- Tutorials
- Courses
- Tracks
Generative AI, LLM & RAG - Skill Up
-1669185704.svg)
Generative AI & LLMs Course is a comprehensive, hands-on course designed to take learners from the foundations of Python programming all the way to cutting-edge concepts in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Prompt Engineering.
This 8-week intensive program combines theory, coding, and real-world projects to help learners gain both conceptual understanding and practical expertise.
Course Overview
Start your journey with Python programming essentials and gradually move into deep learning, NLP, transformers, and Hugging Face tools. Youll also explore the inner workings of LLMs, master prompt engineering strategies, and build production-grade AI systems with RAG and LangChain.
From implementing neural networks to fine-tuning large models and deploying AI-powered chatbots, this course provides a full-stack pathway into the world of generative AI.
Course Highlights
- Learn Python programming from scratch for AI/ML applications
- Get hands-on with NumPy, Pandas, Scikit-learn, TensorFlow, and PyTorch
- Build and train Neural Networks, RNNs, LSTMs, Transformers, and Autoencoders
- Master NLP tasks: tokenization, stop words, stemming, lemmatization, BoW, TF-IDF, embeddings
- Work with Generative AI architectures: Seq2Seq, Attention, Transformers, GPT, BERT
- Explore Hugging Face tools: models hub, datasets, pipelines, APIs
- Understand the internals of LLMs: parameters, scaling laws, fine-tuning (LoRA, QLoRA, PEFT), RLHF
- Dive deep into Prompt Engineering techniques and AI guardrails
- Learn RAG concepts with embeddings, vector databases, LangChain, and LangGraph
- Hands-on projects: News Article Categorizer, Multi-PDF Chatbot, Website+CSV Knowledge Bot, Full-Stack RAG QA Bot, and Final LLM App
Course Content
- Installation, Input/Output, Variables, Keywords
- Data Types, Operators, Conditional Statements
- Loops, Functions, Strings, Lists, Dictionaries, Tuples, Sets
- Collections, Comprehensions, OOPs
- Error & Exception Handling
- Advanced Python: Generators, Decorators, Context Managers
- Introduction to NumPy and Pandas
- What is AI? Generative vs. Discriminative Models
- Intro to Scikit-learn, TensorFlow, PyTorch
- Neural Networks Basics
- Text Preprocessing with NLTK: Tokenization, Stop Words, Stemming, Lemmatization
- NLP Tasks: Bag of Words, POS Tagging, NER
- Text Representations: TF-IDF, Word2Vec, GloVe
- Project: News Article Categorizer
- RNNs, LSTMs, GRUs
- Seq2Seq Models
- Autoencoders
- Transformer Architecture
- Self-Attention & Multi-Head Attention
- Positional Encoding, Encoder-Decoder Models, Latent Space
- Deepfakes, AI Bias & Responsible Use
- Introduction to Hugging Face
- Using Pretrained Models
- Models Hub & Model Cards
- Datasets Hub & APIs
- Pipeline Abstraction & Inference API
- Pretraining Objectives, GPT vs BERT
- Transfer Learning with Hugging Face
Pricing