Course Length
8 training hours
Course Overview
The fast pace of development in LLMs and related technologies, such as agentic AI, made it possible to use them even in enterprise grade applications. There are already a few areas where a new generation of LLM-based applications totally redefined applications' capabilities and users' expectations while AI technologies are going to radically change all kinds of other software areas as well.
That's why IT and other technical managers and professionals need to understand the technologies used in AI applications such as LLMs, RAG and agents.
Training Objectives
At the end of the training participants:
- • Recognize common LLM-based applications and understand their main building blocks.
- • Get a high-level understanding of how modern large language models (LLMs) work and how they are trained in multiple steps.
- • Explain the pros and cons of using LLMs via their APIs and via frameworks and be familiar with some popular open-source options.
- • Understand the main ideas behind prompt engineering, including practical tips and best practices for working effectively with modern LLMs.
- • Know the basics of RAG (Retrieval-Augmented Generation) systems, including their main parts, ways to improve their performance, and some new alternative solutions.
- • Understand the motivations for and the two main types of LLM-based agentic systems (workflows and autonomous agents) as well as the key components and the way of working of autonomous agents.
- • Recognize the importance and services of monitoring and evaluating LLM applications throughout their lifecycle as well as learning about some leading tools in this field (optional).
Main Topics
- • Introduction to LLM based applications: current types, building blocks, challenges
- • Why and how LLMs work and are trained?
- • Using closed- and open-source LLMs via APIs and app. development frameworks
- • Prompt engineering
- • "Talk with your documents": Retrieval Augmented Generation (RAG)
- • "AI that thinks and acts": LLM Agents
- • Quality Assurance at LLM apps: Tracing and Evaluation (optional)
Besides gaining a basic understanding of Large Language Models (LLMs) and other technologies used in LLM-based applications, students will be able to examine their features and play with them during instructor's demonstrations and lab exercises.
Structure
50% lecture, 50% demonstration by the instructor, students can do hands-on lab exercises outside of training hours
Target Audience
Technical managers and professionals who want to familiarize themselves with Large Language Models (LLMs) and LLM based applications.
Prerequisites
Basic understanding of IT concepts, User experience with ChatGPT or similar chatbots.
Course Modules
Module 1: Introduction to LLM based applications: current types, building blocks, challenges
- Main usage areas of LLM-based applications
- Main types of LLM-based applications
- Building blocks of LLM-based applications
- Demo: Popular LLM-based application types
Module 2: Why and how LLMs work and are trained?
- Main elements and operation of LLMs (tokenizer, embeddings, transformer, transformer head, next token selector)
- The 4+1 training phase of LLMs
- Most important LLM vendors and models
- Demo: LLMs before ChatGPT
Module 3: Using closed- and open-source LLMs directly via their APIs
- Using LLMs through APIs
- LLM API text generation modes
- Typical LLM parameters
- Demo: Using a closed-source and an open-source LLM via API
Module 4: Using LLMs via app. development frameworks
- What are LLM app. development frameworks
- Their advantages and disadvantages
- Case study: Langchain, the most popular framework
- Demo: Using LangChain in an LLM chatbot
Module 5: Prompt engineering
- What is prompt engineering?
- Golden rules of prompt engineering
- The "Just Ask" Principle, Zero-shot prompts
- Some important prompt engineering rules
- Demo: Demonstrating basic prompt techniques
Module 6: "Talk with your documents": Retrieval Augmented Generation (RAG)
- What is Retriever Augmented Generation (RAG)?
- How does RAG work?
- Main building blocks of an RAG pipeline
- Advanced RAG techniques
- Demo: Demonstration of Retrieval Augmented Generation (RAG) in an LLM app
Module 7: "AI that thinks and acts": LLM Agents
- Motivations for LLM-based Agentic Systems
- Main Features of and Difference between Workflows and Agents
- Main Building Blocks: Functions, Tools, Agents
- The ReAct autonomous agent execution logic
- Multi-agent systems
- Demo: Agentic workflow and agent
Module 8: Quality Assurance at LLM apps: Tracing and Evaluation (optional)
- Why do we need them during development?
- Tracing and evaluation tools for LLM-based apps
- Tracing basics
- Evaluation basics
- Demo: Langsmith Tracing and Evaluation