[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"similar-EmbeddedLLM--JamAIBase":3,"tool-EmbeddedLLM--JamAIBase":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":75,"owner_avatar_url":76,"owner_bio":77,"owner_company":78,"owner_location":78,"owner_email":79,"owner_twitter":75,"owner_website":80,"owner_url":81,"languages":82,"stars":119,"forks":120,"last_commit_at":121,"license":122,"difficulty_score":10,"env_os":123,"env_gpu":124,"env_ram":124,"env_deps":125,"category_tags":136,"github_topics":137,"view_count":23,"oss_zip_url":78,"oss_zip_packed_at":78,"status":16,"created_at":157,"updated_at":158,"faqs":159,"releases":189},1238,"EmbeddedLLM\u002FJamAIBase","JamAIBase","The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.","JamAIBase 是一个开源的 AI 后端平台，旨在简化 AI 应用的构建与协作。它将嵌入式数据库（SQLite）和向量数据库（LanceDB）结合，支持检索增强生成（RAG）功能，并通过类似电子表格的直观界面和 REST API 提供便捷的操作体验。\n\n它解决了传统 AI 开发中数据管理复杂、流程配置繁琐的问题，让用户无需编写大量代码即可定义数据关系和目标，从而专注于业务逻辑本身。JamAIBase 支持动态生成数据、实时交互、知识存储和智能聊天等功能，适用于需要快速构建 AI 应用的开发者、研究人员以及对 AI 有一定了解的设计师。\n\n其独特之处在于采用声明式范式，用户只需说明“想要什么”，而无需关注“如何实现”。同时，它兼容多种主流大语言模型（如 GPT-4、Claude 3、Llama3），并能高效处理多模态数据。无论是实验不同提示词、训练模型还是评估输出，JamAIBase 都能提供流畅的协作体验，是 AI 应用开发的理想工具。","# JamAI Base\n\n![JamAI Base Cover](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FEmbeddedLLM_JamAIBase_readme_8ae930374083.png)\n\n\u003C!-- prettier-ignore-start -->\n![Linting](https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Factions\u002Fworkflows\u002Flint.yml\u002Fbadge.svg)\n![CI](https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg)\n\n> [!TIP]\n> [Explore our docs](#explore-the-documentation)\n\n\u003C!-- prettier-ignore-end -->\n\n## Overview\n\nJamAI Base is an open-source RAG (Retrieval-Augmented Generation) backend platform that integrates an embedded database (SQLite) and an embedded vector database (LanceDB) with managed memory and RAG capabilities. It features built-in LLM, vector embeddings, and reranker orchestration and management, all accessible through a convenient, intuitive, spreadsheet-like UI and a simple REST API.\n\n![JamAI Base Demo](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FEmbeddedLLM_JamAIBase_readme_e6caf0244b4f.webp)\n\n## Migration Guide from v1 to v2\n\nRefer to [Migration Guide](.\u002FMIGRATION_GUIDE.md)\n\n## Key Features\n\n- Embedded database (SQLite) and vector database (LanceDB)\n- Managed memory and RAG capabilities\n- Built-in LLM, vector embeddings, and reranker orchestration\n- Intuitive spreadsheet-like UI\n- Simple REST API\n\n### Generative Tables\n\nTransform static database tables into dynamic, AI-enhanced entities.\n\n- **Dynamic Data Generation**: Automatically populate columns with relevant data generated by LLMs.\n- **Built-in REST API Endpoint**: Streamline the process of integrating AI capabilities into applications.\n\n### Action Tables\n\nFacilitate real-time interactions between the application frontend and the LLM backend.\n\n- **Real-Time Responsiveness**: Provide a responsive AI interaction layer for applications.\n- **Automated Backend Management**: Eliminate the need for manual backend management of user inputs and outputs.