diff --git a/README.md b/README.md index 6c65ab1..bea054c 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,9 @@ + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/patchy631/ai-engineering-hub) · [上游 README](https://github.com/patchy631/ai-engineering-hub/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 +

Trending Badge @@ -12,212 +18,212 @@ # AI Engineering Hub 🚀 -Welcome to the **AI Engineering Hub** - your comprehensive resource for learning and building with AI! +欢迎来到 **AI Engineering Hub** —— 你学习与构建 AI 应用的全面资源库！ -## 🌟 Why This Repo? +## 🌟 为什么选择本仓库？ -AI Engineering is advancing rapidly, and staying at the forefront requires both deep understanding and hands-on experience. Here, you will find: -- **93+ Production-Ready Projects** across all skill levels -- In-depth tutorials on **LLMs, RAG, Agents, and more** -- Real-world **AI agent** applications -- Examples to implement, adapt, and scale in your projects +AI Engineering（AI 工程）正在快速发展，要站在前沿既需要深入理解，也需要动手实践。在这里，你将找到： +- **93+ 个生产就绪项目**，覆盖各个技能水平 +- 关于 **LLM、RAG、Agent** 等的深度教程 +- 真实世界的 **AI agent** 应用案例 +- 可在你的项目中实现、改编和扩展的示例 -Whether you're a beginner, practitioner, or researcher, this repo provides resources for all skill levels to experiment and succeed in AI engineering. +无论你是初学者、实践者还是研究者，本仓库都为各个技能水平提供资源，助你在 AI 工程中实验并取得成功。 --- -## 📋 Table of Contents +## 📋 目录 -- [Getting Started](#-getting-started) +- [快速入门](#-getting-started) - [Newsletter](#-stay-updated-with-our-newsletter) -- [Projects by Difficulty](#-projects-by-difficulty) - - [Beginner Projects (22)](#-beginner-projects) - - [Intermediate Projects (48)](#-intermediate-projects) - - [Advanced Projects (23)](#-advanced-projects) -- [Contributing](#-contribute-to-the-ai-engineering-hub) -- [License](#-license) +- [按难度划分的项目](#-projects-by-difficulty) + - [初级项目 (22)](#-beginner-projects) + - [中级项目 (48)](#-intermediate-projects) + - [高级项目 (23)](#-advanced-projects) +- [参与贡献](#-contribute-to-the-ai-engineering-hub) +- [许可证](#-license) --- -## 🎯 Getting Started +## 🎯 快速入门 -New to AI Engineering? Start here: +刚接触 AI Engineering？从这里开始： -1. **Complete Beginners**: Check out the [AI Engineering Roadmap](./ai-engineering-roadmap) for a comprehensive learning path -2. **Learn the Basics**: Start with [Beginner Projects](#-beginner-projects) like OCR apps and simple RAG implementations -3. **Build Your Skills**: Move to [Intermediate Projects](#-intermediate-projects) with agents and complex workflows -4. **Master Advanced Concepts**: Tackle [Advanced Projects](#-advanced-projects) including fine-tuning and production systems +1. **完全零基础**：查看 [AI Engineering Roadmap](./ai-engineering-roadmap)，获取完整学习路径 +2. **学习基础**：从 [初级项目](#-beginner-projects) 入手，例如 OCR 应用和简单的 RAG 实现 +3. **提升技能**：进阶到 [中级项目](#-intermediate-projects)，涉及 agent 与复杂工作流 +4. **掌握高级概念**：挑战 [高级项目](#-advanced-projects)，包括微调与生产级系统 --- -## 📬 Stay Updated with Our Newsletter! +## 📬 订阅我们的 Newsletter，保持更新！ -**Get a FREE Data Science eBook** 📖 with 150+ essential lessons in Data Science when you subscribe to our newsletter! Stay in the loop with the latest tutorials, insights, and exclusive resources. [Subscribe now!](https://join.dailydoseofds.com) +**免费获取 Data Science 电子书** 📖 —— 订阅我们的 newsletter 即可获得，内含 150+ 门 Data Science 核心课程！随时掌握最新教程、见解与独家资源。[立即订阅！](https://join.dailydoseofds.com) [![Daily Dose of Data Science Newsletter](https://github.com/patchy631/ai-engineering/blob/main/resources/join_ddods.png)](https://join.dailydoseofds.com) --- -## 🎓 Projects by Difficulty +## 🎓 按难度划分的项目 -### 🟢 Beginner Projects +### 🟢 初级项目 -Perfect for getting started with AI engineering. These projects focus on single components and straightforward implementations. +非常适合 AI 工程入门。这些项目聚焦单一组件与直观实现。 #### OCR & Vision -- [**LaTeX OCR with Llama**](./LaTeX-OCR-with-Llama) - Convert LaTeX equation images to code using Llama 3.2 vision -- [**Llama OCR**](./llama-ocr) - 100% local OCR app with Llama 3.2 and Streamlit -- [**Gemma-3 OCR**](./gemma3-ocr) - Local OCR with structured text extraction using Gemma-3 -- [**Qwen 2.5 OCR**](./qwen-2.5VL-ocr) - Text extraction using Qwen 2.5 VL model +- [**LaTeX OCR with Llama**](./LaTeX-OCR-with-Llama) - 使用 Llama 3.2 vision 将 LaTeX 公式图片转换为代码 +- [**Llama OCR**](./llama-ocr) - 基于 Llama 3.2 与 Streamlit 的 100% 本地 OCR 应用 +- [**Gemma-3 OCR**](./gemma3-ocr) - 使用 Gemma-3 进行本地 OCR 与结构化文本提取 +- [**Qwen 2.5 OCR**](./qwen-2.5VL-ocr) - 使用 Qwen 2.5 VL 模型进行文本提取 #### Chat Interfaces & UI -- [**Local ChatGPT with DeepSeek**](./local-chatgpt%20with%20DeepSeek) - Mini-ChatGPT with DeepSeek-R1 and Chainlit -- [**Local ChatGPT with Llama**](./local-chatgpt) - ChatGPT clone using Llama 3.2 vision -- [**Local ChatGPT with Gemma 3**](./local-chatgpt%20with%20Gemma%203) - Local chat interface with Gemma 3 -- [**DeepSeek Thinking UI**](./deepseek-thinking-ui) - ChatGPT with visible reasoning using DeepSeek-R1 -- [**Qwen3 Thinking UI**](./qwen3-thinking-ui) - Thinking UI with Qwen3:4B and Streamlit -- [**GPT-OSS Thinking UI**](./gpt-oss-thinking-ui) - GPT-OSS with reasoning visualization -- [**Streaming AI Chatbot**](./streaming-ai-chatbot) - Real-time AI streaming with Motia framework +- [**Local ChatGPT with DeepSeek**](./local-chatgpt%20with%20DeepSeek) - 基于 DeepSeek-R1 与 Chainlit 的迷你 ChatGPT +- [**Local ChatGPT with Llama**](./local-chatgpt) - 使用 Llama 3.2 vision 的 ChatGPT 克隆版 +- [**Local ChatGPT with Gemma 3**](./local-chatgpt%20with%20Gemma%203) - 基于 Gemma 3 的本地聊天界面 +- [**DeepSeek Thinking UI**](./deepseek-thinking-ui) - 使用 DeepSeek-R1 展示可见推理过程的 ChatGPT +- [**Qwen3 Thinking UI**](./qwen3-thinking-ui) - 基于 Qwen3:4B 与 Streamlit 的 Thinking UI +- [**GPT-OSS Thinking UI**](./gpt-oss-thinking-ui) - 带推理可视化的 GPT-OSS +- [**Streaming AI Chatbot**](./streaming-ai-chatbot) - 基于 Motia 框架的实时 AI 流式对话 #### Basic RAG -- [**Simple RAG Workflow**](./simple-rag-workflow) - Basic RAG with LlamaIndex and Ollama -- [**Document