Generative AI & Large Language Models (LLMs)
Learn how to build practical Generative AI & LLM applications using prompt engineering, APIs, RAG, fine-tuning, and AI agents.
Course Overview
Course Modules Module 1: Introduction to Generative AI GenAI Overview History of Language Models GPT Architecture Transformer Model Deep-dive GenAI Use Cases Ethical Considerations Module 2: Working with LLM APIs OpenAI API Anthropic Claude API Prompt Engineering Few-shot & Zero-shot Learning Temperature & Sampling API Rate Limits & Costs Module 3: RAG & Knowledge Bases Retrieval-Augmented Generation Vector Databases Embedding Models Semantic Search LlamaIndex & LangChain Knowledge Base Design Module 4: Fine-tuning & Customization When to Fine-tune Dataset Preparation LoRA & QLoRA Hugging Face Transformers Evaluation Metrics RLHF Basics Module 5: Building GenAI Applications AI Chatbots Document Summarization Code Generation Tools Image Generation (DALL-E, Stable Diffusion) AI Agents & Tools Production Deployment Module 6: Capstone Project Use Case Definition Architecture Planning LLM Integration RAG Implementation Evaluation & Testing Demo Presentation Capstone Project Build and deploy a production-ready GenAI application leveraging LLMs, RAG, and external APIs.
Learning Outcomes
Understand transformer architecture and LLM capabilities.
Implement prompt engineering techniques effectively.
Build RAG systems with vector databases.
Fine-tune models for domain-specific applications.
Deploy GenAI applications to production environments.
Prerequisites
Participants should have: Python programming experience Foundational understanding of machine learning API usage familiarity
Enterprise Learning
Tailored learning experiences for enterprises, institutions, and professional cohorts.