Generative AI solutions with Azure OpenAI

Name: Generative AI solutions with Azure OpenAI
Rating: 4.5 (1032 reviews)

APL-3006. Using Python or C# to connect to Azure OpenAI. Use ChatGPT to create chats/code, and DALL-E to create images.

Created byPhillip Burton • over one million students so far, I Do Data Limited

Last updated 12/2024

English

What you'll learn

Deploy an Azure OpenAI resource and an Azure OpenAI model
Generate natural language responses by using Azure OpenAI, including using Python and C#
Apply prompt engineering techniques by using Azure OpenAI
Generate and improve code by using Azure OpenAI
Generate images with DALL-E in Azure OpenAI, including using Python and C#
Use Azure OpenAI on your data, including using Python and C#

Course content

6 sections • 43 lectures • 3h 19m total length

Introduction2:33
Develop generative AI solutions with Azure OpenAI, mastering GPT prompts, DALL-E image creation, and code integration with Python and C sharp.
Welcome to Udemy0:43
How to get the best out of your Udemy course3:05
Master Udemy course navigation and playback controls, including speed, volume, captions, and full-screen view, while accessing notes, Q&A, resources, announcements, ratings, and certificates.
Do you want auto-translated subtitles in more languages?1:20
Curriculum4:42
Explore the curriculum for generative AI solutions with Azure OpenAI, covering deploying resources, prompt engineering, code and image generation with DALL·E, and using your own data.
Resources0:12

Creating an Azure account, and exploring Azure interface6:52
Create a free Azure account and explore the portal to access free services and credits, manage subscriptions and resource groups, and learn about storage accounts before preparing for Azure OpenAI.
1. Applying for and creating an Azure OpenAI resource7:06
Apply for Azure OpenAI access and create a resource by completing the customer voice form, selecting a subscription and use cases such as GPT-3.5 and DALL-E.
2, 3. Deploying and using the GPT-3.5-turbo model5:28
Deploy and test GPT-3.5 turbo in Azure OpenAI Studio using management deployments, then use the chat playground to run prompts and view token usage and costs.
Generate Natural Language Solution responses7:11
What is the prompt?
What is primary content?
What are cues?
What is supporting content?
What are best practices?
8, 9. Prompt engineering - Using System messages8:26
What are they?
What do you define?
How can they be used for non-chat environments?
Templates for system messages
10. Apply other prompt engineering techniques, including few shot learning7:12
Break down the task (use the start of the Azure Studio Code article)
Incorporate previous responses into your next prompt.
Create a chain of thought prompting.
Change the temperature and top_p
Define additional safety and behavioral guardrails
11, 12, 13, 14. Creating code in the portal8:50
Clear syntax
Specify the output structure
Generate code
15, 16. Documenting and refactoring code3:16
Explore how to document and refactor Python code with Azure OpenAI: generate, explain, and document code, then refactor into a modular print_result function and reuse with different inputs.
Responsible Generative AI5:05
Explore responsible generative AI with Azure OpenAI, using content filters to classify prompts and completions for hate and fairness, sexual references, self-harm, and violence.
Using Azure OpenAI in the portal
Practice Activity 11:13
Practice Activity 1 - The Solution6:34
Create and deploy an Azure OpenAI resource with GPT‑3.5 Turbo, configure deployments and system prompts in the chat playground, then integrate with Python and C# in Visual Studio Code.

The ChatCompletion model5:03
Access Azure OpenAI from Visual Studio Code using chat completions with GPT-4 and legacy completions with GPT-3.5; configure endpoint, version, and key, and build messages.
4. Installing Visual Studio Code and copying connection details4:40
Install Visual Studio Code and set up the OpenAI connection by collecting endpoint, key, version, and deployment model in Azure OpenAI, preparing for Python and C# examples.
5. Using Python to connect to the GPT-3.5-turbo model, using version 1.x6:16
Build a Python program that connects to Azure OpenAI with your API key, and uses the gpt-3.5-turbo model via chat completions to generate a programmer slogan.
6, 7. Expanding Python code to use environment variables+ additional parameters4:34
Expand python code by moving Azure Open AI credentials to a .env file, load them with dotenv and os.environ, and set max tokens 200, temperature 0.8, and two output options.
5, 6, 7. Using the 0.28.1 Python library5:49
Learn how to install a specific OpenAI Python library version, adapt code for both 0.28.1 and 1.x, and understand the syntax, engine vs model terminology, and API changes across versions.
Python code
5. Using C# to connect to the OpenAI Resource, using version 1.0.0-beta.1310:14
Create a C# console app to connect to an Azure OpenAI resource using the 1.0.0-beta.13 package, configuring endpoint, key, and model name, then print the chat completion.
5, 6, 7. Expanding our C# code, and using version 1.0.0-beta.97:09
Expand your C# integration with Azure OpenAI by adding max tokens, temperature, and choice count, and compare 1.0.0-beta.9 to 1.0.0-beta.13 for chat message, chat request system message changes.
C# code
6, 10. Adding assistant messages, in the portal and in code7:42
Learn how to add assistant messages in the portal and in code, using user–assistant examples across Python and C#, and manage prompts, responses, and translations.
C# - Version 2.0.0-beta.20:31
Practice Activity 20:38
Practice Activity 2 - The Solution7:17
Configure Azure OpenAI resources for practice activity two by obtaining the key, endpoint, and Ms. GPT 35 deployment model, then build Python and C sharp examples in Visual Studio Code.

