat&logo=discord&logoColor=white&height=20\" alt=\"Discord\" height=\"20\">\u003C\u002Fa>\n       \n    \u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Flumina-ai-inc\u002Fchunkr\">\u003Cimg src=\"https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg\" alt=\"Ask DeepWiki\">\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.chunkr.ai\" width=\"1200\" height=\"630\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flumina-ai-inc_chunkr_readme_cf09f078d44a.png\" alt=\"Chunkr Cloud API\">\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n## Table of Contents\n- [Table of Contents](#table-of-contents)\n- [(Super) Quick Start](#super-quick-start)\n- [Documentation](#documentation)\n- [Open Source vs Cloud API vs Enterprise](#open-source-vs-cloud-api-vs-enterprise)\n- [Quick Start with Docker Compose](#quick-start-with-docker-compose)\n- [LLM Configuration](#llm-configuration)\n  - [Using models.yaml (Recommended)](#using-modelsyaml-recommended)\n  - [Using environment variables (Basic)](#using-environment-variables-basic)\n  - [Common LLM API Providers](#common-llm-api-providers)\n- [Licensing](#licensing)\n- [Connect With Us](#connect-with-us)\n\n## Open Source vs Cloud API vs Enterprise\n\n| Feature | Open Source Repo (good) | Cloud API - chunkr.ai (best) | Enterprise |\n|---------|--------------------|------------------------|------------|\n| **Perfect for** | Development & testing | Production workloads | Large-scale \u002F High-security |\n| **Layout Analysis** | Uses open-source models | Proprietary in-house models | In-house + custom-tuned |\n| **OCR Accuracy** | Community OCR engines | Optimized OCR stack | Optimized + domain-tuned |\n| **VLM Processing** | Basic open VLMs | Enhanced proprietary VLMs | Custom fine-tunes |\n| **Excel Support** | ❌ | ✅ Native parser | ✅ Native parser |\n| **Document Types** | PDF, PPT, Word, Images | PDF, PPT, Word, Images, Excel | PDF, PPT, Word, Images, Excel |\n| **Infrastructure** | Self-hosted | Fully managed cloud | Managed \u002F On-prem |\n| **Support** | Discord community | Dedicated support | Dedicated founding team |\n| **Migration Support** | Community-driven | Docs + email | Dedicated migration team |\n\n---\n\nThe **open-source release** is ideal if you want transparency, local hosting, or to experiment with Chunkr’s pipeline.  \nFor **best performance, production reliability, and access to in-house models**, we recommend the \u003Ca href=\"https:\u002F\u002Fwww.chunkr.ai\">Chunkr Cloud API\u003C\u002Fa>.  \nFor **high-security or regulated industries**, our **Enterprise edition** offers on-prem or VPC deployments.\n\n\n## Quick Start with Docker Compose\n\n1. Prerequisites:\n   - [Docker and Docker Compose](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F)\n   - [NVIDIA Container Toolkit](https:\u002F\u002Fdocs.nvidia.com\u002Fdatacenter\u002Fcloud-native\u002Fcontainer-toolkit\u002Finstall-guide.html) (for GPU support, optional)\n\n2. Clone the repo:\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\ncd chunkr\n```\n\n3. Set up environment variables:\n```bash\n# Copy the example environment file\ncp .env.example .env\n\n# Configure your llm models\ncp models.example.yaml models.yaml\n```\n\nFor more information on how to set up LLMs, see [here](#llm-configuration).\n\n4. Start the services:\n```bash\n# For GPU deployment:\ndocker compose up -d\n\n# For CPU-only deployment:\ndocker compose -f compose.yaml -f compose.cpu.yaml up -d\n\n# For Mac ARM architecture (M1, M2, M3, etc.):\ndocker compose -f compose.yaml -f compose.cpu.yaml -f compose.mac.yaml up -d\n```\n\n5. Access the services:\n   - Web UI: `http:\u002F\u002Flocalhost:5173`\n   - API: `http:\u002F\u002Flocalhost:8000`\n\n6. Stop the services when done:\n```bash\n# For GPU deployment:\ndocker compose down\n\n# For CPU-only deployment:\ndocker compose -f compose.yaml -f compose.cpu.yaml down\n\n# For Mac ARM architecture (M1, M2, M3, etc.):\ndocker compose -f compose.yaml -f compose.cpu.yaml -f compose.mac.yaml down\n```\n## LLM Configuration\n\nChunkr supports two ways to configure LLMs:\n\n1. **models.yaml file**: Advanced configuration for multiple LLMs with additional options\n2. **Environment variables**: Simple configuration for a single LLM\n\n### Using models.yaml (Recommended)\n\nFor more flexible configuration with multiple models, default\u002Ffallback options, and rate limits:\n\n1. Copy the example file to create your configuration:\n```bash\ncp models.example.yaml models.yaml\n```\n\n2. Edit the models.yaml file with your configuration. Example:\n```yaml\nmodels:\n  - id: gpt-4o\n    model: gpt-4o\n    provider_url: https:\u002F\u002Fapi.openai.com\u002Fv1\u002Fchat\u002Fcompletions\n    api_key: \"your_openai_api_key_here\"\n    default: true\n    rate-limit: 200 # requests per minute - optional\n```\n\nBenefits of using models.yaml:\n- Configure multiple LLM providers simultaneously\n- Set default and fallback models\n- Add distributed rate limits per model\n- Reference models by ID in API requests (see docs for more info)\n\n>Read the `models.example.yaml` file for more information on the available options.\n\n### Using environment variables (Basic)\n\nYou can use any OpenAI API compatible endpoint by setting the following variables in your .env file:\n``` \nLLM__KEY:\nLLM__MODEL:\nLLM__URL:\n```\n\n### Common LLM API Providers\n\nBelow is a table of common LLM providers and their configuration details to get you started:\n\n| Provider         | API URL                                                                  | Documentation                                                                                                                          |\n| ---------------- | ------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------- |\n| OpenAI           | https:\u002F\u002Fapi.openai.com\u002Fv1\u002Fchat\u002Fcompletions                               | [OpenAI Docs](https:\u002F\u002Fplatform.openai.com\u002Fdocs)                                                                                        |\n| Google AI Studio | https:\u002F\u002Fgenerativelanguage.googleapis.com\u002Fv1beta\u002Fopenai\u002Fchat\u002Fcompletions | [Google AI Docs](https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Fopenai)                                                                         |\n| OpenRouter       | https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fchat\u002Fcompletions                            | [OpenRouter Models](https:\u002F\u002Fopenrouter.ai\u002Fmodels)                                                                                      |\n| Self-Hosted      | http:\u002F\u002Flocalhost:8000\u002Fv1                                                 | [VLLM](https:\u002F\u002Fdocs.vllm.ai\u002Fen\u002Flatest\u002Fserving\u002Fopenai_compatible_server.html) or [Ollama](https:\u002F\u002Follama.com\u002Fblog\u002Fopenai-compatibility) |\n\n## Licensing\n\nThe core of this project is dual-licensed:\n\n1. [GNU Affero General Public License v3.0 (AGPL-3.0)](LICENSE)\n2. Commercial License\n\nTo use Chunkr without complying with the AGPL-3.0 license terms you can [contact us](mailto:mehul@chunkr.ai) or visit our [website](https:\u002F\u002Fchunkr.ai).\n\n## Connect With Us\n- 📧 Email: [mehul@chunkr.ai](mailto:mehul@chunkr.ai)\n- 📅 Schedule a call: [Book a 30-minute meeting](https:\u002F\u002Fcal.com\u002Fmehulc\u002F30min)\n- 🌐 Visit our website: [chunkr.ai](https:\u002F\u002Fchunkr.ai)\n","\u003Cbr \u002F>\n\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\">\n    \u003Cimg src=\"images\u002Flogo.svg\" alt=\"Chunkr Logo\" width=\"80\" height=\"80\">\n  \u003C\u002Fa>\n\n\u003Ch3 align=\"center\">Chunkr | 开源文档智能 API\u003C\u002Fh3>\n\n  \u003Cp align=\"center\">\n    面向文档布局分析、OCR (光学字符识别) 和语义分块的生产就绪服务。\u003Cbr \u002F>\n    将 PDF、PPT、Word 文档及图片转换为适用于 RAG (检索增强生成)\u002FLLM (大语言模型) 的分块内容。\n    \u003Cbr \u002F>\u003Cbr \u002F>\n    \u003Cb>布局分析\u003C\u002Fb> | \u003Cb>OCR + 边界框\u003C\u002Fb> | \u003Cb>结构化 HTML & Markdown\u003C\u002Fb> | \u003Cb>视觉 - 语言模型 (VLM) 处理\u003C\u002Fb>\n    \u003Cbr \u002F>\u003Cbr \u002F>\n    👉 \u003Cb>注意：\u003C\u002Fb> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\">开源 AGPL 版本\u003C\u002Fa> 与我们完全托管的 \u003Ca href=\"https:\u002F\u002Fwww.chunkr.ai\">云 API\u003C\u002Fa> **不同**。  \n    开源版本使用社区\u002F开源模型，而云 API 运行**专有内部模型**，以提供更高的准确性、速度和可靠性。\n    \u003Cbr \u002F>\u003Cbr \u002F>\n    \u003Ca href=\"https:\u002F\u002Fwww.chunkr.ai\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTry_it_out-chunkr.ai-blue?style=flat&logo=rocket&height=20\" alt=\"立即体验\" height=\"20\">\u003C\u002Fa>\n       \n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002Fnew\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FReport_Bug-GitHub_Issues-red?style=flat&logo=github&height=20\" alt=\"报告问题\" height=\"20\">\u003C\u002Fa>\n       \n    \u003Ca href=\"#connect-with-us\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FContact-Get_in_Touch-green?style=flat&logo=mail&height=20\" alt=\"联系我们\" height=\"20\">\u003C\u002Fa>\n       \n    \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FXzKWFByKzW\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join_Community-5865F2?style=flat&logo=discord&logoColor=white&height=20\" alt=\"Discord\" height=\"20\">\u003C\u002Fa>\n       \n    \u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Flumina-ai-inc\u002Fchunkr\">\u003Cimg src=\"https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg\" alt=\"询问 DeepWiki\">\u003C\u002Fa>\n  \u003C\u002Fp>\n\u003C\u002Fdiv>\n\n\u003Cdiv align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fwww.chunkr.ai\" width=\"1200\" height=\"630\">\n    \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flumina-ai-inc_chunkr_readme_cf09f078d44a.png\" alt=\"Chunkr 云 API\">\n  \u003C\u002Fa>\n\u003C\u002Fdiv>\n\n## 目录\n- [目录](#table-of-contents)\n- [(超级) 快速开始](#super-quick-start)\n- [文档](#documentation)\n- [开源版 vs 云 API vs 企业版](#open-source-vs-cloud-api-vs-enterprise)\n- [使用 Docker Compose 快速开始](#quick-start-with-docker-compose)\n- [LLM (大语言模型) 配置](#llm-configuration)\n  - [使用 models.yaml（推荐）](#using-modelsyaml-recommended)\n  - [使用环境变量（基础）](#using-environment-variables-basic)\n  - [常见 LLM API 提供商](#common-llm-api-providers)\n- [许可协议](#licensing)\n- [联系我们](#connect-with-us)\n\n## 开源版 vs 云 API vs 企业版\n\n| 功能 | 开源仓库（适合开发） | 云 API - chunkr.ai（最佳） | 企业版 |\n|---------|--------------------|------------------------|------------|\n| **适用场景** | 开发与测试 | 生产工作负载 | 大规模 \u002F 高安全性 |\n| **布局分析** | 使用开源模型 | 专有内部模型 | 内部 + 定制微调 |\n| **OCR 准确率** | 社区 OCR 引擎 | 优化的 OCR 栈 | 优化 + 领域微调 |\n| **VLM 处理** | 基础开源 VLM | 增强的专有 VLM | 自定义微调 |\n| **Excel 支持** | ❌ | ✅ 原生解析器 | ✅ 原生解析器 |\n| **文档类型** | PDF, PPT, Word, 图片 | PDF, PPT, Word, 图片, Excel | PDF, PPT, Word, 图片, Excel |\n| **基础设施** | 自托管 | 全托管云 | 托管 \u002F 本地部署 |\n| **支持** | Discord 社区 | 专属支持 | 专属创始团队 |\n| **迁移支持** | 社区驱动 | 文档 + 邮件 | 专属迁移团队 |\n\n---\n\n如果您希望透明化、本地托管或尝试 Chunkr 的流程，**开源版本**是理想选择。  \n对于**最佳性能、生产可靠性和访问内部模型**，我们推荐 \u003Ca href=\"https:\u002F\u002Fwww.chunkr.ai\">Chunkr 云 API\u003C\u002Fa>。  \n对于**高安全性或受监管行业**，我们的**企业版**提供本地部署或 VPC 部署。\n\n\n## 使用 Docker Compose 快速开始\n\n1. 前置条件：\n   - [Docker 和 Docker Compose](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F)\n   - [NVIDIA 容器工具包](https:\u002F\u002Fdocs.nvidia.com\u002Fdatacenter\u002Fcloud-native\u002Fcontainer-toolkit\u002Finstall-guide.html)（用于 GPU 支持，可选）\n\n2. 克隆仓库：\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\ncd chunkr\n```\n\n3. 设置环境变量：\n```bash\n# 复制示例环境文件\ncp .env.example .env\n\n# 配置您的 llm 模型\ncp models.example.yaml models.yaml\n```\n\n有关如何设置 LLM 的更多信息，请参见 [此处](#llm-configuration)。\n\n4. 启动服务：\n```bash\n# 用于 GPU 部署：\ndocker compose up -d\n\n# 仅用于 CPU 部署：\ndocker compose -f compose.yaml -f compose.cpu.yaml up -d\n\n# 用于 Mac ARM 架构（M1, M2, M3 等）：\ndocker compose -f compose.yaml -f compose.cpu.yaml -f compose.mac.yaml up -d\n```\n\n5. 访问服务：\n   - Web UI: `http:\u002F\u002Flocalhost:5173`\n   - API: `http:\u002F\u002Flocalhost:8000`\n\n6. 完成后停止服务：\n```bash\n# 用于 GPU 部署：\ndocker compose down\n\n# 仅用于 CPU 部署：\ndocker compose -f compose.yaml -f compose.cpu.yaml down\n\n# 用于 Mac ARM 架构（M1, M2, M3 等）：\ndocker compose -f compose.yaml -f compose.cpu.yaml -f compose.mac.yaml down\n```\n## LLM 配置\n\nChunkr 支持两种配置 LLM 的方式：\n\n1. **models.yaml 文件**：针对多个 LLM 的高级配置，包含额外选项\n2. **环境变量**：单个 LLM 的简单配置\n\n### 使用 models.yaml（推荐）\n\n对于更灵活的配置，包括多个模型、默认\u002F回退选项和速率限制：\n\n1. 复制示例文件以创建您的配置：\n```bash\ncp models.example.yaml models.yaml\n```\n\n2. 使用您的配置编辑 models.yaml 文件。示例：\n```yaml\nmodels:\n  - id: gpt-4o\n    model: gpt-4o\n    provider_url: https:\u002F\u002Fapi.openai.com\u002Fv1\u002Fchat\u002Fcompletions\n    api_key: \"your_openai_api_key_here\"\n    default: true\n    rate-limit: 200 # requests per minute - optional\n```\n\n使用 models.yaml 的好处：\n- 同时配置多个 LLM 提供商\n- 设置默认和回退模型\n- 为每个模型添加分布式速率限制\n- 在 API 请求中通过 ID 引用模型（详见文档）\n\n>阅读 `models.example.yaml` 文件以了解可用选项的更多信息。\n\n### 使用环境变量（基础）\n\n您可以通过在 `.env` 文件中设置以下变量来使用任何兼容 OpenAI API 的端点：\n``` \nLLM__KEY:\nLLM__MODEL:\nLLM__URL:\n```\n\n### 常见大语言模型 (LLM) API 提供商\n\n以下是常见的 LLM 提供商及其配置详情的表格，助您快速开始：\n\n| 提供商         | API URL                                                                  | 文档                                                                                                                           |\n| ---------------- | ------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------ |\n| OpenAI           | https:\u002F\u002Fapi.openai.com\u002Fv1\u002Fchat\u002Fcompletions                               | [OpenAI 文档](https:\u002F\u002Fplatform.openai.com\u002Fdocs)                                                                                |\n| Google AI Studio | https:\u002F\u002Fgenerativelanguage.googleapis.com\u002Fv1beta\u002Fopenai\u002Fchat\u002Fcompletions | [Google AI 文档](https:\u002F\u002Fai.google.dev\u002Fgemini-api\u002Fdocs\u002Fopenai)                                                                 |\n| OpenRouter       | https:\u002F\u002Fopenrouter.ai\u002Fapi\u002Fv1\u002Fchat\u002Fcompletions                            | [OpenRouter 模型](https:\u002F\u002Fopenrouter.ai\u002Fmodels)                                                                                |\n| 自托管           | http:\u002F\u002Flocalhost:8000\u002Fv1                                                 | [VLLM](https:\u002F\u002Fdocs.vllm.ai\u002Fen\u002Flatest\u002Fserving\u002Fopenai_compatible_server.html) 或 [Ollama](https:\u002F\u002Follama.com\u002Fblog\u002Fopenai-compatibility) |\n\n## 许可协议\n\n本项目的核心采用双重许可：\n\n1. [GNU Affero 通用公共许可证 v3.0 (AGPL-3.0)](LICENSE)\n2. 商业许可证\n\n如果您希望在不遵守 AGPL-3.0 许可条款的情况下使用 Chunkr，可以 [联系我们](mailto:mehul@chunkr.ai) 或访问我们的 [网站](https:\u002F\u002Fchunkr.ai)。\n\n## 联系我们\n- 📧 邮箱：[mehul@chunkr.ai](mailto:mehul@chunkr.ai)\n- 📅 预约通话：[预订 30 分钟会议](https:\u002F\u002Fcal.com\u002Fmehulc\u002F30min)\n- 🌐 访问我们的网站：[chunkr.ai](https:\u002F\u002Fchunkr.ai)","# Chunkr 快速上手指南\n\n**Chunkr** 是一个开源的文档智能 API，支持文档布局分析、OCR 和语义分块。它可将 PDF、PPT、Word 及图片转换为适合 RAG\u002FLLM 使用的数据块。本指南针对开源版本（基于社区模型）的快速部署进行说明。\n\n## 环境准备\n\n在开始之前，请确保您的开发环境满足以下要求：\n\n- **操作系统**: Linux \u002F macOS \u002F Windows (需支持 Docker)\n- **核心工具**: \n  - [Docker](https:\u002F\u002Fdocs.docker.com\u002Fget-docker\u002F)\n  - [Docker Compose](https:\u002F\u002Fdocs.docker.com\u002Fcompose\u002Finstall\u002F)\n- **硬件加速 (可选)**: \n  - 如需 GPU 支持，请安装 [NVIDIA Container Toolkit](https:\u002F\u002Fdocs.nvidia.com\u002Fdatacenter\u002Fcloud-native\u002Fcontainer-toolkit\u002Finstall-guide.html)\n  - 若仅使用 CPU 或 Mac ARM 架构 (M1\u002FM2\u002FM3)，无需额外显卡驱动\n\n## 安装步骤\n\n### 1. 克隆仓库\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\ncd chunkr\n```\n\n### 2. 配置环境变量\n复制示例文件并修改配置：\n```bash\n# 复制环境变量模板\ncp .env.example .env\n\n# 复制 LLM 模型配置模板\ncp models.example.yaml models.yaml\n```\n\n> **注意**: 您需要编辑 `.env` 和 `models.yaml` 文件以填入有效的 LLM API Key。