https://i125.fastpic.org/big/2025/0630/e3/bbcc4ad26e9f40719605652cba59b1e3.avif
Free Download Udemy - Become An Llm & Agentic Ai Engineer 14-Day Bootcamp - 2025
Published 5/2025
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 26.29 GB | Duration: 24h 7m
Master Large Language Models, Hugging Face, AutoGen, CrewAI, LangChain, N8N, OpenAI Agents SDK, LangGraph, Gradio, & MCP
What you'll learn
Understand the foundations of Large Language Models (LLMs) and Agentic AI, including how LLMs are trained, fine-tuned, and deployed.
Create and deploy intelligent autonomous AI agents using cutting-edge frameworks like AutoGen, OpenAI Agents SDK, LangGraph, n8n, and MCP.
Explore and benchmark open-source LLMs such as LLama, DeepSeek, Qwen, Phi, and Gemma using Hugging Face and LM Studio.
Develop real-world applications using API access to OpenAI, Gemini, and Claude for text generation and vision tasks.
Apply a proven 5-step framework to select the right AI model for your business: maximizing cost-efficiency, minimizing latency, & accelerating time to market.
Evaluate LLMs using leaderboards like Vellum and Chat Arena, and conduct blind tests to objectively assess AI model performance.
Design Retrieval-Augmented Generation (RAG) pipelines using LangChain, OpenAI embeddings, & ChromaDB for efficient document retrieval & question answering.
Build an interactive, transparent AI-powered Q&A system with a Gradio interface that displays answers along with source citations for enhanced user trust.
Master data validation & structured output generation using the Pydantic library, including BaseModel, type hints, & parsed output creation from OpenAI models.
Build an AI-powered resume editor that analyzes gaps between a resume & job description & automatically tailors resumes/cover letters for targeted applications.
Learn how to fine-tune pre-trained open-source LLMs using parameter-efficient methods like LoRA and tools such as Hugging Face's TRL and SFTTrainer.
Master dataset preparation and model evaluation techniques, including calculating accuracy, precision, recall, and F1-score using scikit-learn.
Apply key components in Hugging Face Transformers library such as pipeline( ), AutoTokenizer( ), and AutoModelForCausalLM( ).
Gain practical experience working with open-source datasets/models on Hugging Face, & apply quantization techniques like bitsandbytes to optimize Performance.
Master advanced prompt engineering techniques such as zero-shot, few-shot, and chain-of-thought prompting.
Deploy multi-model AI agents using AutoGen, integrating LLMs from OpenAI, Gemini, & Claude, enabling agent collaboration & human-in-the-loop oversight.
Develop and deploy agentic AI workflows using LangGraph, mastering concepts like states, edges, conditional logic, and multi-stage nodes.
Design & build AI-powered booking agents using LangGraph, enabling automated search & recommendation of flights & hotels through integration with external APIs.
Build a data science agent team using CrewAI, creating specialized agents for workflow planning, data analysis, model building, and predictive analytics.
Design and automate end-to-end Agentic AI workflows using n8n, integrating services like Gmail, Google Sheets, Google Calendar, and OpenAI.
Build an advanced AI tutor system using Model-Context-Protocol (MCP) and OpenAI Agents SDK, enabling dynamic tool interoperability.
Requirements
You will need a laptop and an internet connection!
No programming experience required; basic Python skills are a plus.