\n- **Complex Workflow Orchestration**: Enable the creation of sophisticated LLM workflows.\n\n### Knowledge Tables\n\nAct as repositories for structured data and documents, enhancing the LLM’s contextual understanding.\n\n- **Rich Contextual Backdrop**: Provide a rich contextual backdrop for LLM operations.\n- **Enhanced Data Retrieval**: Support other generative tables by supplying detailed, structured contextual information.\n- **Efficient Document Management**: Enable uploading and synchronization of documents and data.\n\n### Chat Tables\n\nSimplify the creation and management of intelligent chatbot applications.\n\n- **Intelligent Chatbot Development**: Simplify the development and operational management of chatbots.\n- **Context-Aware Interactions**: Enhance user engagement through intelligent and context-aware interactions.\n- **Seamless Integration**: Integrate with Retrieval-Augmented Generation (RAG) to utilize content from any Knowledge Table.\n\n### LanceDB Integration\n\nEfficient management and querying of large-scale multi-modal data.\n\n- **Optimized Data Handling**: Store, manage, query, and retrieve embeddings on large-scale multi-modal data efficiently.\n- **Scalability**: Ensure optimal performance and seamless scalability.\n\n### Declarative Paradigm\n\nFocus on defining \"what\" you want to achieve rather than \"how\" to achieve it.\n\n- **Simplified Development**: Allow users to define relationships and desired outcomes.\n- **Non-Procedural Approach**: Eliminate the need to write procedures.\n- **Functional Flexibility**: Support functional programming through LLMs.\n\n## Key Benefits\n\n### Ease of Use\n\n- **Interface**: Simple, intuitive spreadsheet-like interface.\n- **Focus**: Define data requirements through natural language prompts.\n\n### Scalability\n\n- **Foundation**: Built on LanceDB, an open-source vector database designed for AI workloads.\n- **Performance**: Serverless design ensures optimal performance and seamless scalability.\n\n### Flexibility\n\n- **LLM Support**: Supports any LLMs, including OpenAI GPT-4, Anthropic Claude 3, and Meta Llama3.\n- **Capabilities**: Leverage state-of-the-art AI capabilities effortlessly.\n\n### Declarative Paradigm\n\n- **Approach**: Define the \"what\" rather than the \"how.\"\n- **Simplification**: Simplifies complex data operations, making them accessible to users with varying levels of technical expertise.\n\n### Innovative RAG Techniques\n\n- **Effortless RAG**: Built-in RAG features, no need to build the RAG pipeline yourself.\n- **Query Rewriting**: Boosts the accuracy and relevance of your search queries.\n- **Hybrid Search & Reranking**: Combines keyword-based search, structured search, and vector search for the best results.\n- **Structured RAG Content Management**: Organizes and manages your structured content seamlessly.\n- **Adaptive Chunking**: Automatically determines the best way to chunk your data.\n- **BGE M3-Embedding**: Leverages multi-lingual, multi-functional, and multi-granular text embeddings for free.\n\n## Getting Started\n\n### Option 1: Use the JamAI Base Cloud\n\n[Sign up for a free account!](https:\u002F\u002Fcloud.jamaibase.com\u002F) Did we mention that you can get free LLM tokens?