推荐使用 `models.yaml` 配置多个模型及速率限制。\n\n**LLM 配置示例 (`models.yaml`)**:\n```yaml\nmodels:\n  - id: gpt-4o\n    model: gpt-4o\n    provider_url: https:\u002F\u002Fapi.openai.com\u002Fv1\u002Fchat\u002Fcompletions\n    api_key: \"your_openai_api_key_here\"\n    default: true\n    rate-limit: 200\n```\n\n### 3. 启动服务\n根据您的硬件环境选择对应的启动命令：\n\n- **GPU 部署**:\n  ```bash\n  docker compose up -d\n  ```\n- **纯 CPU 部署**:\n  ```bash\n  docker compose -f compose.yaml -f compose.cpu.yaml up -d\n  ```\n- **Mac ARM 架构 (M1\u002FM2\u002FM3)**:\n  ```bash\n  docker compose -f compose.yaml -f compose.cpu.yaml -f compose.mac.yaml up -d\n  ```\n\n## 基本使用\n\n服务启动成功后，您可通过以下地址访问：\n\n- **Web 管理界面**: `http:\u002F\u002Flocalhost:5173`\n- **API 接口**: `http:\u002F\u002Flocalhost:8000`\n\n停止服务时，请使用对应的 `down` 命令（例如 `docker compose down`）。\n\n---\n\n**⚠️ 许可说明**\n本项目采用双重许可模式（AGPL-3.0 或商业许可）。如果您需要在生产环境中使用且不遵守 AGPL 条款，请联系官方获取商业授权。","某法律科技初创团队正在搭建企业级合同检索助手，核心需求是从海量历史扫描件中提取关键条款并接入大模型知识库。\n\n### 没有 chunkr 时\n- 直接使用 PyPDF2 等基础库解析时，复杂的跨页表格会被打散成无意义的乱码字符串。\n- 面对模糊的扫描件，开源 OCR 方案往往误识率高，导致“金额”、“日期”等关键字段提取失败。\n- 缺乏语义理解能力，生成的文本切片过长或断裂，严重影响后续向量检索的准确率。\n- 不同格式的文档（Word、PPT）需要分别开发解析脚本，工程维护成本极高。\n\n### 使用 chunkr 后\n- chunkr 利用视觉布局分析技术，精准定位表格区域，确保数据结构在转换后依然完整。\n- 集成优化的 OCR 引擎能高效处理低分辨率图像，显著提升手写体及印章文字的识别精度。\n- 提供开箱即用的语义分块功能，自动按逻辑段落切割文本，完美适配 RAG 检索需求。\n- 统一支持 PDF、Word 等多种格式输入，开发者只需调用一次接口即可完成多源数据标准化。\n\nchunkr 通过端到端的文档智能处理，让团队能快速构建高可用的企业级知识问答系统。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Flumina-ai-inc_chunkr_8621a7f9.png","lumina-ai-inc","Lumina","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Flumina-ai-inc_2c82c3a2.png","",null,"chunkrai","https:\u002F\u002Fwww.chunkr.ai","https:\u002F\u002Fgithub.com\u002Flumina-ai-inc",[84,88,92,96,100,104,108,112],{"name":85,"color":86,"percentage":87},"Rust","#dea584",43.6,{"name":89,"color":90,"percentage":91},"TypeScript","#3178c6",34.8,{"name":93,"color":94,"percentage":95},"CSS","#663399",9.3,{"name":97,"color":98,"percentage":99},"PLpgSQL","#336790",6.9,{"name":101,"color":102,"percentage":103},"Python","#3572A5",4.6,{"name":105,"color":106,"percentage":107},"Dockerfile","#384d54",0.5,{"name":109,"color":110,"percentage":111},"HTML","#e34c26",0.2,{"name":113,"color":114,"percentage":115},"JavaScript","#f1e05a",0.1,2939,183,"2026-04-04T14:18:40","AGPL-3.0","Linux, macOS","可选，需 NVIDIA 显卡及 NVIDIA Container Toolkit，具体型号、显存及 CUDA 版本未说明","未说明",{"notes":124,"python":122,"dependencies":125},"依赖 Docker 和 Docker Compose 环境；GPU 支持为可选；需配置 LLM API 密钥；开源版使用社区模型，云版使用专有模型；核心代码采用 AGPL-3.0 或商业双许可。",[122],[51,13,14],4,"2026-03-27T02:49:30.150509","2026-04-06T08:46:23.074150",[131,136,140,145,150,155],{"id":132,"question_zh":133,"answer_zh":134,"source_url":135},2136,"Docker Compose 部署后如何获取或配置 API_KEY？","需要将 `.env.example` 文件复制为 `.env`，并在其中添加你的 OpenAI API Key。之后运行 `docker compose up` 即可正常使用前端。此方案已在多个机器上测试通过（基于 commit b7be0b6）。\n\n来源：https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F355","https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F355",{"id":137,"question_zh":138,"answer_zh":139,"source_url":135},2137,"如何在没有 GPU 的环境下运行 Chunkr？","可以使用 CPU 模式运行。具体命令为：`docker compose -f compose-cpu.yaml up -d`。这允许在不使用 GPU 的情况下启动服务。\n\n来源：https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F355",{"id":141,"question_zh":142,"answer_zh":143,"source_url":144},2138,"Docker 部署后无法登录系统怎么办？","尝试重启容器以解决随机 Docker 错误：先执行 `sudo docker compose down`，然后执行 `sudo docker compose up`。同时检查本地是否运行了 PostgreSQL 服务（Mac 通常开机自动启动），确保数据库连接正常。\n\n来源：https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F438","https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F438",{"id":146,"question_zh":147,"answer_zh":148,"source_url":149},2139,"Chunkr 是否支持使用自托管的开源大模型（Local LLM）？","支持。你可以使用任何兼容 OpenAI API 的大模型。性能方面，Qwen\u002FQwen2.5-VL-72B-Instruct 效果最好（比云 API 差约 5%）；若需自托管，推荐 Qwen\u002FQwen2.5-VL-7B-Instruct（比云 API 差约 8%）。\n\n来源：https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F330","https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F330",{"id":151,"question_zh":152,"answer_zh":153,"source_url":154},2140,"自托管时 Keycloak 证书配置及登录重定向失败如何解决？","可以通过 OpenSSL 生成证书来解决 IP 访问问题。