Working with large language models using Azure

本课程是 Microsoft Generative AI Engineering 专业证书的一部分

位教师： Microsoft

访问权限由 New York State Department of Labor 提供

4个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

4个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将获得的技能

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

23 项作业

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

积累 Software Development 领域的专业知识

本课程是 Microsoft Generative AI Engineering 专业证书专项课程的一部分

在注册此课程时，您还会同时注册此专业证书。

向行业专家学习新概念
获得对主题或工具的基础理解
通过实践项目培养工作相关技能
通过 Microsoft 获得可共享的职业证书

该课程共有4个模块

Master the development of generative AI solutions using Microsoft Azure. This hands-on course guides you through the complete application lifecycle, from foundational concepts to deployment. You will learn to control Large Language Models (LLMs) with advanced prompt engineering, ground models in custom data using Retrieval-Augmented Generation (RAG) pipelines, and tailor their behavior with fine-tuning techniques. Using powerful Azure tools, you'll build, deploy, and manage sophisticated AI applications ready to solve real-world challenges.

This foundational module introduces the core concepts behind Large Language Models (LLMs). You will start by exploring the fundamental architecture that powers models like GPT (Generative Pre-trained Transformer) and learn how they process information and generate human-like text. The second half of the module is dedicated to prompt engineering, where you will learn and apply essential techniques—from basic commands to advanced strategies like few-shot learning and chain-of-thought—to effectively communicate with and control AI models to achieve desired outcomes.

涵盖的内容

8个视频8篇阅读材料5个作业

8个视频总计34分钟

Introduction to Microsoft Generative AI engineering certification 4分钟
Introduction to Working with Large Language Models using Azure course 3分钟
Introduction to LLMs and prompt engineering 3分钟
The impact of LLMs 6分钟
A look inside an LLM: From prompt to response 5分钟
Why Prompt Engineering Matters 4分钟
Crafting effective prompts 6分钟
Module 1 summary: LLM fundamentals and prompt engineering 2分钟

8篇阅读材料总计95分钟

Course syllabus and recommended background 5分钟
Overview of LLM interaction 10分钟
Exploring LLM architecture 15分钟
LLM fundamentals: From tokens to sequential models 15分钟
The blueprint of modern LLMs: The transformer architecture 15分钟
Insights from LLM interactions 10分钟
Techniques in prompt engineering 15分钟
Prompt engineering success strategies 10分钟

5个作业总计180分钟

Interacting with LLMs: Basics 30分钟
LLM architecture: Practice Quiz 30分钟
Creating successful prompts 60分钟
Prompt engineering skills: Practice Quiz 30分钟
Module 1 Evaluation: Graded Quiz 30分钟

This module focuses on one of the most powerful techniques for enhancing LLMs: Retrieval-Augmented Generation (RAG). You will learn how to ground models in external, private, or real-time data sources to provide more accurate and contextually relevant responses. You will start by building a basic RAG pipeline using Azure services and then progress to constructing and optimizing advanced systems with techniques like semantic ranking and sophisticated data chunking strategies.

涵盖的内容

5个视频6篇阅读材料6个作业

5个视频总计24分钟

Introduction to RAG: Grounding AI with data 5分钟
RAG pipelines explained 6分钟
Data sources for RAG: Azure AI Search and the Marketplace 6分钟
Advanced RAG configurations 5分钟
Module 2 summary: Mastering RAG pipelines 3分钟

6篇阅读材料总计70分钟

Understanding RAG frameworks 15分钟
Introduction to RAG techniques 10分钟
Reviewing your first RAG pipeline 10分钟
Advanced RAG pipeline techniques 15分钟
Effective RAG optimization strategies 10分钟
Case study: Implementing advanced RAG in a corporate setting 10分钟

6个作业总计215分钟

Exploring RAG pipelines 30分钟
Basic RAG pipeline setup 35分钟
RAG fundamentals: Practice Quiz 30分钟
Optimizing RAG implementations 60分钟
Advanced RAG skills evaluation: Practice Quiz 30分钟
Module 2 evaluation: Graded Quiz 30分钟

This module explores fine-tuning as a powerful method for customizing an LLM's core behavior, style, or knowledge for specialized tasks. You will learn the entire fine-tuning workflow, from preparing a high-quality dataset to launching the training job and evaluating the customized model's performance in Azure. Critically, you will learn to strategically decide when to use fine-tuning versus RAG—or a hybrid of both—to create highly effective, domain-specific AI solutions.

涵盖的内容

4个视频7篇阅读材料6个作业

4个视频总计19分钟

The art of fine-tuning 6分钟
A guided tour of Azure's fine-tuning interface 5分钟
Integrating domain expertise into your application 5分钟
Module 3 summary: Mastering customization with fine-tuning 2分钟

7篇阅读材料总计70分钟

Fine-tuning techniques 10分钟
Learnings from fine-tuning LLMs 10分钟
Evaluating your custom fine-tuned model 10分钟
Strategies for domain integration 10分钟
A framework for evaluating custom models 10分钟
Analyzing domain specific LLMs 10分钟
RAG vs. fine-tuning: A strategic decision framework 10分钟

6个作业总计215分钟

Fine-tuning practice 30分钟
Customized LLM implementation 35分钟
Fine-tuning comprehension: Practice Quiz 30分钟
From customization to application: A domain-specific LLM lab 60分钟
Real world use assessment: Practice Quiz 30分钟
Module 3 evaluation: Graded Quiz 30分钟

This module transitions from theory to practice by guiding you through the end-to-end process of building and deploying a complete generative AI application. You will learn to design an application's architecture and user flow before using Azure AI Foundry and Prompt flow tools to build it. The module then covers the critical MLOps lifecycle, teaching you how to deploy your application as a secure endpoint, manage it in a production environment, and implement monitoring with Azure Monitor for performance and cost.