\n\n### Option 2: Launch self-hosted services\n\n[Follow our step-by-step guide.](https:\u002F\u002Fdocs.jamaibase.com\u002Fsdk\u002Fpython-sdk-documentation#oss)\n\n### Explore the Documentation:\n\n- [SDK and Platform Documentation](https:\u002F\u002Fdocs.jamaibase.com)\n- [API Documentation](https:\u002F\u002Fjamaibase.readme.io)\n- [Changelog](CHANGELOG.md)\n- [Versioning](VERSIONING.md)\n\n## Examples\n\nWant to try building apps with JamAI Base? We've got some awesome examples to get you started! Check out our [example docs](https:\u002F\u002Fdocs.jamaibase.com\u002Fgetting-started\u002Fuse-case) for inspiration.\n\nHere are a couple of cool frontend examples:\n\n1. [Simple Chatbot Bot using NLUX](https:\u002F\u002Fdocs.jamaibase.com\u002Fgetting-started\u002Fquick-start\u002Fnlux-frontend-only): Build a basic chatbot without any backend setup. It's a great way to dip your toes in!\n2. [Simple Chatbot Bot using NLUX + Express.js](https:\u002F\u002Fdocs.jamaibase.com\u002Fgetting-started\u002Fquick-start\u002Fnlux-+-express.js): Take it a step further and add some backend power with Express.js.\n3. [Simple Chatbot Bot using Streamlit](https:\u002F\u002Fdocs.jamaibase.com\u002Fsdk\u002Fpython-sdk-documentation#streamlit-chat-app): Are you a Python dev? Checkout this Streamlit demo!\n\nLet us know if you have any questions – we're here to help! Happy coding! 😊\n\n## Community and Support\n\nJoin our vibrant developer community for comprehensive documentation, tutorials, and resources:\n\n- **Discord**: [Join our Discord](https:\u002F\u002Fdiscord.gg\u002FrV6DECA8Dw)\n- **GitHub**: [Star our GitHub repository](https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase)\n\n## Contributing\n\nWe welcome contributions! Please read our [Contributing Guide](Contributing_Guide_Link) to get started.\n\n## License\n\nThis project is released under the Apache 2.0 License. - see the [LICENSE](https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fblob\u002Fmain\u002FLICENSE) file for details.\n\n## Contact\n\nFollow us on [X](https:\u002F\u002Fx.com\u002FEmbeddedLLM) and [LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fembedded-llm\u002F) for updates and news.\n","# JamAI Base\n\n![JamAI Base封面](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FEmbeddedLLM_JamAIBase_readme_8ae930374083.png)\n\n\u003C!-- prettier-ignore-start -->\n![代码检查](https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Factions\u002Fworkflows\u002Flint.yml\u002Fbadge.svg)\n![持续集成](https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Factions\u002Fworkflows\u002Fci.yml\u002Fbadge.svg)\n\n> [!TIP]\n> [浏览我们的文档](#浏览文档)\n\n\u003C!-- prettier-ignore-end -->\n\n## 概述\n\nJamAI Base 是一个开源的 RAG（检索增强生成）后端平台，集成了嵌入式数据库（SQLite）和嵌入式向量数据库（LanceDB），并具备内存管理和 RAG 功能。它内置了大语言模型、向量嵌入以及重排序器的编排与管理，所有功能均可通过便捷直观的电子表格式 UI 和简洁的 REST API 访问。\n\n![JamAI Base演示](https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FEmbeddedLLM_JamAIBase_readme_e6caf0244b4f.webp)\n\n## 从 v1 迁移到 v2 的迁移指南\n\n请参阅[迁移指南](.