命令如下：`openssl req -x509 -nodes -days 365 -newkey rsa-2048 -keyout certs\u002Fnginx.key -out certs\u002Fnginx.crt -subj \"\u002FCN=localhost\" -addext \"subjectAltName=DNS:localhost,IP:127.0.0.1\"`。同时确保 `.env` 中的 `VITE_KEYCLOAK_URL` 等配置与服务器 IP 匹配。\n\n来源：https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F523","https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F523",{"id":156,"question_zh":157,"answer_zh":158,"source_url":159},2141,"使用 SDK 上传文件时出现 ReadTimeout 错误如何处理？","这是 SDK 在轮询过程中可能遇到的已知问题。建议更新到最新版本的 SDK 包，维护者已确认相关修复版本测试通过。请确保网络环境稳定且使用了正确的 API 配置。\n\n来源：https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F451","https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F451",[161,166,171,176,181,186,191,196,201,206,210,215,220,225,230,234,238,243,248,253],{"id":162,"version":163,"summary_zh":164,"released_at":165},111286,"v2.2.1","## [2.2.1](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fv2.2.0...v2.2.1) (2025-07-31)\n\n\n### Bug Fixes\n\n* Replaced vgt with yolo model as it's more practical for consumer hardware ([ff4b906](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fff4b9063eaa0fabc14586d1176ec528fe77e2fa0))","2025-07-31T20:29:25",{"id":167,"version":168,"summary_zh":169,"released_at":170},111287,"chunkr-services-v0.1.6","## [0.1.6](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-services-v0.1.5...chunkr-services-v0.1.6) (2025-07-31)\n\n\n### Bug Fixes\n\n* Replaced vgt with yolo model as it's more practical for consumer hardware ([ff4b906](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fff4b9063eaa0fabc14586d1176ec528fe77e2fa0))","2025-07-31T20:29:24",{"id":172,"version":173,"summary_zh":174,"released_at":175},111288,"v2.2.0","## [2.2.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fv2.1.1...v2.2.0) (2025-07-30)\n\n\n### Features\n\n* Created a stable and simple version by removing all extra\u002Funused components ([#570](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F570)) ([7a444ea](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F7a444eac4cab1e4f811997fc513a9f2db97aa5b3))\n\n\n### Bug Fixes\n\n* **core:** Auto-fix clippy warnings ([afa853c](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fafa853cdd6122d75aa61cc743f507e76cd6e2be6))\n* Remove duplicate email addresses in README.md ([e15d2de](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fe15d2defa5f5372837c200c53a29505ae9924d89))\n* Use local builds in compose.yaml for easier development ([c53f1de](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fc53f1de5de2bcfcfab7919c04e0ed78f44d3f6e4))","2025-07-30T18:13:27",{"id":177,"version":178,"summary_zh":179,"released_at":180},111289,"chunkr-web-v2.2.0","## [2.2.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-web-v2.1.1...chunkr-web-v2.2.0) (2025-07-30)\n\n\n### Features\n\n* Created a stable and simple version by removing all extra\u002Funused components ([#570](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F570)) ([7a444ea](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F7a444eac4cab1e4f811997fc513a9f2db97aa5b3))","2025-07-30T18:13:26",{"id":182,"version":183,"summary_zh":184,"released_at":185},111290,"chunkr-services-v0.1.5","## [0.1.5](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-services-v0.1.4...chunkr-services-v0.1.5) (2025-07-30)\n\n\n### Features\n\n* Created a stable and simple version by removing all extra\u002Funused components ([#570](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F570)) ([7a444ea](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F7a444eac4cab1e4f811997fc513a9f2db97aa5b3))","2025-07-30T18:13:25",{"id":187,"version":188,"summary_zh":189,"released_at":190},111291,"chunkr-core-v2.0.1","## [2.0.1](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-core-v2.0.0...chunkr-core-v2.0.1) (2025-07-30)\n\n\n### Bug Fixes\n\n* **core:** Auto-fix