17. Using DALL-E 2 in the portal3:13
Generate images with Dall-E in the portal using the correct OpenAI resource location, craft prompts, select image size and style, adjust filters and tile size, and enable deployment.
18, 19. Using DALL-E 2 in Python, using version 0.28.14:27
Install openai v0.28.1 in Visual Studio Code, create program.py, and run Python code to generate DALL-E 2 images from a prompt, then print and open the image URL.
Using Python with DALL-E 2
18, 19. Using DALL-E 2 in C#5:07
Learn to call the DALL-E 2 engine from a C# console app using the Azure OpenAI library, configure the endpoint and key, and retrieve the generated image URL.
Practice Activity 30:35
Practice Activity 3 - The Solution4:18
Practice activity walks through building image generation workflows with Python and C# on Azure OpenAI, configuring endpoints, keys, prompts, and image size to generate and view images.

Creating Azure resources to use your own data in the portal8:20
Learn to connect your own data to Azure OpenAI by uploading documents to blob storage and indexing with Azure AI search, so the chat model uses your data.
20. Uploading and using our own data in the portal5:46
Upload and ingest your data into an Azure AI search index, upload supported file types, and capture the endpoint, key, and index for use in Python and C sharp.
21. Use your own data in Python8:00
Add a search index to your Python program to use your own data with Azure OpenAI by configuring environment variables for endpoint, key, and index, and adding data sources.
21. Use your own data in C#4:40
Learn how to incorporate your own data in a C# app by wiring a search endpoint, key, and index, then configure Azure Cognitive Search chat extensions for prompts.
Use your own data
Practice Activity 40:52
Practice Activity 4 - The Solution7:45
Demonstrates building an Azure OpenAI solution by provisioning blob storage and AI search, ingesting documents, and querying with Python and C# to confirm a 30-day trial.
Deleting Azure resources2:37
Learn to deprovision Azure resources to stop recurring charges by deleting Azure Open AI, AI Search, blob storage, and resource groups, and monitor costs in cost management.

What's Next?2:35
Explore next steps after mastering generative AI solutions with Azure OpenAI, including taking the Microsoft Applied Skills assessment and practicing with interactive labs to build natural language responses and code.
Congratulations for completing the course1:01
Complete the course by reviewing the Azure Open AI resource, applying prompt engineering to conversations and code, and connecting to a GPT model with Python and C sharp across APIs.
Bonus Lecture - AI Microsoft Applied Skills0:10

Requirements

There are no requirements for watching the course.
If you want to program in Python or C#, then you will need to download Visual Studio Code. It is available for Windows, macOS and Linux.

Description

This course goes through all of the skills which were required for the Microsoft Applied Skills: Develop generative AI solutions with Azure OpenAI Service. While the skills are still relevant, please note - this Microsoft Applied Skill was discontinued on October 31, 2024.

This course has been updated in line with the expanded Study Guide (June 2024).

Please note: This course is not affiliated with, endorsed by, or sponsored by Microsoft.

What do people like you say about this course?

Antonina says: Great course for beginners, thank you!

Steven says: Good intro to using Python and C# to interact with Microsoft Azure AI services. Philip is a terrific instructor, clear and concise. Course has good examples & exercises.

In this 3 hour course we’ll cover the skills that were needed for the APL-3006 Microsoft Applied Skills credential for generative AI.

It will also help with the Microsoft exam AI-102 "Designing and Implementing a Microsoft Azure AI Solution".

The tasks that you need to perform to get this skill are:

Deploy an Azure OpenAI resource and an Azure OpenAI model. We'll create an Azure account using a free trial, and then apply for permission to create and Azure OpenAI resource. Once that permission is generated, we'll create the resource, and deploy a GPT-3.5-turbo model (this is the technology behind ChatGPT) in the Azure OpenAI Studio.
Generate natural language responses by using Azure OpenAI. We'll use the GPT Chat playground to send prompts and receive responses. We will also download Visual Studio Code and write code in Python and C#.
Apply prompt engineering techniques by using Azure OpenAI. We'll improve the quality of the prompts with Primary and Supporting Content, cues, system and assistant messages, chain of thought prompting, and more, with our GPT Playground (or ChatGPT).
Generate and improve code by using Azure OpenAI. We'll create and amend Python, C# and SQL code, using section dividers, comments, and unit tests.
Generate images with DALL-E in Azure OpenAI. We'll create images based on prompts, and write code in Python and C# to generate it in our program.
Use Azure OpenAI on your data. We'll upload PDFs into our GPT-3.5-turbo model, which will provide updated information or company documents for our GPT model to use.

There are several Practice Activities and quizzes throughout the course, so you can be sure that you are learning.

By the end of the course, you'll be much more confident about developing generative AI solutions with Azure OpenAI Service, using GPT, ChatGPT or DALL-E.

Who this course is for:

This is for you if you want to use Generative Artificial Intelligence, either using a portal or programming using Python or C#.
This course will guide you through the skills required for the Microsoft Applied Skills credential "Develop generative AI solutions with Azure OpenAI Service".
This is especially for you if you are, or want to be, an AI Engineer, App Maker, or Developer, or just want to learn more about Gen AI.

Generative AI solutions with Azure OpenAI

What you'll learn

Explore related topics

Course content

Introduction6 lectures • 13min

Using Azure OpenAI in the portal11 lectures • 1hr 7min

Connecting to the GPT-3.5-turbo model using Python and C#11 lectures • 1hr

Using DALL-E 2, using the portal and in code5 lectures • 18min

Use your own data7 lectures • 38min

Congratulations for completing the course3 lectures • 4min

Requirements

Description

Who this course is for: