ai-engineering-hub

<p align="center">
  <a href="https://trendshift.io/repositories/12800">
    <img src="assets/TRENDING-BADGE.png" alt="Trending Badge" style="width: 250px; height: 55px;" width="250" height="55"/>
  </a>
</p>

<p align="center">
  <img src="assets/ai-eng-hub.gif" alt="AI Engineering Hub Banner">
</p>

---

# AI Engineering Hub 🚀

Welcome to the **AI Engineering Hub** - your comprehensive resource for learning and building with AI!

## 🌟 Why This Repo?

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

Whether you're a beginner, practitioner, or researcher, this repo provides resources for all skill levels to experiment and succeed in AI engineering.

---

## 📋 Table of Contents

- [Getting Started](#-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)

---

## 🎯 Getting Started

New to AI Engineering? Start here:

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

---

## 📬 Stay Updated with Our Newsletter!

**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)

[![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

### 🟢 Beginner Projects

Perfect for getting started with AI engineering. These projects focus on single components and straightforward implementations.

#### 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

#### 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

#### 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

#### 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

#### 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

---

### 🟡 Intermediate Projects

Multi-component systems, agentic workflows, and advanced features for experienced practitioners.

#### 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

#### 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

#### 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

#### 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

#### 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

#### 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

---

### 🔴 Advanced Projects

Complex systems, fine-tuning, production deployments, and cutting-edge implementations.

#### 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

#### 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) - Res