[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-nuclia--nucliadb":3,"tool-nuclia--nucliadb":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",138956,2,"2026-04-05T11:33:21",[13,15,26],"语言模型",{"id":28,"name":29,"github_repo":30,"description_zh":31,"stars":32,"difficulty_score":23,"last_commit_at":33,"category_tags":34,"status":16},2271,"ComfyUI","Comfy-Org\u002FComfyUI","ComfyUI 是一款功能强大且高度模块化的视觉 AI 引擎，专为设计和执行复杂的 Stable Diffusion 图像生成流程而打造。它摒弃了传统的代码编写模式，采用直观的节点式流程图界面，让用户通过连接不同的功能模块即可构建个性化的生成管线。\n\n这一设计巧妙解决了高级 AI 绘图工作流配置复杂、灵活性不足的痛点。用户无需具备编程背景，也能自由组合模型、调整参数并实时预览效果，轻松实现从基础文生图到多步骤高清修复等各类复杂任务。ComfyUI 拥有极佳的兼容性，不仅支持 Windows、macOS 和 Linux 全平台，还广泛适配 NVIDIA、AMD、Intel 及苹果 Silicon 等多种硬件架构，并率先支持 SDXL、Flux、SD3 等前沿模型。\n\n无论是希望深入探索算法潜力的研究人员和开发者，还是追求极致创作自由度的设计师与资深 AI 绘画爱好者，ComfyUI 都能提供强大的支持。其独特的模块化架构允许社区不断扩展新功能，使其成为当前最灵活、生态最丰富的开源扩散模型工具之一，帮助用户将创意高效转化为现实。",107662,"2026-04-03T11:11:01",[13,14,15],{"id":36,"name":37,"github_repo":38,"description_zh":39,"stars":40,"difficulty_score":23,"last_commit_at":41,"category_tags":42,"status":16},3704,"NextChat","ChatGPTNextWeb\u002FNextChat","NextChat 是一款轻量且极速的 AI 助手，旨在为用户提供流畅、跨平台的大模型交互体验。它完美解决了用户在多设备间切换时难以保持对话连续性，以及面对众多 AI 模型不知如何统一管理的痛点。无论是日常办公、学习辅助还是创意激发，NextChat 都能让用户随时随地通过网页、iOS、Android、Windows、MacOS 或 Linux 端无缝接入智能服务。\n\n这款工具非常适合普通用户、学生、职场人士以及需要私有化部署的企业团队使用。对于开发者而言，它也提供了便捷的自托管方案，支持一键部署到 Vercel 或 Zeabur 等平台。\n\nNextChat 的核心亮点在于其广泛的模型兼容性，原生支持 Claude、DeepSeek、GPT-4 及 Gemini Pro 等主流大模型，让用户在一个界面即可自由切换不同 AI 能力。此外，它还率先支持 MCP（Model Context Protocol）协议，增强了上下文处理能力。针对企业用户，NextChat 提供专业版解决方案，具备品牌定制、细粒度权限控制、内部知识库整合及安全审计等功能，满足公司对数据隐私和个性化管理的高标准要求。",87618,"2026-04-05T07:20:52",[13,26],{"id":44,"name":45,"github_repo":46,"description_zh":47,"stars":48,"difficulty_score":23,"last_commit_at":49,"category_tags":50,"status":16},2268,"ML-For-Beginners","microsoft\u002FML-For-Beginners","ML-For-Beginners 是由微软推出的一套系统化机器学习入门课程，旨在帮助零基础用户轻松掌握经典机器学习知识。这套课程将学习路径规划为 12 周，包含 26 节精炼课程和 52 道配套测验，内容涵盖从基础概念到实际应用的完整流程，有效解决了初学者面对庞大知识体系时无从下手、缺乏结构化指导的痛点。\n\n无论是希望转型的开发者、需要补充算法背景的研究人员，还是对人工智能充满好奇的普通爱好者，都能从中受益。课程不仅提供了清晰的理论讲解，还强调动手实践，让用户在循序渐进中建立扎实的技能基础。其独特的亮点在于强大的多语言支持，通过自动化机制提供了包括简体中文在内的 50 多种语言版本，极大地降低了全球不同背景用户的学习门槛。此外，项目采用开源协作模式，社区活跃且内容持续更新，确保学习者能获取前沿且准确的技术资讯。如果你正寻找一条清晰、友好且专业的机器学习入门之路，ML-For-Beginners 将是理想的起点。",84991,"2026-04-05T10:45:23",[14,51,52,53,15,54,26,13,55],"数据工具","视频","插件","其他","音频",{"id":57,"name":58,"github_repo":59,"description_zh":60,"stars":61,"difficulty_score":10,"last_commit_at":62,"category_tags":63,"status":16},3128,"ragflow","infiniflow\u002Fragflow","RAGFlow 是一款领先的开源检索增强生成（RAG）引擎，旨在为大语言模型构建更精准、可靠的上下文层。它巧妙地将前沿的 RAG 技术与智能体（Agent）能力相结合，不仅支持从各类文档中高效提取知识，还能让模型基于这些知识进行逻辑推理和任务执行。\n\n在大模型应用中，幻觉问题和知识滞后是常见痛点。RAGFlow 通过深度解析复杂文档结构（如表格、图表及混合排版），显著提升了信息检索的准确度，从而有效减少模型“胡编乱造”的现象，确保回答既有据可依又具备时效性。其内置的智能体机制更进一步，使系统不仅能回答问题，还能自主规划步骤解决复杂问题。\n\n这款工具特别适合开发者、企业技术团队以及 AI 研究人员使用。无论是希望快速搭建私有知识库问答系统，还是致力于探索大模型在垂直领域落地的创新者，都能从中受益。RAGFlow 提供了可视化的工作流编排界面和灵活的 API 接口，既降低了非算法背景用户的上手门槛，也满足了专业开发者对系统深度定制的需求。作为基于 Apache 2.0 协议开源的项目，它正成为连接通用大模型与行业专有知识之间的重要桥梁。",77062,"2026-04-04T04:44:48",[15,14,13,26,54],{"id":65,"github_repo":66,"name":67,"description_en":68,"description_zh":69,"ai_summary_zh":69,"readme_en":70,"readme_zh":71,"quickstart_zh":72,"use_case_zh":73,"hero_image_url":74,"owner_login":75,"owner_name":76,"owner_avatar_url":77,"owner_bio":78,"owner_company":79,"owner_location":79,"owner_email":80,"owner_twitter":81,"owner_website":82,"owner_url":83,"languages":84,"stars":115,"forks":116,"last_commit_at":117,"license":118,"difficulty_score":119,"env_os":120,"env_gpu":120,"env_ram":120,"env_deps":121,"category_tags":128,"github_topics":129,"view_count":10,"oss_zip_url":79,"oss_zip_packed_at":79,"status":16,"created_at":147,"updated_at":148,"faqs":149,"releases":175},995,"nuclia\u002Fnucliadb","nucliadb","NucliaDB, The AI Search database for RAG","NucliaDB 是一款专为非结构化数据设计的 AI 搜索数据库，特别适合需要处理大量文本、文件和其他复杂数据的开发者和研究人员。它结合了向量搜索、全文检索和图索引的能力，能够快速找到语义相似的内容，而不仅依赖关键词匹配。这让它在处理自然语言任务时表现出色，比如查找相似句子或提取上下文相关的数据。\n\n对于希望利用 AI 能力但又不想从头构建复杂数据处理流程的团队来说，NucliaDB 提供了一个开箱即用的解决方案。通过与 Nuclia 云服务集成，它可以自动完成数据提取、增强和推理等繁琐工作，让用户专注于应用开发。此外，它的多租户支持和基于角色的安全系统也使其非常适合企业级应用场景。\n\n技术亮点方面，NucliaDB 使用 Rust 和 Python 编写，兼具高性能和易用性。它支持分布式搜索、云原生架构，并兼容多种存储后端（如 PostgreSQL、S3 等）。这些特性让它既能处理大规模数据集，又能灵活适应不同的部署环境。\n\n无论是想快速搭建一个智能搜索引擎，还是为机器学习模型准备训练数据，NucliaDB 都是一个值得尝试的选择，尤其适合熟悉 NLP 技术的开发者和研究人员使用。","[![Contributor Covenant](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FContributor%20Covenant-2.0-4baaaa.svg)](CODE_OF_CONDUCT.md)\n[![License: AGPL V3](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-AGPL%20V3-blue)](LICENCE.md)\n![X (formerly Twitter) Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FnucliaAI?color=blue)\n![Rust](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRust-black?logo=rust&style=plastic)\n![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-black?logo=python&style=plastic)\n[![codecov](https:\u002F\u002Fcodecov.io\u002Fgh\u002Fnuclia\u002Fnucliadb\u002Fbranch\u002Fmain\u002Fgraph\u002Fbadge.svg?token=06SRGAV5SS)](https:\u002F\u002Fcodecov.io\u002Fgh\u002Fnuclia\u002Fnucliadb)\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Fimages\u002Fnuclia_db_positiu.svg\" alt=\"Nuclia\" height=\"100\">\n\u003C\u002Fp>\n\u003Ch3 align=\"center\">The AI Search Database.\u003C\u002Fh3>\n\n\u003Ch4 align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fmanagement\u002Fnucliadb\u002Fintro\">Quickstart\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002F\">Nuclia Docs\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fnuclia-community.slack.com\">Community\u003C\u002Fa>\n\u003C\u002Fh4>\n\nNucliaDB is a robust database that allows storing and searching on\nunstructured data.