Course Overview
Step into the world of Generative AI and Large Language Models (LLMs) with this Complete Generative AI Mastery Course, an immersive, project-driven program designed to take you from fundamentals to professional-level mastery. In this Generative AI course, you will build production-grade AI applications using industry-standard frameworks such as LangChain, LLaMA 3, FAISS, and Milvus — the same technologies powering real-world enterprise and research-grade AI systems.
The course begins with a deep dive into the core concepts of Transformers, GANs, embeddings, and foundation models, helping you understand how modern generative models process and generate human-like content. You will then explore Retrieval-Augmented Generation (RAG), vector databases, and multimodal AI to create powerful, context-aware, and intelligent solutions for text, image, and video understanding.
Through 12+ guided, hands-on projects, you will build:
AI chatbots powered by LLMs
Intelligent document retrieval & RAG systems
Image generation & Vision AI applications
Semantic similarity search engines
AI-powered video retrieval systems
You will work with cutting-edge models and architectures, including T5 and multimodal models, while applying best practices for real-world system design.
By the end of this course, you will master the complete Generative AI pipeline — from data ingestion, embeddings, model chaining, fine-tuning, and optimization to scalable deployment across edge, cloud, and hybrid environments.
Whether you are a Python developer, AI enthusiast, data scientist, researcher, or tech innovator, this course equips you with the practical skills and deep technical understanding needed to design, build, and deploy next-generation LLM and Vision AI systems from scratch.
FAQ
FAQ area empty
Course curriculum
Chương 1 Introduction 1 bài · 3 phút
Chương 2 Meet Your Instructor 1 bài · 2 phút
Chương 3 Understanding AI – From Origins to Impact 1 bài · 11 phút
Chương 4 The Complete Detailed Roadmap of Deep learning 1 bài · 26 phút
Chương 5 The Complete Detailed Roadmap of Natural Language Processing (NLP) 1 bài · 10 phút
Chương 6 The Complete Detailed Roadmap of Generative AI (Gen Ai) 1 bài · 10 phút
-
The Complete Detailed Roadmap of Generative AI (Gen Ai) 10:25
Chương 7 Environment Setup for Python Development 2 bài · 3 phút
- Installing Python Học thử 1:27
-
VS Code Setup for Python Development 1:59
Chương 8 Project #1: Custom GAN Image Generation — Build & Train Your Own Model 2 bài · 32 phút
-
Part 1: Custom GAN Image Generation — Build & Train Your Own Model 14:01
-
Part 2: Custom GAN Image Generation — Build & Train Your Own Model 17:56
Chương 9 Project #2: Pre-trained GAN Image Generation — Deploy SOTA Model 1 bài · 7 phút
Chương 10 Project #3: Steganography with GAN – Hide Text in Images 3 bài · 37 phút
-
Part 1: GAN Based Text Hiding in Images Using Steganography 13:40
-
Part 2: GAN Based Text Hiding in Images Using Steganography 11:33
-
Part 3: GAN Based Text Hiding in Images Using Steganography 12:00
Chương 11 Detailed Overview of the Transformer Architecture 1 bài · 4 phút
-
Understanding the Transformer Architecture 3:33
Chương 12 Project #4 Build a Transformer from Scratch for Neural Machine Translation 5 bài · 51 phút
-
Transformer Basics –Input & Positional Embeddings 13:21
-
Understanding Layer Normalization & Feedforward Blocks In Transformers 10:57
-
Transformer Layer-Mutli Head Attention Explained 11:51
-
Transformer Training Techniques Explained 10:29
-
Inference with Trained Transformer Models 4:25
Chương 13 Project #5: Build a Chatbot with Gemma 2B – Model & Deployment 1 bài · 16 phút
-
Build a Chatbot with Gemma 2B – Model & Deployment 15:52
Chương 14 Project #6: Chat With Your Own Pdf Document Using BGE 1.5, Faiss & PHI-2 LLM 4 bài · 48 phút
-
RAG Explanation & BGE 1.5 Model Explanation 12:20
-
Faiss-Implementation & Key Concepts 8:57
-
PHI-2 Model-Implementation & Inference Code Explanation 12:04
-
Final Chat Implementation-BGE 1.5,Faiss & PHI-2 Code Execution 14:14
Chương 15 Project #7: RAG System with Llama-2 + LangChain + MPNet Embeddings 2 bài · 30 phút
-
Part 1: Build a RAG System with Llama-2, LangChain, and MPNet Embeddings 10:32
-