Chat RAG**](./document-chat-rag) - Chat with documents using Llama 3.3 -- [**Fastest RAG Stack**](./fastest-rag-stack) - Fast RAG with SambaNova, LlamaIndex, and Qdrant -- [**GitHub RAG**](./github-rag) - Chat with GitHub repos locally -- [**ModernBERT RAG**](./modernbert-rag) - RAG with ModernBert embeddings -- [**Llama 4 RAG**](./llama-4-rag) - RAG powered by Meta's Llama 4 +- [**Simple RAG Workflow**](./simple-rag-workflow) - 使用 LlamaIndex 与 Ollama 的基础 RAG +- [**Document Chat RAG**](./document-chat-rag) - 使用 Llama 3.3 与文档对话 +- [**Fastest RAG Stack**](./fastest-rag-stack) - 基于 SambaNova、LlamaIndex 与 Qdrant 的快速 RAG +- [**GitHub RAG**](./github-rag) - 在本地与 GitHub 仓库对话 +- [**ModernBERT RAG**](./modernbert-rag) - 使用 ModernBert embeddings 的 RAG +- [**Llama 4 RAG**](./llama-4-rag) - 由 Meta 的 Llama 4 驱动的 RAG #### Multimodal & Media -- [**Image Generation with Janus-Pro**](./imagegen-janus-pro) - Local image generation with DeepSeek Janus-pro 7B -- [**Video RAG with Gemini**](./video-rag-gemini) - Chat with videos using Gemini AI +- [**Image Generation with Janus-Pro**](./imagegen-janus-pro) - 使用 DeepSeek Janus-pro 7B 进行本地图像生成 +- [**Video RAG with Gemini**](./video-rag-gemini) - 使用 Gemini AI 与视频对话 #### Other Tools -- [**Website to API with FireCrawl**](./Website-to-API-with-FireCrawl) - Convert websites to APIs -- [**AI News Generator**](./ai_news_generator) - News generation with CrewAI and Cohere -- [**Siamese Network**](./siamese-network) - Digit similarity detection on MNIST +- [**Website to API with FireCrawl**](./Website-to-API-with-FireCrawl) - 将网站转换为 API +- [**AI News Generator**](./ai_news_generator) - 使用 CrewAI 与 Cohere 生成新闻 +- [**Siamese Network**](./siamese-network) - 在 MNIST 上进行数字相似度检测 --- -### 🟡 Intermediate Projects +### 🟡 中级项目 -Multi-component systems, agentic workflows, and advanced features for experienced practitioners. +多组件系统、agentic 工作流与高级特性，适合有经验的实践者。 #### AI Agents & Workflows -- [**YouTube Trend Analysis**](./Youtube-trend-analysis) - Analyze YouTube trends with CrewAI and BrightData -- [**AutoGen Stock Analyst**](./autogen-stock-analyst) - Advanced analyst with Microsoft AutoGen -- [**Agentic RAG**](./agentic_rag) - RAG with document search and web fallback -- [**Agentic RAG with DeepSeek**](./agentic_rag_deepseek) - Enterprise agentic RAG with GroundX -- [**Book Writer Flow**](./book-writer-flow) - Automated book writing with CrewAI -- [**Content Planner Flow**](./content_planner_flow) - Content workflow with CrewAI Flow -- [**Brand Monitoring**](./brand-monitoring) - Automated brand monitoring system -- [**Hotel Booking Crew**](./hotel-booking-crew) - Multi-agent hotel booking with DeepSeek-R1 -- [**Deploy Agentic RAG**](./deploy-agentic-rag) - Private Agentic RAG API with LitServe -- [**Zep Memory Assistant**](./zep-memory-assistant) - AI Agent with human-like memory -- [**Agent with MCP Memory**](./agent-with-mcp-memory) - Agents with Graphiti memory