\n\nIt is an out of the box hybrid search database, utilizing vector,\nfull text and graph indexes.\n\nNucliaDB is written in Rust and Python. We designed it to index large datasets and provide multi-teanant support.\n\nWhen utilizing NucliaDB with Nuclia cloud, you are able to the power\nof an NLP database without the hassle of data extraction, enrichment\nand inference. We do all the hard work for you.\n\n\n# Features\n- Store text, files, vectors, labels and annotations\n- Perform text searches and given a word or set of words, return resources in our database that contain them.\n- Perform semantic searches with vectors. For example, given a set of vectors, return the closest matches in our database. With NLP, this allows us to look for similar sentences without being constrained by exact keywords.\n- Export your data in a format compatible with most NLP pipelines (HuggingFace datasets, pytorch, etc)\n- Store original data, extracting and data pulled from the Understanding API\n- Index fields, paragraphs, and semantic sentences on index storage\n- Cloud data and insight extraction with the Nuclia Understanding API™\n- Cloud connection to train ML models with Nuclia Learning API™\n- Role based security system with upstream proxy authentication validation\n- Resources with multiple fields and metadata\n- Text\u002FHTML\u002FMarkdown plain fields support\n- Field types: text, file, link, conversation\n- Storage layer (PostgreSQL)\n- Blob support with S3-compatible API, GCS and Azure Blob Storage\n- Replication of index storage\n- Distributed search\n- Cloud-native\n\n## Architecture\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fnuclia_nucliadb_readme_97073c79957d.png\" alt=\"Architecture\" width=\"500px\" style=\"background-color: #fff\">\n\u003C\u002Fp>\n\n## Quickstart\n\nTrying NucliaDB is super easy! You can extend your knowledge with the\nfollowing readings:\n\n- [Quick start!](https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fmanagement\u002Fnucliadb\u002Fintro)\n- Read about what Knowledge boxes are in [our basic concepts](https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fmanagement\u002Fnucliadb\u002Fbasics) section\n- [Upload your data](https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fingestion\u002Fintro)\n\n# 💬 Community\n\n- Chat with us in [Slack][slack]\n- 📝 [Blog Posts][blogs]\n- Follow us on [X][X]\n- Do you want to [work with us][linkedin]?\n\n# 🙋 FAQ\n\n## How is NucliaDB different from traditional search engines like Elasticsearch or Solr?\n\nThe core difference and advantage of NucliaDB is its architecture built from the ground up for unstructured data. Its vector index, keyword, graph and fuzzy search provide an API to use all extracted and extracted information from Nuclia, Understanding API and provides powerful NLP abilities to any application with low code and peace of mind.\n\n## What license does NucliaDB use?\n\nNucliaDB is open-source under the GNU Affero General Public License Version 3 - AGPLv3. Fundamentally, this means that you are free to use NucliaDB for your project, as long as you don't modify NucliaDB. If you do, you have to make the modifications public.\n\n## What is Nuclia's business model?\n\nOur business model relies on our normalization API, this one is based on `Nuclia Learning API` and `Nuclia Understanding API`. This two APIs offers transformation of unstructured data to NucliaDB compatible data with AI. We also offer NucliaDB as a service at our multi-cloud provider infrastructure: [https:\u002F\u002Fnuclia.cloud](https:\u002F\u002Fnuclia.cloud).\n\n# 🤝 Contribute and spread the word\n\nWe are always happy to have contributions: code, documentation, issues, feedback, or even saying hello on Slack! Here is how you can get started:\n\n- Read our [Contributor Covenant Code of Conduct](CODE_OF_CONDUCT.md)\n- Create a fork of NucliaDB and submit your pull request!\n\n✨ And to thank you for your contributions, claim your swag by emailing us at info at nuclia.com.\n\n## Reference\n\n- [Nuclia Documentation](https:\u002F\u002Fdocs.nuclia.dev\u002F)\n- [API Reference](https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fapi)\n\n## Meta\n\n- [Rust Code Style](CODE_STYLE_RUST.md)\n- [Python Code Style](CODE_STYLE_PYTHON.md)\n- [Code of conduct](CODE_OF_CONDUCT.md)\n- [Contributing](CONTRIBUTING.md)\n\n[website]: https:\u002F\u002Fnuclia.com\u002F\n[cloud]: https:\u002F\u002Fnuclia.cloud\u002F\n[X]: https:\u002F\u002Fx.com\u002FnucliaAI\n[slack]: https:\u002F\u002Fnuclia-community.slack.com\n[blogs]: https:\u002F\u002Fnuclia.com\u002Fblog\n[linkedin]: https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fnuclia\u002F\n","[![Contributor Covenant](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FContributor%20Covenant-2.0-4baaaa.svg)](CODE_OF_CONDUCT.md)\n[![License: AGPL V3](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-AGPL%20V3-blue)](LICENCE.md)\n![X (formerly Twitter) Follow](https:\u002F\u002Fimg.shields.io\u002Ftwitter\u002Ffollow\u002FnucliaAI?color=blue)\n![Rust](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRust-black?logo=rust&style=plastic)\n![Python](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPython-black?logo=python&style=plastic)\n[![codecov](https:\u002F\u002Fcodecov.io\u002Fgh\u002Fnuclia\u002Fnucliadb\u002Fbranch\u002Fmain\u002Fgraph\u002Fbadge.svg?token=06SRGAV5SS)](https:\u002F\u002Fcodecov.io\u002Fgh\u002Fnuclia\u002Fnucliadb)\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"docs\u002Fassets\u002Fimages\u002Fnuclia_db_positiu.svg\" alt=\"Nuclia\" height=\"100\">\n\u003C\u002Fp>\n\u003Ch3 align=\"center\">AI 搜索数据库。