Description
The AI revolution is accelerating at an unimaginable pace, and those who master Large Language Models (LLMs) and Agentic AI will define the future of technology. The "Become an LLM & Agentic AI Engineer Bootcamp" is an intensive, 14-day hands-on program designed to equip professionals and enthusiasts with the skills needed to build real-world AI applications. Whether you're a developer, data scientist, researcher, or technology leader, this bootcamp provides the tools and knowledge to navigate and innovate in this fast-evolving space confidently.You will begin by exploring the foundations of LLMs and agent frameworks, including how to benchmark models using LM Studio. The course then guides you through working with powerful closed-source APIs from providers like OpenAI, Gemini, and Claude. You will learn how to structure system and user messages, understand tokenization, and control outputs to build projects such as AI-powered text generators and vision-enabled calorie trackers.As you advance, you'll dive into the world of open-source LLMs. You will fine-tune models on Hugging Face using state-of-the-art techniques like LoRA and Parameter-Efficient Fine-Tuning (PEFT). Alongside this, you'll gain experience designing AI-powered web applications using Gradio, creating interactive streaming apps, and building intelligent AI tutors.A core component of the bootcamp focuses on mastering prompt engineering, including zero-shot, few-shot, and chain-of-thought prompting techniques to achieve consistent and controlled outputs. You'll also explore advanced capabilities such as building Retrieval-Augmented Generation (RAG) pipelines and working with embeddings for semantic search and knowledge retrieval.The program concludes with the development of next-generation AI agents. You will use frameworks like AutoGen, OpenAI Agents SDK, LangGraph, n8n, and MCP to create autonomous agents capable of interacting with external systems, APIs, and other digital tools. Each module emphasizes building practical, working projects that reinforce the learning objectives and prepare you for real-world deployment.This bootcamp is led by Dr. Ryan Ahmed, a highly experienced AI professor and educator who has taught over half a million learners globally. It is ideal for software engineers, data scientists, AI researchers, and technology professionals who want to break into the LLM and AI agent development space.The format of the program emphasizes project-based learning with step-by-step guidance, community interaction, and access to mentorship and continuous feedback. From Day 1, you'll be building real-world applications, positioning yourself at the forefront of this transformative field.Enroll today, and I look forward to seeing you inside!
Overview
Section 1: Welcome to the Bootcamp!
Lecture 1 Instructor Introduction and LLM in Action!
Lecture 2 Download the Bootcamp Materials
Lecture 3 Bootcamp Outline
Lecture 4 Key Success Tips
Section 2: -------PART A: CLOSED-SOURCE LLMs, GRADIO, & BENCHMARKING-------
Lecture 5 Welcome to Part A of the Bootcamp!
Section 3: Day 1: Develop a Character AI Chatbot Using OpenAI API
Lecture 6 Task 1. Character AI Chatbot Project Introduction & Key Learning Objectives
Lecture 7 Task 2. Download Anaconda and Configure OpenAI API
Lecture 8 Task 3. Our First Chat with OpenAI API
Lecture 9 ❓Practice Opportunity Question: Test OpenAI API for Text Generation
Lecture 10 Practice Opportunity Solution: Test OpenAI API for Text Generation
Lecture 11 Task 4. Understand OpenAI API response Structure & Token Usage
Lecture 12 ❓Practice Opportunity Question: OpenAI Tokenizer Tool
Lecture 13 Practice Opportunity Solution: OpenAI Tokenizer Tool
Lecture 14 Task 5. Giving Our AI Chatbot a Personality Using the System Message!
Lecture 15 ❓Practice Opportunity Question: Changing AI Personalities
Lecture 16 Practice Opportunity Solution: Changing AI Personalities
Lecture 17 Conclusion, Summary, and Thank You!
Section 4: Day 2: Build an AI Calorie Tracker Using OpenAI API (Vision GPTs)
Lecture 18 Task 1. AI Calorie Tracker Project Introduction & Key Learning Objectives
Lecture 19 Task 2. Read a Sample Image Using Python's Pillow (PIL) Library
Lecture 20 ❓Practice Opportunity Question: Read & View Images Using PIL
Lecture 21 Practice Opportunity Solution: Read & View Images Using PIL
Lecture 22 Task 3. Understand Prompt Engineering Fundamentals
Lecture 23 ❓Practice Opportunity Question: Prompt Engineering Fundamentals
Lecture 24 Practice Opportunity Solution: Prompt Engineering Fundamentals
Lecture 25 Task 4. Perform Image Recognition Using OpenAI API's Vision GPT Models (Part A)
Lecture 26 Task 4. Perform Image Recognition Using OpenAI API's Vision GPT Models (Part B)
Lecture 27 ❓Practice Opportunity Question: Calling OpenAI API's Vision GPT Models
Lecture 28 Practice Opportunity Solution: Calling OpenAI API's Vision GPT Models
Lecture 29 Task 5. Obtain the Calorie Count of Food Images Using Vision GPT Models
Lecture 30 ❓Practice Opportunity Question: Expand API Payload to include Nutritional Value
Lecture 31 Practice Opportunity Solution: Expand API Payload to include Nutritional Value
Lecture 32 Conclusion, Summary, & Thank You Message!