clippy warnings ([afa853c](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fafa853cdd6122d75aa61cc743f507e76cd6e2be6))","2025-07-30T18:13:24",{"id":192,"version":193,"summary_zh":194,"released_at":195},111292,"v2.1.1","## [2.1.1](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fv2.1.0...v2.1.1) (2025-06-30)\n\n\n### Bug Fixes\n\n* Remove keycloakify theme ([ea46cbe](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fea46cbea3e6d6abca04f2c79f8c5bd75d496ac7b))","2025-06-30T20:05:03",{"id":197,"version":198,"summary_zh":199,"released_at":200},111293,"chunkr-web-v2.1.1","## [2.1.1](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-web-v2.1.0...chunkr-web-v2.1.1) (2025-06-30)\n\n\n### Bug Fixes\n\n* Remove keycloakify theme ([ea46cbe](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fea46cbea3e6d6abca04f2c79f8c5bd75d496ac7b))","2025-06-30T20:05:02",{"id":202,"version":203,"summary_zh":204,"released_at":205},111294,"v2.1.0","## [2.1.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fv2.0.0...v2.1.0) (2025-06-28)\n\n\n### Features\n\n* Redesign keycloak auth pages ([adaf74b](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fadaf74b2c57b37779794e9e3c736905b02bccff3))\n\n\n### Bug Fixes\n\n* Resolve logger warnings ([#510](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F510)) ([8810d5e](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F8810d5ec1ce03c12daa1bee98afed3fb2386cf5a))","2025-06-28T23:44:00",{"id":207,"version":208,"summary_zh":209,"released_at":205},111295,"chunkr-web-v2.1.0","## [2.1.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-web-v2.0.0...chunkr-web-v2.1.0) (2025-06-28)\n\n\n### Features\n\n* Redesign keycloak auth pages ([adaf74b](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fadaf74b2c57b37779794e9e3c736905b02bccff3))",{"id":211,"version":212,"summary_zh":213,"released_at":214},111296,"chunkr-services-v0.1.4","## [0.1.4](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-services-v0.1.3...chunkr-services-v0.1.4) (2025-06-28)\n\n\n### Bug Fixes\n\n* Resolve logger warnings ([#510](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F510)) ([8810d5e](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F8810d5ec1ce03c12daa1bee98afed3fb2386cf5a))","2025-06-28T23:43:59",{"id":216,"version":217,"summary_zh":218,"released_at":219},111297,"v2.0.0","## [2.0.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fv1.20.3...v2.0.0) (2025-06-24)\n\n\n### ⚠ BREAKING CHANGES\n\n* consolidate HTML\u002Fmarkdown generation into single format choice\n\n### Features\n\n* Consolidate HTML\u002Fmarkdown generation into single format choice ([a974f3f](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fa974f3fbc2bd9158ca052c21a121b479e0eb7613))","2025-06-24T20:49:15",{"id":221,"version":222,"summary_zh":223,"released_at":224},111298,"chunkr-web-v2.0.0","## [2.0.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-web-v1.6.2...chunkr-web-v2.0.0) (2025-06-24)\n\n\n### ⚠ BREAKING CHANGES\n\n* consolidate HTML\u002Fmarkdown generation into single format choice\n\n### Features\n\n* Consolidate HTML\u002Fmarkdown generation into single format choice ([a974f3f](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fa974f3fbc2bd9158ca052c21a121b479e0eb7613))","2025-06-24T20:49:14",{"id":226,"version":227,"summary_zh":228,"released_at":229},111299,"chunkr-core-v2.0.0","## [2.0.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-core-v1.15.1...chunkr-core-v2.0.0) (2025-06-24)\n\n\n### ⚠ BREAKING CHANGES\n\n* consolidate HTML\u002Fmarkdown generation into single format choice\n\n### Features\n\n* Consolidate HTML\u002Fmarkdown generation into single format choice ([a974f3f](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fa974f3fbc2bd9158ca052c21a121b479e0eb7613))","2025-06-24T20:49:13",{"id":231,"version":232,"summary_zh":233,"released_at":219},111300,"chunkr-chart-v2.0.0","## [2.0.