\u003C\u002Fh3>\n\n\u003Ch4 align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fmanagement\u002Fnucliadb\u002Fintro\">快速入门\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002F\">Nuclia 文档\u003C\u002Fa> |\n  \u003Ca href=\"https:\u002F\u002Fnuclia-community.slack.com\">社区\u003C\u002Fa>\n\u003C\u002Fh4>\n\nNucliaDB 是一个强大的数据库，允许存储和搜索非结构化数据。\n\n它是一个开箱即用的混合搜索数据库，利用向量、全文和图索引。\n\nNucliaDB 使用 Rust 和 Python 编写。我们设计它用于索引大型数据集并提供多租户支持。\n\n当将 NucliaDB 与 Nuclia 云一起使用时，您可以利用 NLP 数据库的强大功能，而无需担心数据提取、丰富和推理。我们为您完成了所有繁重的工作。\n\n\n# 功能\n- 存储文本、文件、向量、标签和注释\n- 执行文本搜索，给定一个单词或一组单词，返回包含它们的数据库资源。\n- 使用向量执行语义搜索。例如，给定一组向量，返回数据库中最接近的匹配项。通过 NLP（自然语言处理），这使我们能够查找相似的句子，而不受精确关键词的限制。\n- 以兼容大多数 NLP 管道的格式导出您的数据（HuggingFace 数据集、pytorch 等）\n- 存储原始数据，提取并通过理解 API 获取的数据\n- 在索引存储中索引字段、段落和语义句子\n- 使用 Nuclia 理解 API™ 进行云数据和洞察提取\n- 使用 Nuclia 学习 API™ 连接云端以训练机器学习模型\n- 基于角色的安全系统，具有上游代理身份验证验证\n- 支持多个字段和元数据的资源\n- 支持纯文本\u002FHTML\u002FMarkdown 字段\n- 字段类型：文本、文件、链接、对话\n- 存储层（PostgreSQL）\n- 使用 S3 兼容 API、GCS 和 Azure Blob Storage 的 Blob 支持\n- 索引存储的复制\n- 分布式搜索\n- 云原生\n\n## 架构\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fnuclia_nucliadb_readme_97073c79957d.png\" alt=\"架构\" width=\"500px\" style=\"background-color: #fff\">\n\u003C\u002Fp>\n\n## 快速入门\n\n尝试 NucliaDB 非常容易！您可以通过以下阅读扩展知识：\n\n- [快速开始！](https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fmanagement\u002Fnucliadb\u002Fintro)\n- 在 [我们的基本概念](https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fmanagement\u002Fnucliadb\u002Fbasics) 部分了解知识框是什么\n- [上传您的数据](https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fingestion\u002Fintro)\n\n# 💬 社区\n\n- 在 [Slack][slack] 上与我们聊天\n- 📝 [博客文章][blogs]\n- 在 [X][X] 上关注我们\n- 您想 [与我们一起工作][linkedin] 吗？\n\n# 🙋 常见问题\n\n## NucliaDB 与传统的搜索引擎（如 Elasticsearch 或 Solr）有何不同？\n\nNucliaDB 的核心区别和优势在于其专为非结构化数据构建的架构。它的向量索引、关键字、图形和模糊搜索提供了使用从 Nuclia 提取的所有信息的 API，理解 API 并为任何应用程序提供强大的 NLP 能力，只需少量代码即可安心使用。\n\n## NucliaDB 使用什么许可证？\n\nNucliaDB 在 GNU Affero 通用公共许可证版本 3 - AGPLv3 下开源。从根本上说，这意味着只要不对 NucliaDB 进行修改，就可以自由地将其用于您的项目。如果您进行了修改，则必须将修改公开。\n\n## Nuclia 的商业模式是什么？\n\n我们的商业模式依赖于我们的标准化 API，该 API 基于 `Nuclia 学习 API` 和 `Nuclia 理解 API`。这两个 API 提供了使用 AI 将非结构化数据转换为与 NucliaDB 兼容的数据。我们还在多云提供商基础设施上提供 NucliaDB 作为服务：[https:\u002F\u002Fnuclia.cloud](https:\u002F\u002Fnuclia.cloud)。\n\n# 🤝 贡献并传播\n\n我们总是乐于接受贡献：代码、文档、问题、反馈，甚至在 Slack 上打个招呼！