\u002FMIGRATION_GUIDE.md)\n\n## 主要特性\n\n- 嵌入式数据库（SQLite）和向量数据库（LanceDB）\n- 内存管理和 RAG 功能\n- 内置大语言模型、向量嵌入及重排序器编排\n- 直观的电子表格式 UI\n- 简单的 REST API\n\n### 生成表\n\n将静态数据库表转化为动态的、由 AI 增强的实体。\n\n- **动态数据生成**：自动用大语言模型生成的相关数据填充列。\n- **内置 REST API 端点**：简化将 AI 功能集成到应用程序中的流程。\n\n### 行动表\n\n促进应用程序前端与大语言模型后端之间的实时交互。\n\n- **实时响应性**：为应用程序提供响应迅速的 AI 交互层。\n- **自动化后端管理**：无需手动管理用户输入与输出的后端。\n- **复杂工作流编排**：支持创建复杂的大语言模型工作流。\n\n### 知识表\n\n作为结构化数据和文档的存储库，增强大语言模型的上下文理解能力。\n\n- **丰富的上下文背景**：为大语言模型的操作提供丰富的上下文背景。\n- **增强的数据检索**：通过提供详细、结构化的上下文信息，支持其他生成表。\n- **高效的文档管理**：支持文档和数据的上传与同步。\n\n### 聊天表\n\n简化智能聊天机器人应用程序的创建与管理。\n\n- **智能聊天机器人开发**：简化聊天机器人的开发与运营管理。\n- **上下文感知的交互**：通过智能且上下文感知的交互提升用户参与度。\n- **无缝集成**：可与检索增强生成（RAG）集成，以利用任何知识表中的内容。\n\n### LanceDB 集成\n\n高效管理和查询大规模多模态数据。\n\n- **优化的数据处理**：高效存储、管理、查询和检索大规模多模态数据的嵌入。\n- **可扩展性**：确保最佳性能与无缝扩展。\n\n### 声明式范式\n\n专注于定义“想要实现什么”，而非“如何实现”。\n\n- **简化开发**：允许用户通过自然语言提示定义关系和期望结果。\n- **非过程式方法**：无需编写过程。\n- **函数式灵活性**：通过大语言模型支持函数式编程。\n\n## 主要优势\n\n### 易用性\n\n- **界面**：简单、直观的电子表格式界面。\n- **重点**：通过自然语言提示定义数据需求。\n\n### 可扩展性\n\n- **基础**：基于 LanceDB 构建，这是一种专为 AI 工作负载设计的开源向量数据库。\n- **性能**：无服务器设计确保最佳性能与无缝扩展。\n\n### 灵活性\n\n- **大语言模型支持**：支持任何大语言模型，包括 OpenAI GPT-4、Anthropic Claude 3 和 Meta Llama3。\n- **能力**：轻松利用最先进的 AI 能力。\n\n### 声明式范式\n\n- **方法**：定义“想要什么”而非“如何实现”。\n- **简化**：简化复杂的数据操作，使不同技术水平的用户都能轻松使用。\n\n### 创新的 RAG 技术\n\n- **轻松的 RAG**：内置 RAG 功能，无需自行搭建 RAG 流水线。\n- **查询重写**：提升搜索查询的准确性和相关性。\n- **混合搜索与重排序**：结合关键词搜索、结构化搜索和向量搜索，以获得最佳结果。\n- **结构化 RAG 内容管理**：无缝组织和管理您的结构化内容。\n- **自适应分块**：自动确定最佳的数据分块方式。\n- **BGE M3 嵌入**：免费使用多语言、多功能、多粒度的文本嵌入。\n\n## 入门指南\n\n### 方案一：使用 JamAI Base 云服务\n\n[注册免费账户！](https:\u002F\u002Fcloud.jamaibase.com\u002F) 我们提到过您可以获得免费的大语言模型令牌吗？\n\n### 方案二：启动自托管服务\n\n[按照我们的分步指南操作。](https:\u002F\u002Fdocs.jamaibase.com\u002Fsdk\u002Fpython-sdk-documentation#oss)\n\n### 浏览文档：\n\n- [SDK 和平台文档](https:\u002F\u002Fdocs.jamaibase.com)\n- [API 文档](https:\u002F\u002Fjamaibase.readme.io)\n- [更新日志](CHANGELOG.md)\n- [版本控制](VERSIONING.md)\n\n## 示例\n\n想尝试用 JamAI Base 构建应用吗？我们有一些超棒的示例供您入门！请查看我们的[示例文档](https:\u002F\u002Fdocs.jamaibase.com\u002Fgetting-started\u002Fuse-case)获取灵感。\n\n这里有几个很酷的前端示例：\n\n1. [仅使用 NLUX 的简易聊天机器人](https:\u002F\u002Fdocs.jamaibase.com\u002Fgetting-started\u002Fquick-start\u002Fnlux-frontend-only)：无需任何后端设置即可构建一个基本聊天机器人。这是个很好的入门方式！\n2. [使用 NLUX + Express.js 的简易聊天机器人](https:\u002F\u002Fdocs.jamaibase.com\u002Fgetting-started\u002Fquick-start\u002Fnlux-+-express.js)：更进一步，使用 Express.js 添加一些后端功能。\n3. [使用 Streamlit 的简易聊天机器人](https:\u002F\u002Fdocs.jamaibase.com\u002Fsdk\u002Fpython-sdk-documentation#streamlit-chat-app)：您是 Python 开发者吗？快来看看这个 Streamlit 演示吧！\n\n如果您有任何问题，请随时联系我们——我们随时为您提供帮助！祝您编码愉快！😊\n\n## 社区与支持\n\n加入我们充满活力的开发者社区，获取全面的文档、教程和资源：\n\n- **Discord**：[加入我们的 Discord](https:\u002F\u002Fdiscord.gg\u002FrV6DECA8Dw)\n- **GitHub**：[给我们的 GitHub 仓库点赞](https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase)\n\n## 贡献\n\n我们欢迎贡献！请阅读我们的[贡献指南](Contributing_Guide_Link)开始参与。\n\n## 许可证\n\n本项目采用 Apache 2.0 许可证发布。详情请参阅[LICENSE](https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fblob\u002Fmain\u002FLICENSE)文件。