and Opik -- [**ACP Code**](./acp-code) - Agent Communication Protocol demo -- [**Motia Content Creation**](./motia-content-creation) - Social media automation workflow +- [**YouTube Trend Analysis**](./Youtube-trend-analysis) - 使用 CrewAI 与 BrightData 分析 YouTube 趋势 +- [**AutoGen Stock Analyst**](./autogen-stock-analyst) - 基于 Microsoft AutoGen 的高级分析师 +- [**Agentic RAG**](./agentic_rag) - 支持文档搜索与网页回退的 RAG +- [**Agentic RAG with DeepSeek**](./agentic_rag_deepseek) - 基于 GroundX 的企业级 agentic RAG +- [**Book Writer Flow**](./book-writer-flow) - 使用 CrewAI 自动撰写书籍 +- [**Content Planner Flow**](./content_planner_flow) - 基于 CrewAI Flow 的内容工作流 +- [**Brand Monitoring**](./brand-monitoring) - 自动化品牌监测系统 +- [**Hotel Booking Crew**](./hotel-booking-crew) - 基于 DeepSeek-R1 的多 agent 酒店预订 +- [**Deploy Agentic RAG**](./deploy-agentic-rag) - 使用 LitServe 部署私有 Agentic RAG API +- [**Zep Memory Assistant**](./zep-memory-assistant) - 具备类人记忆的 AI Agent +- [**Agent with MCP Memory**](./agent-with-mcp-memory) - 集成 Graphiti 记忆与 Opik 的 Agent +- [**ACP Code**](./acp-code) - Agent Communication Protocol 演示 +- [**Motia Content Creation**](./motia-content-creation) - 社交媒体自动化工作流 #### Voice & Audio -- [**Real-time Voice Bot**](./real-time-voicebot) - Conversational travel guide with AssemblyAI -- [**RAG Voice Agent**](./rag-voice-agent) - Real-time RAG Voice Agent with Cartesia -- [**Chat with Audios**](./chat-with-audios) - RAG over audio files -- [**Audio Analysis Toolkit**](./audio-analysis-toolkit) - Audio analysis with AssemblyAI -- [**Multilingual Meeting Notes**](./multilingual-meeting-notes-generator) - Auto meeting notes with language detection +- [**Real-time Voice Bot**](./real-time-voicebot) - 基于 AssemblyAI 的对话式旅行向导 +- [**RAG Voice Agent**](./rag-voice-agent) - 基于 Cartesia 的实时 RAG Voice Agent +- [**Chat with Audios**](./chat-with-audios) - 面向音频文件的 RAG +- [**Audio Analysis Toolkit**](./audio-analysis-toolkit) - 使用 AssemblyAI 进行音频分析 +- [**Multilingual Meeting Notes**](./multilingual-meeting-notes-generator) - 支持语言检测的自动会议纪要 #### Advanced RAG -- [**RAG with Dockling**](./rag-with-dockling) - RAG over Excel with IBM's Docling -- [**Trustworthy RAG**](./trustworthy-rag) - RAG over complex docs with TLM -- [**Fastest RAG with Milvus and Groq**](./fastest-rag-milvus-groq) - Sub-15ms retrieval latency -- [**Chat with Code**](./chat-with-code) - Chat with code using Qwen3-Coder -- [**RAG SQL Router**](./rag-sql-router) - Agent with RAG and SQL routing +- [**RAG with Dockling**](./rag-with-dockling) - 使用 IBM 的 Docling 对 Excel 进行 RAG +- [**Trustworthy RAG**](./trustworthy-rag) - 使用 TLM 对复杂文档进行 RAG +- [**Fastest RAG with Milvus and Groq**](./fastest-rag-milvus-groq) - 亚 15ms 检索延迟 +- [**Chat with Code**](./chat-with-code) - 使用 Qwen3-Coder 与代码对话 +- [**RAG SQL Router**](./rag-sql-router) - 集成 RAG 与 SQL 路由的 Agent #### Multimodal -- [**DeepSeek Multimodal RAG**](./deepseek-multimodal-RAG) - MultiModal RAG with DeepSeek-Janus-Pro -- [**ColiVara Website RAG**](./Colivara-deepseek-website-RAG) - MultiModal RAG for websites -- [**Multimodal RAG with AssemblyAI**](./multimodal-rag-assemblyai) - Audio + vector database + CrewAI +- [**DeepSeek Multimodal RAG**](./deepseek-multimodal-RAG) - 基于 DeepSeek-Janus-Pro 的多模态 RAG +- [**ColiVara Website RAG**](./Colivara-deepseek-website-RAG) - 面向网站的多模态 RAG +- [**Multimodal RAG with AssemblyAI**](./multimodal-rag-assemblyai) - 音频 + 向量数据库 + CrewAI #### MCP (Model Context Protocol) -- [**Cursor Linkup MCP**](./cursor_linkup_mcp) - Custom MCP with deep web search -- [**EyeLevel MCP RAG**](./eyelevel-mcp-rag) - MCP for RAG over complex docs -- [**LlamaIndex MCP**](./llamaindex-mcp) - Local MCP client with LlamaIndex -- [**MCP Agentic RAG**](./mcp-agentic-rag) - MCP-powered Agentic RAG for Cursor -- [**MCP Agentic RAG Firecrawl**](./mcp-agentic-rag-firecrawl) - Agentic RAG with Firecrawl -- [**MCP Video RAG**](./mcp-video-rag) - Video RAG using Ragie via MCP -- [**MCP Voice Agent**](./mcp-voice-agent) - Voice agent with Firecrawl and Supabase -- [**SDV MCP**](./sdv-mcp) - Synthetic Data Vault orchestration -- [**KitOps MCP**](./kitops-mcp) - ML model management with KitOps -- [**Stagehand × MCP-Use**](./stagehand%20x%20mcp-use) - Web automation with Stagehand MCP +- [**Cursor Linkup MCP**](./cursor_linkup_mcp) - 支持深度网页搜索的自定义 MCP +- [**EyeLevel MCP RAG**](./eyelevel-mcp-rag) - 面向复杂文档的 MCP RAG +- [**LlamaIndex MCP**](./llamaindex-mcp) - 基于 LlamaIndex 的本地 MCP 客户端 +- [**MCP Agentic RAG**](./mcp-agentic-rag) - 面向 Cursor 的 MCP 驱动 Agentic RAG +- [**MCP Agentic RAG Firecrawl**](./mcp-agentic-rag-firecrawl) - 集成 Firecrawl 的 Agentic RAG +- [**MCP Video RAG**](./mcp-video-rag) - 通过 MCP 使用 Ragie 进行 Video RAG +- [**MCP Voice Agent**](./mcp-voice-agent) - 集成 Firecrawl 与 Supabase 的 Voice agent +- [**SDV MCP**](./sdv-mcp) - Synthetic Data Vault 编排 +- [**KitOps MCP**](./kitops-mcp) - 使用 KitOps 进行 ML 模型管理 +- [**Stagehand × MCP-Use**](./stagehand%20x%20mcp-use) - 基于 Stagehand MCP 的 Web 自动化 -#### Model Comparison & Evaluation -- [**Evaluation and Observability**](./eval-and-observability) - E2E RAG evaluation with CometML Opik -- [**Llama 4 vs DeepSeek-R1**](./llama-4_vs_deepseek-r1) - Compare models using RAG -- [**Qwen3 vs DeepSeek-R1**](./qwen3_vs_deepseek-r1) - Model comparison with Opik -- [**O3 vs Claude Code**](./o3-vs-claude-code) - Compare Claude 3.7 and o3 -- [**Sonnet4 vs O4**](./sonnet4-vs-o4) - Code generation comparison -- [**Sonnet4 vs Qwen3-Coder**](./sonnet4-vs-qwen3-coder) - Coder model comparison -- [**Code Model Comparison**](./code-model-comparison) - Frontier model code comparison -- [**GPT-OSS vs Qwen3**](./gpt-oss-vs-qwen3) - Reasoning capabilities comparison +#### 模型对比与评估 +- [**评估与可观测性（Evaluation and Observability）**](./eval-and-observability) - 使用 CometML Opik 进行端到端 RAG 评估 +- [**Llama 4 vs DeepSeek-R1**](./llama-4_vs_deepseek-r1) - 使用 RAG 对比模型 +- [**Qwen3 vs