以下是您可以开始的方式：\n\n- 阅读我们的 [贡献者公约行为准则](CODE_OF_CONDUCT.md)\n- 创建 NucliaDB 的分支并提交您的拉取请求！\n\n✨ 为了感谢您的贡献，请通过电子邮件 info at nuclia.com 索取您的纪念品。\n\n## 参考\n\n- [Nuclia 文档](https:\u002F\u002Fdocs.nuclia.dev\u002F)\n- [API 参考](https:\u002F\u002Fdocs.nuclia.dev\u002Fdocs\u002Fapi)\n\n## 元信息\n\n- [Rust 代码风格](CODE_STYLE_RUST.md)\n- [Python 代码风格](CODE_STYLE_PYTHON.md)\n- [行为准则](CODE_OF_CONDUCT.md)\n- [贡献指南](CONTRIBUTING.md)\n\n[website]: https:\u002F\u002Fnuclia.com\u002F\n[cloud]: https:\u002F\u002Fnuclia.cloud\u002F\n[X]: https:\u002F\u002Fx.com\u002FnucliaAI\n[slack]: https:\u002F\u002Fnuclia-community.slack.com\n[blogs]: https:\u002F\u002Fnuclia.com\u002Fblog\n[linkedin]: https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fnuclia\u002F","# Nucliadb 快速上手指南\n\nNucliaDB 是一个强大的数据库，专注于存储和搜索非结构化数据。它结合了向量、全文和图索引，提供混合搜索能力。\n\n---\n\n## 环境准备\n\n### 系统要求\n- 操作系统：Linux 或 macOS（推荐 Ubuntu 20.04+）\n- 内存：至少 4GB（建议 8GB+）\n- 存储：至少 10GB 可用空间\n\n### 前置依赖\n- Python >= 3.8\n- Rust (稳定版)\n- PostgreSQL (用于存储层)\n- S3 兼容存储（可选，如 MinIO）\n\n安装依赖：\n```bash\n# 安装 Rust\ncurl --proto '=https' --tlsv1.2 -sSf https:\u002F\u002Fsh.rustup.rs | sh\n\n# 安装 Python 和 pip\nsudo apt update\nsudo apt install python3 python3-pip\n\n# 安装 PostgreSQL\nsudo apt install postgresql postgresql-contrib\n```\n\n---\n\n## 安装步骤\n\n1. 克隆 NucliaDB 仓库：\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Fnuclia\u002Fnucliadb.git\n   cd nucliadb\n   ```\n\n2. 创建虚拟环境并安装 Python 依赖：\n   ```bash\n   python3 -m venv venv\n   source venv\u002Fbin\u002Factivate\n   pip install -r requirements.txt\n   ```\n\n3. 编译 Rust 组件：\n   ```bash\n   cargo build --release\n   ```\n\n4. 配置 PostgreSQL 数据库：\n   ```bash\n   sudo -u postgres psql\n   CREATE DATABASE nucliadb;\n   CREATE USER nucliadb WITH PASSWORD 'password';\n   GRANT ALL PRIVILEGES ON DATABASE nucliadb TO nucliadb;\n   \\q\n   ```\n\n5. 设置环境变量：\n   ```bash\n   export DATABASE_URL=postgres:\u002F\u002Fnucliadb:password@localhost\u002Fnucliadb\n   ```\n\n6. 启动服务：\n   ```bash\n   python manage.py runserver\n   ```\n\n---\n\n## 基本使用\n\n以下是一个简单的示例，展示如何上传数据并执行搜索。\n\n### 上传数据\n使用 API 上传文本数据：\n```bash\ncurl -X POST \"http:\u002F\u002Flocalhost:8080\u002Fapi\u002Fv1\u002Fresource\" \\\n     -H \"Content-Type: application\u002Fjson\" \\\n     -d '{\"title\": \"示例文档\", \"content\": \"这是测试内容\"}'\n```\n\n### 执行搜索\n执行关键词搜索：\n```bash\ncurl -X GET \"http:\u002F\u002Flocalhost:8080\u002Fapi\u002Fv1\u002Fsearch?q=测试\"\n```\n\n执行语义搜索（需要向量支持）：\n```bash\ncurl -X POST \"http:\u002F\u002Flocalhost:8080\u002Fapi\u002Fv1\u002Fsearch\u002Fvector\" \\\n     -H \"Content-Type: application\u002Fjson\" \\\n     -d '{\"vector\": [0.1, 0.2, 0.3]}'\n```\n\n---\n\n更多高级功能和配置，请参考官方文档：[Nuclia 文档](https:\u002F\u002Fdocs.nuclia.dev\u002F)","一家在线教育平台的技术团队正在开发智能课程推荐系统，希望通过分析学员的学习记录和课程内容，为每位学员提供个性化的学习建议。