Practical AI/ML tutorials, prompt engineering deep-dives, LLM agent walkthroughs, and generative AI project demos — built for students, developers, and AI engineers who want to go from concept to working code fast.
RAG #1
RAG Series · Video 1
A complete end-to-end RAG (Retrieval-Augmented Generation) series taking you from beginner concepts to production-ready systems. Covers vector databases, embeddings, chunking strategies, hybrid search, re-ranking, and advanced RAG architectures used in real-world AI applications.
RAG #2
RAG Series · Video 2
Build your first RAG pipeline from scratch. This video walks through the core components — document loading, chunking, embedding, vector storage, and retrieval — giving you a solid foundation to understand how production-grade RAG systems are constructed.
RAG #3
RAG Series · Video 3
Understand document loaders — the first step in any RAG pipeline. This video breaks down how loaders work, the different types available, and how to load PDFs, web pages, and other data sources into your RAG system in the simplest way possible.
RAG #4
RAG Series · Video 4
A deep dive into chunking strategies — one of the most critical decisions in any RAG pipeline. Covers fixed-size chunking, overlap chunking, and semantic chunking, with practical comparisons to help you choose the right strategy for your use case and data type.
RAG #5
RAG Series · Video 5
Discover how embedding optimization can dramatically improve your RAG system's accuracy. Learn how to choose the right embedding model, fine-tune embeddings for your domain, and avoid the common mistakes that silently kill retrieval performance.
RAG #6
RAG Series · Video 6
Learn how cosine similarity powers semantic search in RAG systems. This video explains different similarity search types, how vector distance metrics work, and why choosing the right similarity function directly impacts your retrieval quality.
EP. 1
10:29
Prompt Engineering Series · Video 1
Start your journey into Generative AI with a solid foundation in prompt engineering. This video covers the basics of how to write good prompts, why prompt structure matters, and how to get better outputs from LLMs like ChatGPT. Learn the core principles — good prompts, better outputs, smarter results — with real examples you can apply immediately.
EP. 2
18:21
Prompt Engineering Series · Video 2
Master zero-shot prompting — the technique that lets you get powerful answers from an LLM with no examples at all, just a clean, well-structured prompt. Learn how zero-shot prompting leverages the LLM's built-in knowledge, why simple input can produce powerful output, and how to ask anything and get fast, efficient results without hand-crafting examples. No examples. Just a prompt.
Next up: Few-Shot Prompting, Chain-of-Thought, and LLM Agent walkthroughs.
Subscribe to get notifiedYour browser can't preview PDFs inline.
⬇ Download Resume