Section 5: Day 3: Build an Adaptive LLM/AI Tutor with Gradio for Multi-level Learning
Lecture 33 Task 1. Introduction & Key Learning Objectives - Adaptive AI Tutor with Gradio
Lecture 34 Task 2. Learn Gradio 101 & Showcase Capabilities (Maps, Images, & Streaming)
Lecture 35 Task 3. Build and Test an AI Tutor Function (Without Gradio)
Lecture 36 ❓Practice Opportunity Question: Test AI Tutor Function with Many Personalities
Lecture 37 Practice Opportunity Solution: Test AI Tutor Function with Many Personalities
Lecture 38 Task 4. Build an Interactive Interface Using Gradio (No Streaming)
Lecture 39 ❓Practice Opportunity Question: Configure Gradio Interface Components
Lecture 40 Practice Opportunity Solution: Configure Gradio Interface Components
Lecture 41 Task 5. Add Streaming for an Enhanced Chat Experience in Gradio
Lecture 42 ❓Practice Opportunity Question: Streaming for an Enhanced Chat Experience
Lecture 43 Practice Opportunity Solution: Streaming for an Enhanced Chat Experience
Lecture 44 Task 6. Build a Multi-Level AI Tutor in Gradio with Explanation Level Slider
Lecture 45 ❓Practice Opportunity Question: Testing AI Tutor Slider Levels & Einstein Mode!
Lecture 46 Practice Opportunity Solution: Testing AI Tutor Slider Levels & Einstein Mode!
Lecture 47 Conclusion, Summary, & Thank You Message!
Section 6: Day 4: Build Websites with Claude, Gemini, & OpenAI & LLMs Leaderboards
Lecture 48 Task 1. Introduction & Module Objectives - Build Websites & LLMs Leaderboards
Lecture 49 Task 2. LLM Comparison, Benchmarks, & Vellum Leaderboard
Lecture 50 ❓Practice Opportunity Question: Vellum Leaderboard & LLMs Benchmarking
Lecture 51 Practice Opportunity Solution: Vellum Leaderboard & LLMs Benchmarking
Lecture 52 Task 3. Exploring Chatbot Arena and Blind AI/LLMs Models Testing
Lecture 53 ❓Practice Opportunity Question: Blind AI Testing Using Chatbot Arena
Lecture 54 Practice Opportunity Solution: Blind AI Testing Using Chatbot Arena
Lecture 55 Task 4. Setup API Key & Compare Math & Creative abilities of Claude, Gemini, GPT
Lecture 56 ❓Practice Opportunity Question: Compare LLMs Coding Abilities
Lecture 57 Practice Opportunity Solution: Compare LLMs Coding Abilities
Lecture 58 Task 5. Define the Startup Idea & Structure the Prompt
Lecture 59 ❓Practice Opportunity Question: Prompt Structuring for HTML Generation
Lecture 60 Practice Opportunity Solution: Prompt Structuring for HTML Generation
Lecture 61 Task 6. Generate Websites & HTML Landing Pages with OpenAI API
Lecture 62 ❓Practice Opportunity Question: HTML Landing Pages Generation
Lecture 63 Practice Opportunity Solution: HTML Landing Pages Generation
Lecture 64 Task 7. Generate HTML Landing Pages with Google Gemini-2.0-Flash API
Lecture 65 ❓Practice Opportunity Question: Compare Gemini Vs. OpenAI Website Generation
Lecture 66 Practice Opportunity Solution: Compare Gemini Vs. OpenAI Website Generation
Lecture 67 Task 8. Generate HTML Landing Pages with Anthropic Claude 3.7 Sonnet
Lecture 68 ❓Practice Opportunity Question: Website Design with LLM (Claude by Anthropic)
Lecture 69 Practice Opportunity Solution: Website Design with LLM (Claude by Anthropic)
Lecture 70 Conclusion, Summary, & Thank You Message!
Section 7: -------PART B: OPEN-SOURCE LLMs, HUGGING FACE, RAG & FINE-TUNING-------
Lecture 71 Welcome to Part B of this Bootcamp!