\n\n### 没有 nucliadb 时\n- 学员的学习记录分散在文本笔记、视频观看记录和在线讨论中，难以统一管理和搜索\n- 传统搜索引擎只能基于关键词匹配，无法理解语义，导致推荐结果不够精准\n- 数据存储和索引需要多个独立系统维护，增加了开发和运维成本\n- 处理大量非结构化数据时性能下降明显，影响用户体验\n- 缺乏多租户支持，难以实现不同学科的独立数据管理\n\n### 使用 nucliadb 后\n- 统一存储学员的各种学习记录，包括文本、视频和对话，简化了数据管理流程\n- 利用语义搜索功能，能够根据学习内容的深层含义进行精准推荐\n- 一体化的混合搜索架构减少了系统复杂度，降低了维护成本\n- 分布式搜索和索引复制确保了系统在大数据量下的稳定性能\n- 原生支持多租户架构，让不同学科可以独立管理各自的数据空间\n\n通过 nucliadb，教育平台实现了智能化、高性能的课程推荐系统，显著提升了学员的学习体验和效果。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002Fnuclia_nucliadb_18069e22.png","nuclia","Nuclia","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002Fnuclia_032a1c72.png","The RAG as a Service company",null,"info@nuclia.com","nucliaAI","https:\u002F\u002Fnuclia.com","https:\u002F\u002Fgithub.com\u002Fnuclia",[85,89,93,97,101,105,108,112],{"name":86,"color":87,"percentage":88},"Python","#3572A5",77,{"name":90,"color":91,"percentage":92},"Rust","#dea584",18.1,{"name":94,"color":95,"percentage":96},"PureBasic","#5a6986",4.6,{"name":98,"color":99,"percentage":100},"Go Template","#00ADD8",0.2,{"name":102,"color":103,"percentage":104},"Makefile","#427819",0.1,{"name":106,"color":107,"percentage":104},"HTML","#e34c26",{"name":109,"color":110,"percentage":111},"Shell","#89e051",0,{"name":113,"color":114,"percentage":111},"Dockerfile","#384d54",719,58,"2026-04-04T14:16:23","NOASSERTION",4,"未说明",{"notes":122,"python":120,"dependencies":123},"需要 Rust 和 Python 环境支持；存储层依赖 PostgreSQL；支持多种云存储服务（如 S3、GCS、Azure Blob Storage）；分布式搜索和云原生架构可能需要额外配置。",[124,125,126,127],"PostgreSQL","S3-compatible API","GCS","Azure Blob Storage",[53,26,13,51,54],[130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,75,145,146],"database","language-model","machine-learning","mlops","search","search-engine","search-engines","semantic","semantic-search-engine","text-classification","unstructured-data","vector-search","vector-search-engine","vectors","ai-powered-search","python","rust","2026-03-27T02:49:30.150509","2026-04-06T05:16:42.154246",[150,155,160,165,170],{"id":151,"question_zh":152,"answer_zh":153,"source_url":154},4424,"为什么使用插入的向量查询时，结果得分不是 1？","这可能与向量相似度函数计算的精度有关。NucliaDB 的设计是为每个文档存储多个向量（例如每个段落一个向量），因此即使查询向量与存储向量完全一致，得分也可能略低于 1。最重要的是，查询结果应返回正确的第一项。","https:\u002F\u002Fgithub.com\u002Fnuclia\u002Fnucliadb\u002Fissues\u002F1293",{"id":156,"question_zh":157,"answer_zh":158,"source_url":159},4425,"如何在 Windows 上安装 NucliaDB？","由于 `tikv-client` 仅支持 Linux 和 macOS，Windows 用户可能会遇到依赖解析失败的问题。建议使用 Docker 安装和运行 NucliaDB，这是目前最简单的方法。","https:\u002F\u002Fgithub.com\u002Fnuclia\u002Fnucliadb\u002Fissues\u002F977",{"id":161,"question_zh":162,"answer_zh":163,"source_url":164},4426,"如何解决 `parse_duration` 和 `remove_dir_all` 等依赖的安全问题？","部分依赖的安全问题难以直接解决，因为它们是传递性依赖（如 `tantivy` 和 `tempdir`）。