Build Multi-Agent LLM Applications with AutoGen

Build Multi-Agent LLM Applications with AutoGen, available at Free, has an average rating of 3.88, with 19 lectures, based on 21 reviews, and has 853 subscribers.

You will learn about Define LLM agents and its various components Build multi-agent applications following different conversational patterns Integrate web scraping, external APIs and image capabilities in agents Create Retrieval Augment Generation (RAG) pipeline with AutoGen Implement Prompt Engineering techniques with LLM agents This course is ideal for individuals who are Data Scientists and Machine Learning Engineers who'd like to integrate LLMs in various use-cases or Software Engineers who need a hands-on guide to develop LLM-based multi-agent workflows or Architects who need a high-level understanding of what's possible with agentic workflows It is particularly useful for Data Scientists and Machine Learning Engineers who'd like to integrate LLMs in various use-cases or Software Engineers who need a hands-on guide to develop LLM-based multi-agent workflows or Architects who need a high-level understanding of what's possible with agentic workflows.

Enroll now: Build Multi-Agent LLM Applications with AutoGen

Summary

Title: Build Multi-Agent LLM Applications with AutoGen

Price: Free

Average Rating: 3.88

Number of Lectures: 19

Number of Published Lectures: 19

Number of Curriculum Items: 20

Number of Published Curriculum Objects: 20

Original Price: Free

Quality Status: approved

Status: Live

What You Will Learn

Define LLM agents and its various components
Build multi-agent applications following different conversational patterns
Integrate web scraping, external APIs and image capabilities in agents
Create Retrieval Augment Generation (RAG) pipeline with AutoGen
Implement Prompt Engineering techniques with LLM agents

Who Should Attend

Data Scientists and Machine Learning Engineers who'd like to integrate LLMs in various use-cases
Software Engineers who need a hands-on guide to develop LLM-based multi-agent workflows
Architects who need a high-level understanding of what's possible with agentic workflows

Target Audiences

Data Scientists and Machine Learning Engineers who'd like to integrate LLMs in various use-cases
Software Engineers who need a hands-on guide to develop LLM-based multi-agent workflows
Architects who need a high-level understanding of what's possible with agentic workflows

Welcome to the Build Multi-Agent LLM Applications with AutoGen!

Are you excited about exploring the world of Generative AI? In this course, we’ll learn how to create conversable and customizable AI agents powered by Large Language Models. This is a hands-on course with exercises in Python. We’ll cover how to integrate external tools like APIs and web scrapers with agents. We’ll cover advanced techniques like Retrieval Augmented Generation, Prompt Engineering (ReAct), and Task Decomposition. We’ll also implement different conversational patterns like group chats and nested chats.

Intended Audience:

This intermediate-level course is designed for data scientists, machine learning engineers, and software engineers aiming to expand their expertise into the LLM/Generative AI space.

Course Outline:

• Environment Setup

• Getting Started with AutoGen (Basic Concepts)

• Large Language Model Agents

• Agents with Human-in-the-Loop

• Agents with Code Execution Capability

• Agents with access to external tools like APIs and web scrapers

• Agents in different Conversational Patterns (Sequential, Group, Nested Chats)

• Agents with GPT-4 Turbto/DALL-E Image Generation Endpoints

• Prompt Engineering Techniques (ReAct) with Agents

• Retrieval Augmented Generation (RAG) using Chroma DB and LLM Agents

• Task Decomposition (Build Automated LLM Agents)

• Message Transformations for LLM Agents

• Using Non-OpenAI/Open Source Models with LM Studio

Join me on this journey to explore the world of LLM Agents and Generative AI!

Course Curriculum

Chapter 1: Introduction

Lecture 1: Welcome

Lecture 2: What You Should Know

Lecture 3: Environment Setup

Chapter 2: Agents and its Components

Lecture 1: Getting Started with AutoGen

Lecture 2: LLM Component

Lecture 3: Human In The Loop

Lecture 4: Code Executors

Lecture 5: Tools

Lecture 6: Shortcut Classes

Chapter 3: Conversational Patterns

Lecture 1: Sequential Chat

Lecture 2: Group Chat

Lecture 3: Nested Chat

Chapter 4: Advanced Workflows

Lecture 1: Agents with Images

Lecture 2: Prompt Engineering: ReAct

Lecture 3: Task Decomposition

Lecture 4: Retrieval Augmented Generation (RAG)

Chapter 5: Transformations

Lecture 1: TransformMessages Capability

Chapter 6: Using Non-Open AI Models

Lecture 1: Non-Open AI Models

Chapter 7: Next Steps

Lecture 1: Next Steps

Instructors

Shahzeb Naveed
ML Engineer at General Motors

Rating Distribution

1 stars: 2 votes
2 stars: 1 votes
3 stars: 1 votes
4 stars: 6 votes
5 stars: 11 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

Menu