\n\n## 联系方式\n\n关注我们在[X](https:\u002F\u002Fx.com\u002FEmbeddedLLM)和[LinkedIn](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Fembedded-llm\u002F)上的账号，获取最新动态与资讯。","# JamAIBase 快速上手指南\n\n## 环境准备\n\n### 系统要求\n\n- 操作系统：支持 Linux、macOS 或 Windows（推荐使用 Linux 或 macOS）\n- Python 版本：3.8 及以上\n- 网络连接：需要访问互联网以下载依赖项和模型\n\n### 前置依赖\n\n确保已安装以下工具：\n\n- Python 3.8+\n- pip (Python 包管理器)\n- Git (用于克隆代码仓库)\n\n建议使用国内镜像源加速依赖安装，例如使用 [清华源](https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002F)：\n\n```bash\npip install -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple \u003Cpackage_name>\n```\n\n---\n\n## 安装步骤\n\n### 1. 克隆仓库\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase.git\ncd JamAIBase\n```\n\n### 2. 安装依赖\n\n```bash\npip install -r requirements.txt\n```\n\n> 如果你在国内，可以使用以下命令加速安装：\n> ```bash\n> pip install -r requirements.txt -i https:\u002F\u002Fpypi.tuna.tsinghua.edu.cn\u002Fsimple\n> ```\n\n### 3. 启动服务\n\n```bash\npython main.py\n```\n\n默认情况下，服务将在 `http:\u002F\u002Flocalhost:8000` 上运行。\n\n---\n\n## 基本使用\n\n### 示例：创建一个简单的知识表并进行查询\n\n1. **通过 UI 创建知识表**  \n   打开浏览器，访问 `http:\u002F\u002Flocalhost:8000`，进入 JamAIBase 的 Web 界面。  \n   在“知识表”部分，创建一个新的表，并上传一些文档或结构化数据。\n\n2. **使用 REST API 查询知识表**  \n   使用 curl 或 Postman 发送请求：\n\n```bash\ncurl -X GET \"http:\u002F\u002Flocalhost:8000\u002Fapi\u002Fknowledge_tables\u002Fmy_table\u002Fquery?query=人工智能\"\n```\n\n这将返回与“人工智能”相关的知识内容。\n\n3. **创建一个简单的聊天机器人（Chat Table）**  \n   在 UI 中创建一个“聊天表”，并配置其使用上面的知识表作为 RAG 数据源。  \n   你可以通过 REST API 与聊天机器人交互：\n\n```bash\ncurl -X POST \"http:\u002F\u002Flocalhost:8000\u002Fapi\u002Fchat_tables\u002Fmy_chatbot\u002Fmessages\" \\\n     -H \"Content-Type: application\u002Fjson\" \\\n     -d '{\"message\": \"什么是人工智能？\"}'\n```\n\n---\n\n如需进一步了解功能细节，请参考官方文档：[JamAIBase 文档](https:\u002F\u002Fdocs.jamaibase.com)","某科技公司的产品团队正在开发一个智能客服系统，需要集成多个大型语言模型（LLM）并实时处理用户查询，同时确保数据的一致性和可追溯性。\n\n### 没有 JamAIBase 时\n\n- 开发人员需要手动编写复杂的后端逻辑来管理不同 LLM 的调用和响应，导致开发周期长且容易出错。\n- 数据存储和检索依赖于多个独立的数据库系统，难以统一管理和实时更新。\n- 实时交互功能需要额外搭建中间层服务，增加了系统的复杂性和维护成本。\n- 团队协作困难，不同成员对模型配置和数据流程的理解不一致，影响整体效率。\n- 缺乏直观的界面进行实验和调试，每次调整都需要重新部署整个系统。\n\n### 使用 JamAIBase 后\n\n- 开发人员可以通过直观的表格式界面快速定义模型调用流程和数据生成规则，大幅缩短开发时间。\n- 内置的 SQLite 和 LanceDB 支持统一管理结构化和向量化数据，实现高效的数据检索与更新。\n- 通过 Action Tables 实现前端与 LLM 后端的实时交互，无需额外搭建中间服务。\n- 团队成员可以在同一平台协作，共享模型配置、数据流程和实验结果，提升协作效率。\n- 提供 REST API 和动态数据生成功能，支持快速实验和调试，降低迭代成本。\n\nJamAIBase 让智能客服系统的开发更加高效、灵活，并显著提升了团队协作与数据管理能力。","https:\u002F\u002Foss.gittoolsai.com\u002Fimages\u002FEmbeddedLLM_JamAIBase_bef61927.png","EmbeddedLLM","https:\u002F\u002Foss.gittoolsai.com\u002Favatars\u002FEmbeddedLLM_5f436274.jpg","EmbeddedLLM is the creator behind JamAI Base, a platform designed to orchestrate AI with spreadsheet-like simplicity.",null,"info@embeddedLLM.com","https:\u002F\u002Fembeddedllm.com","https:\u002F\u002Fgithub.com\u002FEmbeddedLLM",[83,87,91,95,99,102,106,109,113,116],{"name":84,"color":85,"percentage":86},"Python","#3572A5",59.2,{"name":88,"color":89,"percentage":90},"Svelte","#ff3e00",25.4,{"name":92,"color":93,"percentage":94},"TypeScript","#3178c6",14,{"name":96,"color":97,"percentage":98},"HTML","#e34c26",0.4,{"name":100,"color":101,"percentage":98},"JavaScript","#f1e05a",{"name":103,"color":104,"percentage":105},"CSS","#663399",0.3,{"name":107,"color":108,"percentage":105},"Shell","#89e051",{"name":110,"color":111,"percentage":112},"Batchfile","#C1F12E",0,{"name":114,"color":115,"percentage":112},"HCL","#844FBA",{"name":117,"color":118,"percentage":112},"PowerShell","#012456",1090,41,"2026-04-04T18:23:19","Apache-2.0","Linux, macOS, Windows","未说明",{"notes":126,"python":127,"dependencies":128},"支持通过 