更新这些依赖可能导致需要重新索引旧数据。团队计划在未来解决这些问题，但目前建议通过其他方式缓解风险。","https:\u002F\u002Fgithub.com\u002Fnuclia\u002Fnucliadb\u002Fissues\u002F987",{"id":166,"question_zh":167,"answer_zh":168,"source_url":169},4427,"如何修复拼写错误（如 \"knowlwedge\"）？","可以通过提交 Pull Request 修复拼写错误。团队欢迎新贡献者参与项目开发。","https:\u002F\u002Fgithub.com\u002Fnuclia\u002Fnucliadb\u002Fissues\u002F1012",{"id":171,"question_zh":172,"answer_zh":173,"source_url":174},4428,"为什么使用 `get_or_create()` 时会出现 `requests` 模块未解析的错误？","`nucliadb-sdk` 未将 `requests` 明确列为依赖项，因此在某些环境中可能会出现导入错误。建议手动安装 `requests` 模块以解决问题：`pip install requests`。","https:\u002F\u002Fgithub.com\u002Fnuclia\u002Fnucliadb\u002Fissues\u002F656",[176,180,184,188,192,196,200,204,208,212,216,220,224,228,232,236,240,244,248,252],{"id":177,"version":178,"summary_zh":79,"released_at":179},103851,"v6.12.1","2026-03-25T15:03:17",{"id":181,"version":182,"summary_zh":79,"released_at":183},103852,"v6.12.0","2026-02-04T11:22:55",{"id":185,"version":186,"summary_zh":79,"released_at":187},103853,"v6.11.1","2026-01-23T13:58:20",{"id":189,"version":190,"summary_zh":79,"released_at":191},103854,"v6.11.0","2026-01-20T11:57:49",{"id":193,"version":194,"summary_zh":79,"released_at":195},103855,"v6.10.0","2025-12-23T10:49:56",{"id":197,"version":198,"summary_zh":79,"released_at":199},103856,"v6.9.7","2025-11-28T13:07:38",{"id":201,"version":202,"summary_zh":79,"released_at":203},103857,"v6.9.6","2025-11-20T10:36:32",{"id":205,"version":206,"summary_zh":79,"released_at":207},103858,"v6.9.5","2025-11-14T11:03:40",{"id":209,"version":210,"summary_zh":79,"released_at":211},103859,"v6.9.4","2025-11-11T09:28:40",{"id":213,"version":214,"summary_zh":79,"released_at":215},103860,"v6.9.3","2025-11-03T16:08:48",{"id":217,"version":218,"summary_zh":79,"released_at":219},103861,"v6.9.2","2025-10-27T21:23:16",{"id":221,"version":222,"summary_zh":79,"released_at":223},103862,"v6.9.1","2025-10-17T08:21:28",{"id":225,"version":226,"summary_zh":79,"released_at":227},103863,"v6.9.0","2025-09-29T12:54:21",{"id":229,"version":230,"summary_zh":79,"released_at":231},103864,"v6.8.1","2025-09-12T08:32:04",{"id":233,"version":234,"summary_zh":79,"released_at":235},103865,"v6.8.0","2025-09-10T10:43:35",{"id":237,"version":238,"summary_zh":79,"released_at":239},103866,"v6.7.2","2025-08-26T09:09:21",{"id":241,"version":242,"summary_zh":79,"released_at":243},103867,"v6.7.1","2025-08-12T09:34:57",{"id":245,"version":246,"summary_zh":79,"released_at":247},103868,"v6.7.0","2025-07-21T12:02:56",{"id":249,"version":250,"summary_zh":79,"released_at":251},103869,"v6.6.1","2025-06-13T09:40:46",{"id":253,"version":254,"summary_zh":79,"released_at":255},103870,"v6.6.0","2025-06-13T09:16:14"]