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-chart-v1.3.2...chunkr-chart-v2.0.0) (2025-06-24)\n\n\n### ⚠ BREAKING CHANGES\n\n* consolidate HTML\u002Fmarkdown generation into single format choice\n\n### Features\n\n* Consolidate HTML\u002Fmarkdown generation into single format choice ([a974f3f](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fa974f3fbc2bd9158ca052c21a121b479e0eb7613))",{"id":235,"version":236,"summary_zh":237,"released_at":229},111301,"chunkr-ai-v0.1.0","## [0.1.0](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-ai-v0.0.50...chunkr-ai-v0.1.0) (2025-06-24)\n\n\n### ⚠ BREAKING CHANGES\n\n* consolidate HTML\u002Fmarkdown generation into single format choice\n\n### Features\n\n* Consolidate HTML\u002Fmarkdown generation into single format choice ([a974f3f](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fa974f3fbc2bd9158ca052c21a121b479e0eb7613))",{"id":239,"version":240,"summary_zh":241,"released_at":242},111302,"v1.20.3","## [1.20.3](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fv1.20.2...v1.20.3) (2025-06-20)\n\n\n### Bug Fixes\n\n* Updated rust version ([5fce4c4](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F5fce4c4496dc02954088373b415ba7722ff076be))","2025-06-20T20:47:52",{"id":244,"version":245,"summary_zh":246,"released_at":247},111303,"v1.20.2","## [1.20.2](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fv1.20.1...v1.20.2) (2025-06-20)\n\n\n### Bug Fixes\n\n* Reverted landing page hero image ([#548](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F548)) ([e798336](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fe7983361fdbb9243c055f2444cacb55aa6072a78))\n* Stored cross-site scripting in segmentchunk component ([#546](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F546)) ([49334b7](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F49334b788e742f7453c8987e856b57dcb56f0773))","2025-06-20T19:17:09",{"id":249,"version":250,"summary_zh":251,"released_at":252},111304,"chunkr-web-v1.6.2","## [1.6.2](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fchunkr-web-v1.6.1...chunkr-web-v1.6.2) (2025-06-20)\n\n\n### Bug Fixes\n\n* Reverted landing page hero image ([#548](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F548)) ([e798336](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002Fe7983361fdbb9243c055f2444cacb55aa6072a78))\n* Stored cross-site scripting in segmentchunk component ([#546](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F546)) ([49334b7](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F49334b788e742f7453c8987e856b57dcb56f0773))","2025-06-20T19:17:08",{"id":254,"version":255,"summary_zh":256,"released_at":257},111305,"v1.20.1","## [1.20.1](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcompare\u002Fv1.20.0...v1.20.1) (2025-05-28)\n\n\n### Bug Fixes\n\n* **core:** Auto-fix clippy warnings ([#541](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F541)) ([00db663](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F00db66361022d5566f281badf327a73724da7922))\n* Update default for high resolution to true ([#536](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F536)) ([37cc757](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F37cc757ea41acce4a662a127bc141e77b56cda03))\n* Update robots.txt and blog post page, added sitemap, and removed toast from auth  ([#535](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F535)) ([3c8f827](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F3c8f82701d4ff40f932b24607da2dfd394f31e60))\n* Updated manual conversion from html to mkd to pandoc ([#539](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F539)) ([16cc847](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F16cc847f5728bd963bf8f367579721098190141c))\n\n\n### Performance Improvements\n\n* Improved llm analytics for extraction errors ([#538](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fissues\u002F538)) ([0302499](https:\u002F\u002Fgithub.com\u002Flumina-ai-inc\u002Fchunkr\u002Fcommit\u002F0302499f9942c3f2d0f3888ef419d7e2f6945394))","2025-05-28T23:54:21"]