REST API 和 UI 进行交互，推荐使用 Python SDK 开发应用，首次运行可能需要下载模型文件","3.8+",[129,130,131,132,133,134,135],"torch","transformers","accelerate","lancedb","sqlite","fastapi","uvicorn",[26,14,54,15,13],[138,139,140,141,142,132,143,144,145,146,147,148,149,150,151,152,153,154,155,156],"agents","ai","ai-agents-framework","baas","chatbot","llm","llm-ops","python","serverless","backend-as-a-service","chatgpt","orchestration","rag","retrieval-augmented-generation","workflow","svelte","spreadsheet","intelligent-spreadsheet","llama3-1","2026-03-27T02:49:30.150509","2026-04-06T05:15:15.751451",[160,165,170,175,180,185],{"id":161,"question_zh":162,"answer_zh":163,"source_url":164},5628,"如何解决在 Grammarly 编辑文本时，JamAIBase 的列修改被重置的问题？","在使用 Grammarly 编辑文本后，需要按 Enter 键确认单元格的值修改，否则修改内容会被重置。","https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fissues\u002F12",{"id":166,"question_zh":167,"answer_zh":168,"source_url":169},5629,"如何跟踪信用额度的使用情况？","目前系统可以在错误信息中显示具体哪种配额已用尽，但尚未提供完整的使用记录追踪功能。建议关注后续更新以获取更详细的使用记录。","https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fissues\u002F7",{"id":171,"question_zh":172,"answer_zh":173,"source_url":174},5630,"存储使用页面显示不准确，如何解决？","此问题将在下一个版本中修复，请等待更新后重新检查存储使用情况。","https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fissues\u002F6",{"id":176,"question_zh":177,"answer_zh":178,"source_url":179},5631,"如何解决在 Docker 拉取镜像时出现的访问被拒绝问题？","这些警告是正常的，因为镜像是通过本地 Dockerfile 构建的。只需继续执行构建过程，最终应能成功构建。","https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fissues\u002F24",{"id":181,"question_zh":182,"answer_zh":183,"source_url":184},5632,"如何在 JamAIBase 中实现项目重命名功能？","项目重命名功能已经实现，但行顺序调整功能暂未考虑，因为表格设计更偏向于数据库而非电子表格。","https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fissues\u002F10",{"id":186,"question_zh":187,"answer_zh":188,"source_url":169},5633,"如何在 billing 页面中查看信用额度的使用记录？","当前 billing 页面仅显示余额，不提供详细的使用记录。最新更新后，错误信息会提示具体哪种配额已耗尽，但完整的使用记录功能仍在开发中。",[190,195,200,205,210,215],{"id":191,"version":192,"summary_zh":193,"released_at":194},105273,"v0.4","## What's Changed (v0.4)\r\n\r\nThis is a huge release 🚀\r\n\r\n**✨ Main features:**\r\n\r\n* **Python Code Execution:**  Unlock powerful data manipulation directly within JamAIBase workflows with Python code execution in backend `GenTable` columns and Python SDK `CodeGenConfig`.\r\n* **Audio Data Type Support:**  JamAIBase now natively supports audio data, allowing you to work with `audio` data type in UI tables and process audio in backend `GenTable`.\r\n* **Enhanced Chat Mode:** Experience smoother chat interactions with the new multi-turn chat option in UI column settings.\r\n* **Function Calling for LLMs:** Extend LLM capabilities with function calling support in the backend.\r\n* **DeepSeek Model Support:** Expand your LLM options with integration of DeepSeek models.\r\n* **Improved File Handling:**  Benefit from audio file upload support and configurable file upload size limits for various file types.