Part 2: Build a RAG System with Llama-2, LangChain, and MPNet Embeddings 19:28
Chương 16 Project #8: RAG Chatbot for Policy Documents (BGE + Faiss + Llama 3) 2 bài · 28 phút
-
RAG Project-BGE,Faiss & Llama-3 Project Explanation 10:42
-
RAG Project-BGE,Faiss & Llama-3 Code Explanation & Execution 17:27
Chương 17 Project #9: Stable Diffusion Image Generation – Code & Prompts 2 bài · 22 phút
-
Stable Diffusion-Code Implementation Explanation 11:10
-
Stable Diffusion-Code Execution with Prompts 10:24
Chương 18 Project #10: Image & Text Similarity Search with CLIP, Faiss & Milvus 4 bài · 44 phút
-
Image & Text Similarity Search-CLIP, Faiss & COCO Dataset 11:01
-
Image & Text Similarity Search – CLIP, Faiss & Inference on COCO Dataset 14:16
-
Image & Text Similarity –CLIP,Milvus & COCO Dataset 9:48
-
Image & Text Similarity – CLIP Embeddings, Milvus Indexing & Inference on COCO 8:48
Chương 19 Project #11: Smart Video Search System using VILA-2.0, T5 & Milvus 5 bài · 45 phút
-
Part 1: Smart Video Search System Using VILA-2.0 VLM Model, T5 & Milvus 10:38
-
Part 2: Smart Video Search System Using VILA-2.0 VLM Model, T5 & Milvus 9:08
-
Part 3: Smart Video Search System Using VILA-2.0 VLM Model, T5 & Milvus 9:10
-
Part 4: Smart Video Search System Using VILA-2.0 VLM Model, T5 & Milvus 6:59
-
Part 5: Smart Video Search System Using VILA-2.0 VLM Model, T5 & Milvus 9:19
Chương 20 Additional Concepts – Auto Encoders & Variational Auto Encoders 2 bài · 13 phút
-
Auto Encoders and Variable Auto Encoders Understanding 6:44
-
Understanding Auto Encoder Loss Function (MSE+BCE) 6:14
Chương 21 Additional – Project #12: Auto Encoder Image Denoising with TensorFlow & PyTorch 2 bài · 31 phút
-
Part 1: Auto Encoders Based Image Denoising with Tensorflow and Pytorch 19:40
-
Part 2: Auto Encoders Based Image Denoising with Tensorflow and Pytorch 10:50
Chương 22 Additional Project #13: Variable Auto Encoders Image Denoising Using PyTorch 2 bài · 25 phút
-
Part 1 : Variable Auto Encoders Based Image Denoising Using Pytorch 9:03
-
Part 2: Variable Auto Encoders Based Image Denoising Using Pytorch 15:53
Requirment
-
Basic Python programming knowledge is required. Know variables, data types, control flow, functions, and basic scripting to follow along with labs.
-
Windows PC or Laptop with 4GB+ RAM recommended. Ensure Windows OS is installed, there is sufficient disk space for datasets, and essential developer tools ready
-
A GPU is optional but highly recommended for faster training and real-time experiments; without one, expect much longer training duration and slower performance.
-
The projects and exercises were developed and tested on Windows systems; guides, scripts, and troubleshooting steps are tailored exclusively for Windows learners.
Outcomes
-
Understand the core concepts of Generative AI, including Transformers, GANs, Autoencoders, and RAG frameworks
-
Build end-to-end LLM applications using LangChain, Llama 3, BGE, and Faiss for text and document intelligence
-
Implement Retrieval-Augmented Generation (RAG) systems with vector databases like Milvus for contextual AI chatbots
-
Develop custom GAN models and use Stable Diffusion for realistic image generation and creative AI workflows
-
Master text-image similarity search with CLIP embeddings and large-scale vector indexing
-
Create multimodal AI systems combining text, image, and video understanding using VILA 2.0 and T5
-
Learn how to train, fine-tune, and deploy Generative AI models for real-world use cases
-
Understand transformer internals, including multi-head attention, positional embeddings, and feedforward blocks
-
Explore Autoencoders and Variational Autoencoders (VAE) for denoising, reconstruction, and latent-space learning
-
Build AI-powered applications like chatbots, video search systems, and intelligent assistants from scratch
-
Learn to integrate Faiss and Milvus for high-performance vector search and retrieval in production
-
Develop production-ready AI pipelines, covering embedding generation, inference optimization, and deployment
-
Gain hands-on experience through 12+ advanced projects blending theory with practical coding
-
Acquire job-ready AI engineering skills to design, build, and deploy scalable Generative AI solutions
0 Student
1 Course
0 review