DeepSeek-R1**](./qwen3_vs_deepseek-r1) - 使用 Opik 进行模型对比 +- [**O3 vs Claude Code**](./o3-vs-claude-code) - 对比 Claude 3.7 与 o3 +- [**Sonnet4 vs O4**](./sonnet4-vs-o4) - 代码生成对比 +- [**Sonnet4 vs Qwen3-Coder**](./sonnet4-vs-qwen3-coder) - Coder 模型对比 +- [**代码模型对比（Code Model Comparison）**](./code-model-comparison) - 前沿模型代码对比 +- [**GPT-OSS vs Qwen3**](./gpt-oss-vs-qwen3) - 推理能力对比 --- -### 🔴 Advanced Projects +### 🔴 高级项目 -Complex systems, fine-tuning, production deployments, and cutting-edge implementations. +复杂系统、微调、生产部署与前沿实现。 -#### Fine-tuning & Model Development -- [**DeepSeek Fine-tuning**](./DeepSeek-finetuning) - Fine-tune DeepSeek with Unsloth and Ollama -- [**Build Reasoning Model**](./Build-reasoning-model) - Build DeepSeek-R1-like reasoning models -- [**Attention Is All You Need Implementation**](./attention-is-all-you-need-impl) - Transformer architecture from scratch +#### 微调与模型开发 +- [**DeepSeek 微调（Fine-tuning）**](./DeepSeek-finetuning) - 使用 Unsloth 与 Ollama 微调 DeepSeek +- [**构建推理模型（Build Reasoning Model）**](./Build-reasoning-model) - 构建类 DeepSeek-R1 的推理模型 +- [**Attention Is All You Need 实现**](./attention-is-all-you-need-impl) - 从零实现 Transformer 架构 -#### Advanced Agent Systems -- [**NVIDIA Demo**](./nvidia-demo) - Documentation writer with CrewAI Flows and NVIDIA NIM -- [**Documentation Writer Flow**](./documentation-writer-flow) - Agentic documentation workflow -- [**Multi-Agent Deep Researcher**](./Multi-Agent-deep-researcher-mcp-windows-linux) - MCP-powered deep researcher -- [**Multiplatform Deep Researcher**](./multiplatform_deep_researcher) - Multi-platform research with BrightData -- [**Web Browsing Agent**](./web-browsing-agent) - Browser automation with CrewAI and Stagehand -- [**Paralegal Agent Crew**](./paralegal-agent-crew) - Intelligent paralegal with RAG -- [**FireCrawl Agent**](./firecrawl-agent) - Corrective RAG with web search fallback -- [**Context Engineering Workflow**](./context-engineering-workflow) - Research assistant with TensorLake and Zep -- [**Parlant Conversational Agent**](./parlant-conversational-agent) - Compliance-driven conversational agent -- [**Stock Portfolio Analysis Agent**](./stock-portfolio-analysis-agent) - Portfolio analysis with React frontend -- [**Guidelines vs Traditional Prompt**](./guidelines-vs-traditional-prompt) - Structured guidelines comparison +#### 高级智能体系统 +- [**NVIDIA Demo**](./nvidia-demo) - 使用 CrewAI Flows 与 NVIDIA NIM 的文档撰写工具 +- [**文档撰写流程（Documentation Writer Flow）**](./documentation-writer-flow) - 智能体式文档工作流 +- [**多智能体深度研究员（Multi-Agent Deep Researcher）**](./Multi-Agent-deep-researcher-mcp-windows-linux) - 基于 MCP 的深度研究员 +- [**多平台深度研究员（Multiplatform Deep Researcher）**](./multiplatform_deep_researcher) - 使用 BrightData 进行多平台研究 +- [**网页浏览智能体（Web Browsing Agent）**](./web-browsing-agent) - 使用 CrewAI 与 Stagehand 的浏览器自动化 +- [**法务助理智能体团队（Paralegal Agent Crew）**](./paralegal-agent-crew) - 结合 RAG 的智能法务助理 +- [**FireCrawl