\r\n* **UI\u002FUX Improvements:** Enjoy enhanced column management, improved export options, security enhancements, and bug fixes in the UI.\r\n\r\n**⚠️ There are several breaking changes and deprecations as well, some highlights are listed here, see CHANGELOG for a complete list:**\r\n\r\n* **Backend (GenTable) - Breaking:** Add `Page` column to knowledge table.\r\n* **Backend (GenTable) - Breaking:** Change `file` data type to `image` data type.\r\n\r\n**Upgrade to v0.4 today to take advantage of these exciting new features and improvements!**\r\n\r\nWe encourage you to explore the new features and provide feedback. Thank you for being a part of the JamAIBase community!\r\n## Contributors\r\n\r\n* @Hoipang\r\n* @deafnv\r\n* @haoshan98\r\n* @kamil-hassan201\r\n* @noobHappylife\r\n* @jiahuei\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fcompare\u002Fv0.3.1...v0.4","2025-02-13T16:58:32",{"id":196,"version":197,"summary_zh":198,"released_at":199},105274,"v0.3.1","## Bug Fix\r\n\r\nThis is a bug fix release for frontend code to enable Projects for OSS. SDKs are not affected.\r\n\r\n## What's Changed (v0.3)\r\n\r\nThis is a huge release 🚀\r\n\r\nMain features:\r\n- Multimodal image input column: Now you can insert an image alongside text as input to LLMs\r\n- OSS now supports multiple projects: You are now able to create projects to manage your tables and files\r\n- Added ability to turn any column into multi-turn chat via the `multi_turn` parameter in `LLMGenConfig`\r\n- Added default prompts when creating Generative Tables: Setup time from table creation to running worlflows is now even shorter.\r\n- Support for search query when listing projects, tables, rows\r\n- Table and project import and export\r\n- Various improvements to backend and frontend\r\n\r\nThere are several breaking changes and deprecations as well, some highlights are listed here, see CHANGELOG for a complete list:\r\n- Added `version` and `meta` to table metadata. Please run the provided migration script to upgrade your existing DB files.\r\n- Delete endpoints will return 404 if resource is not found\r\n- `\u002Fv1\u002Fgen_tables\u002F{table_type}\u002F{table_id}\u002Fthread` has one new required query parameter: `column_id`\r\n- Table list endpoint now defaults to not counting table rows\r\n- Output columns must be string type\r\n- Deprecations:\r\n  - Endpoint `\u002Fv1\u002Fgen_tables\u002F{table_type}\u002Fduplicate\u002F{table_id_src}\u002F{table_id_dst}`\r\n\r\n## New Contributors\r\n\r\n* @zec0816\r\n* @Hoipang\r\n* @Jiaqi0602\r\n\r\n## Contributors\r\n\r\n* @deafnv\r\n* @haoshan98\r\n* @kamil-hassan201\r\n* @noobHappylife\r\n* @jiahuei\r\n\r\n## Full Changelog\r\n\r\nhttps:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fcompare\u002Fv0.2...v0.3.1\r\n","2024-11-26T16:34:08",{"id":201,"version":202,"summary_zh":203,"released_at":204},105275,"v0.3","## What's Changed\r\n\r\nThis is a huge release 🚀\r\n\r\nMain features:\r\n- Multimodal image input column: Now you can insert an image alongside text as input to LLMs\r\n- OSS now supports multiple projects: You are now able to create projects to manage your tables and files\r\n- Added ability to turn any column into multi-turn chat via the `multi_turn` parameter in `LLMGenConfig`\r\n- Added default prompts when creating Generative Tables: Setup time from table creation to running worlflows is now even shorter.