Course Outline
Day 1 – Generative AI & LLM Fundamentals
Overview of generative AI and common LLM use cases
Exploring transformer-based architectures (GPT, LLaMA, T5, etc.)
Understanding tokens, tokenization, and embeddings
Leveraging pre-trained models through APIs (OpenAI, Claude)
Utilizing open-source models via Hugging Face
Prompting basics: zero-shot and few-shot techniques
Hands-on session: prompt engineering in a Python notebook
Developing a simple LLM-powered application (CLI or web-based)
Addressing practical constraints: token limits, rate limits, and reliability fundamentals
Day 2 – RAG and Vector Search
The rationale behind RAG: merging LLMs with proprietary data
RAG architecture: ingest, index, retrieve, generate
Document preparation and chunking strategies for effective retrieval
Creating text embeddings via APIs or Hugging Face
Introduction to vector databases (e.g., Chroma, Pinecone)
Hands-on session: building a basic semantic search script
Hands-on session: developing a document Q&A system using RAG
Scaling ingestion and embedding workflows for larger datasets
Evaluating RAG trade-offs: chunk size, top-k selection, cost versus quality
Day 3 – Workflows, Agents, and Production
Defining AI agents and identifying suitable use cases
Introduction to LangGraph and graph-based LLM workflows
Hands-on session: constructing a simple LangGraph workflow with tools
Enhancing workflows with memory and multi-step reasoning
Integrating RAG with agents (agentic RAG)
Monitoring and evaluating LLM and RAG system performance
Deployment strategies for LLM applications (APIs, containers, services)
Cost optimization and performance tuning techniques
Ensuring safety, implementing guardrails, and promoting responsible usage
Capstone mini-project: delivering a comprehensive RAG/agent application demo
Requirements
Proficient Python programming skills and familiarity with APIs are required.
Intended Audience:
This course is designed for organizations aiming to transition from experimental phases to real-world LLM-driven solutions. It caters to software, backend, and full-stack engineers integrating LLMs into their products; data and machine learning engineers focusing on RAG, embeddings, and vector search; solution and enterprise architects developing LLM-based architectures; as well as technical product owners and engineering leaders responsible for evaluating AI use cases, costs, and risks.
Testimonials (2)
use of proper and effective prompt
Marses Pacaldo
Course - Generative AI and Prompt Engineering for Corporate Professionals
The interactive style, the exercises