Agent**](./firecrawl-agent) - 带网页搜索回退的纠正式 RAG（Corrective RAG） +- [**上下文工程工作流（Context Engineering Workflow）**](./context-engineering-workflow) - 使用 TensorLake 与 Zep 的研究助手 +- [**Parlant 对话智能体（Parlant Conversational Agent）**](./parlant-conversational-agent) - 合规驱动的对话智能体 +- [**股票投资组合分析智能体（Stock Portfolio Analysis Agent）**](./stock-portfolio-analysis-agent) - 带 React 前端的投资组合分析 +- [**Guidelines vs 传统 Prompt**](./guidelines-vs-traditional-prompt) - 结构化指南对比 -#### Advanced MCP & Infrastructure -- [**MindsDB MCP**](./mindsdb-mcp) - Unified MCP for all data sources -- [**Financial Analyst DeepSeek**](./financial-analyst-deepseek) - MCP financial analysis workflow -- [**Graphiti MCP**](./graphiti-mcp) - Persistent memory with Zep's Graphiti -- [**Pixeltable MCP**](./pixeltable-mcp) - Unified multimodal data orchestration -- [**Ultimate AI Assistant**](./ultimate-ai-assitant-using-mcp) - Multi-MCP server interface +#### 高级 MCP 与基础设施 +- [**MindsDB MCP**](./mindsdb-mcp) - 面向所有数据源的统一 MCP +- [**Financial Analyst DeepSeek**](./financial-analyst-deepseek) - MCP 金融分析工作流 +- [**Graphiti MCP**](./graphiti-mcp) - 使用 Zep 的 Graphiti 实现持久化记忆 +- [**Pixeltable MCP**](./pixeltable-mcp) - 统一多模态数据编排 +- [**Ultimate AI Assistant**](./ultimate-ai-assitant-using-mcp) - 多 MCP 服务器接口 -#### Production Systems -- [**GroundX Document Pipeline**](./groundX-doc-pipeline) - World-class document processing -- [**NotebookLM Clone**](./notebook-lm-clone) - Full NotebookLM with RAG, citations, and podcasts +#### 生产系统 +- [**GroundX 文档流水线（Document Pipeline）**](./groundX-doc-pipeline) - 世界级文档处理 +- [**NotebookLM Clone**](./notebook-lm-clone) - 完整 NotebookLM，含 RAG、引用与播客 -#### Learning Resources -- [**AI Engineering Roadmap**](./ai-engineering-roadmap) - Complete guide from Python to production AI +#### 学习资源 +- [**AI 工程路线图（AI Engineering Roadmap）**](./ai-engineering-roadmap) - 从 Python 到生产级 AI 的完整指南 --- -## 📢 Contribute to the AI Engineering Hub! +## 📢 为 AI Engineering Hub 做贡献！ -We welcome contributors! Whether you want to add new tutorials, improve existing code, or report issues, your contributions make this community thrive. Here's how to get involved: +我们欢迎贡献者！无论你是想添加新教程、改进现有代码，还是报告问题，你的贡献都能让这个社区蓬勃发展。参与方式如下： -1. **Fork** the repository -2. Create a new branch for your contribution -3. Submit a **Pull Request** and describe the improvements +1. **Fork** 本仓库 +2. 为你的贡献创建新分支 +3. 提交 **Pull Request** 并说明改进内容 -Check out our [contributing guidelines](CONTRIBUTING.md) for more details. +更多详情请参阅我们的[贡献指南](CONTRIBUTING.md)。 --- -## 📜 License +## 📜 许可证 -This repository is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. +本仓库采用 MIT License 许可 — 详见 [LICENSE](LICENSE) 文件。 --- -## 💬 Connect +## 💬 联系 -For discussions, suggestions, and more, feel free to [create an issue](https://github.com/patchy631/ai-engineering/issues) or reach out directly! +欢迎讨论、提出建议等，可随时[创建 issue](https://github.com/patchy631/ai-engineering/issues))或直接联系我们！ **Happy Coding!** 🎉