\r\n- Support for search query when listing projects, tables, rows\r\n- Table and project import and export\r\n- Various improvements to backend and frontend\r\n\r\nThere are several breaking changes and deprecations as well, some highlights are listed here, see CHANGELOG for a complete list:\r\n- Added `version` and `meta` to table metadata. Please run the provided migration script to upgrade your existing DB files.\r\n- Delete endpoints will return 404 if resource is not found\r\n- `\u002Fv1\u002Fgen_tables\u002F{table_type}\u002F{table_id}\u002Fthread` has one new required query parameter: `column_id`\r\n- Table list endpoint now defaults to not counting table rows\r\n- Output columns must be string type\r\n- Deprecations:\r\n  - Endpoint `\u002Fv1\u002Fgen_tables\u002F{table_type}\u002Fduplicate\u002F{table_id_src}\u002F{table_id_dst}`\r\n\r\n## New Contributors\r\n\r\n* @zec0816\r\n* @Hoipang\r\n\r\n## Contributors\r\n\r\n* @deafnv\r\n* @haoshan98\r\n* @kamil-hassan201\r\n* @noobHappylife\r\n* @jiahuei\r\n\r\n## Full Changelog\r\n\r\nhttps:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fcompare\u002Fv0.2...v0.3\r\n","2024-11-21T13:23:06",{"id":206,"version":207,"summary_zh":208,"released_at":209},105276,"v0.2.1-python","## What's Changed\r\n\r\n- [Python] jamaibase: Bug fix: Table type is now correctly handled in Python > 3.10 by @jiahuei in https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fpull\u002F18\r\n\r\n\r\n**Full Changelog**: https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fcompare\u002Fv0.2...v0.2.1-python","2024-08-18T06:17:24",{"id":211,"version":212,"summary_zh":213,"released_at":214},105277,"v0.2","## What's Changed\r\n\r\nThis is a feature-packed release! Some of highlights include:\r\n- New \"Embeddings\" endpoint to generate vector embeddings for texts\r\n- Methods for importing and exporting table data via CSV or TSV\r\n- Ability to filter table rows when listing them by searching for keywords\r\n- Vastly reduced dependency list for Python SDK\r\n- Many other bug fixes and improvements\r\n\r\n## New Contributors\r\n\r\n* @eltociear made their first contribution in https:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fpull\u002F9\r\n* @Jiaqi0602\r\n* @wenjielee11\r\n\r\n## Contributors\r\n\r\n* @deafnv\r\n* @haoshan98\r\n* @iAmir97\r\n* @jiahuei\r\n* @kamil-hassan201\r\n* @noobHappylife\r\n* @tjtanaa \r\n\r\n## Full Changelog\r\n\r\nhttps:\u002F\u002Fgithub.com\u002FEmbeddedLLM\u002FJamAIBase\u002Fcompare\u002Fv0.1...v0.2","2024-07-23T09:48:37",{"id":216,"version":217,"summary_zh":218,"released_at":219},105278,"v0.1","This is our first release 🚀 We are excited to see what you can build with JamAIBase ✨\r\nIt includes backend services that orchestrates Large Language Models (LLMs) via a real-time database, and a frontend UI that allows easy data manipulation and visualization.","2024-06-03T01:40:57"]