Section 8: Day 5: Hugging Face Open-Source Models
Lecture 72 Task 1. Project Overview: Chat with Documents Using Open-Source LLMs
Lecture 73 Task 2. Explore Hugging Face Models, Datasets, and Spaces
Lecture 74 ❓Practice Opportunity Question: Explore Hugging Face
Lecture 75 Practice Opportunity Solution: Explore Hugging Face
Lecture 76 Task 3. Install Key Libraries & Setup Access Tokens for Hugging Face
Lecture 77 ❓Practice Opportunity Question: GPU Access Check on Google Colab
Lecture 78 Practice Opportunity Solution: GPU Access Check on Google Colab
Lecture 79 Task 4. Hugging Face Transformers Library: Pipelines
Lecture 80 ❓Practice Opportunity Question: Transformers Pipelines
Lecture 81 Practice Opportunity Solution: Transformers Pipelines
Lecture 82 Task 5. Hugging Face Transformers Library: AutoTokenizers
Lecture 83 ❓Practice Opportunity Question: Transformers Library AutoTokenizer
Lecture 84 Practice Opportunity Solution: Transformers Library AutoTokenizer
Lecture 85 Task 6. Hugging Face Transformers Library: AutoModelForCasualLM
Lecture 86 ❓Practice Opportunity Question: Transformers AutoModelForCasualLM
Lecture 87 Practice Opportunity Solution: Transformers AutoModelForCasualLM
Lecture 88 Task 7. Read PDF Documents & Extract Content Using PyPDF Library
Lecture 89 ❓Practice Opportunity Question: PyPDF Library
Lecture 90 Practice Opportunity Solution: PyPDF Library
Lecture 91 Task 8. Build the Q&A Logic & Prompt the LLM (Microsoft Phi-4-mini)
Lecture 92 ❓Practice Opportunity Question: Test the Q&A Pipeline with Open-Source LLM
Lecture 93 Practice Opportunity Solution: Test the Q&A Pipeline with Open-Source LLM
Lecture 94 Task 9. Switch LLMs (LLama, Phi, & Gemma) & Build Gradio Interface
Lecture 95 ❓Practice Opportunity Question: Testing Qwen Open-Source LLM
Lecture 96 Practice Opportunity Solution: Testing Qwen Open-Source LLM
Lecture 97 Conclusion & Thank You!
Section 9: Day 6: Reasoning Open-Source LLMs on Hugging Face & Model Leaderboards
Lecture 98 Task 1. Introduction and Module Objectives - Reasoning LLMs on Hugging Face
Lecture 99 Task 2. Explore Hugging Face Datasets Library & Install Key Libraries
Lecture 100 ❓Practice Opportunity Question: Explore Hugging Face Datasets
Lecture 101 Practice Opportunity Solution: Explore Hugging Face Datasets
Lecture 102 Task 3. Load Financial News Datasets from Hugging Face
Lecture 103 ❓Practice Opportunity Question: Explore Financial News Datasets
Lecture 104 Practice Opportunity Solution: Explore Financial News Datasets
Lecture 105 Task 4. Load and Test DeepSeek Reasoning Model - Part 1
Lecture 106 Task 4. Load and Test DeepSeek Reasoning Model - Part 2
Lecture 107 ❓Practice Opportunity Question: Test Math Capabilities of DeepSeek
Lecture 108 Practice Opportunity Solution: Test Math Capabilities of DeepSeek
Lecture 109 Task 5. A Framework for Choosing the right AI Model for Your Business - Part 1
Lecture 110 Task 5. A Framework for Choosing the right AI Model for Your Business - Part 2
Lecture 111 Task 6. Model Leaderboards and Old/New Model Benchmarks - Part 1
Lecture 112 Task 6. Model Leaderboards and Old/New Model Benchmarks - Part 2
Lecture 113 Task 7. Prompting DeepSeek for Reasoning and Classification
Lecture 114 ❓Practice Opportunity Question: Analyze News Sentiment with DeepSeek
Lecture 115 Practice Opportunity Solution: Analyze News Sentiment with DeepSeek
Lecture 116 Task 8. Building Gradio Interface
Lecture 117 Conclusion and Thank You!
Section 10: Day 7: Build Retrieval Augmented Generation (RAG) Pipelines in LangChain
Lecture 118 Task 1. Introduction & Module Objectives - Build RAG Pipelines in LangChain
Lecture 119 Task 2. Understand Retrieval Augmented Generation (RAG) & Why Use it
Lecture 120 Task 3. LangChain 101 & Key Features
Lecture 121 Task 4. Setup, Gather RAG Tools & Load Datasets
Lecture 122 ❓Practice Opportunity Question: LangChain Textloader Testing
Lecture 123 Practice Opportunity Solution: LangChain Textloader Testing
Lecture 124 Task 5. Splitting (Chunking) Documents Using LangChain Text Splitter
Lectu
Видео
