Skip to content

Commit 93d0181

Browse files
GraemeMalcolmGraemeMalcolm
committed
2 parents bdc30c0 + 41adbdd commit 93d0181

File tree

13 files changed

+668
-0
lines changed

13 files changed

+668
-0
lines changed

‎Instructions/Labs/04-code-generation.md

Lines changed: 257 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,257 @@
1+
---
2+
lab:
3+
title: 'Generate code using Azure OpenAI'
4+
---
5+
6+
# Generate code using Azure OpenAI
7+
8+
The Azure OpenAI Service models can generate code for you using natural language prompts, fixing bugs in completed code, and providing code comments. These models can also explain and simplify existing code to help you understand what it does and how to improve it.
9+
10+
This exercise will take approximately **25** minutes.
11+
12+
## Before you start
13+
14+
You will need an Azure subscription that has been approved for access to the Azure OpenAI service.
15+
16+
- To sign up for a free Azure subscription, visit [https://azure.microsoft.com/free](https://azure.microsoft.com/free).
17+
- To request access to the Azure OpenAI service, visit [https://aka.ms/oaiapply](https://aka.ms/oaiapply).
18+
19+
## Provision an Azure OpenAI resource
20+
21+
Before you can use Azure OpenAI models, you must provision an Azure OpenAI resource in your Azure subscription.
22+
23+
1. Sign into the [Azure portal](https://portal.azure.com).
24+
2. Create an **Azure OpenAI** resource with the following settings:
25+
- **Subscription**: An Azure subscription that has been approved for access to the Azure OpenAI service.
26+
- **Resource group**: Create a new resource group with a name of your choice.
27+
- **Region**: Choose any available region.
28+
- **Name**: A unique name of your choice.
29+
- **Pricing tier**: Standard S0
30+
3. Wait for deployment to complete. Then go to the deployed Azure OpenAI resource in the Azure portal.
31+
4. Navigate to **Keys and Endpoint** page, and save those to a text file to use later.
32+
33+
## Deploy a model
34+
35+
To use the Azure OpenAI API for code generation, you must first deploy a model to use through the **Azure OpenAI Studio**. Once deployed, we will use the model with the playground and reference that model in our app.
36+
37+
1. On the **Overview** page for your Azure OpenAI resource, use the **Explore** button to open Azure OpenAI Studio in a new browser tab. Alternatively, navigate to [Azure OpenAI Studio](https://oai.azure.com/?azure-portal=true) directly.
38+
2. In Azure OpenAI Studio, create a new deployment with the following settings:
39+
- **Model name**: gpt-35-turbo
40+
- **Deployment name**: 35turbo
41+
42+
> **Note**: Each Azure OpenAI model is optimized for a different balance of capabilities and performance. We'll use the **3.5 Turbo** model series in the **GPT-3** model family in this exercise, which is highly capable for both language and code understanding.
43+
44+
## Generate code in chat playground
45+
46+
Before using your app, examine how prompt engineering improves the model response in the playground. In this first example, imagine you are trying to write a python app of animals with fun names.
47+
48+
1. In [Azure OpenAI Studio](https://oai.azure.com/?azure-portal=true), navigate to the **Chat** playground in the left pane.
49+
1. In the **Assistant setup** section at the top, select the **Default** system message template.
50+
1. In the **Chat session** section, enter the following prompt and press *Enter*.
51+
52+
```code
53+
Write a function in python that takes a character and string as input, and returns how many times that character appears in the string
54+
```
55+
56+
1. The model will likely respond with a function, with some explanation of what the function does and how to call it.
57+
1. Next, send the prompt `Do the same thing, but this time write it in C#`.
58+
1. Observe the output. The model likely responded very similarly as the first time, but this time coding in C#. You can ask it again for a different language of your choice, or a function to complete a different task such as reversing the input string.
59+
1. Next, let's explore using AI to understand code with this example of a random function you saw written in Ruby. Send the following prompt as the user message.
60+
61+
```code
62+
What does the following function do?
63+
---
64+
def random_func(n)
65+
start = [0, 1]
66+
(n - 2).times do
67+
start << start[-1] + start[-2]
68+
end
69+
start.shuffle.each do |num|
70+
puts num
71+
end
72+
end
73+
```
74+
75+
1. Observe the output, which explains what the function does in natural language. Try asking the model to rewrite it in a language you are familiar with.
76+
77+
## Set up an application in Cloud Shell
78+
79+
To show how to integrate with an Azure OpenAI model, we'll use a short command-line application that runs in Cloud Shell on Azure. Open up a new browser tab to work with Cloud Shell.
80+
81+
1. In the [Azure portal](https://portal.azure.com?azure-portal=true), select the **[>_]** (*Cloud Shell*) button at the top of the page to the right of the search box. A Cloud Shell pane will open at the bottom of the portal.
82+
83+
![Screenshot of starting Cloud Shell by clicking on the icon to the right of the top search box.](../media/cloudshell-launch-portal.png#lightbox)
84+
85+
2. The first time you open the Cloud Shell, you may be prompted to choose the type of shell you want to use (*Bash* or *PowerShell*). Select **Bash**. If you don't see this option, skip the step.
86+
87+
3. If you're prompted to create storage for your Cloud Shell, ensure your subscription is specified and select **Create storage**. Then wait a minute or so for the storage to be created.
88+
89+
4. Make sure the type of shell indicated on the top left of the Cloud Shell pane is switched to *Bash*. If it's *PowerShell*, switch to *Bash* by using the drop-down menu.
90+
91+
5. Once the terminal starts, enter the following command to download the sample application and save it to a folder called `azure-openai`.
92+
93+
```bash
94+
rm -r azure-openai -f
95+
git clone https://github.com/MicrosoftLearning/mslearn-openai azure-openai
96+
```
97+
98+
6. The files are downloaded to a folder named **azure-openai**. Navigate to the lab files for this exercise using the following command.
99+
100+
```bash
101+
cd azure-openai/Labfiles/04-code-generation
102+
```
103+
104+
Applications for both C# and Python have been provided, as well as sample code we'll be using in this lab.
105+
106+
Open the built-in code editor, and you can observe the code files we'll be using in `sample-code`. Use the following command to open the lab files in the code editor.
107+
108+
```bash
109+
code .
110+
```
111+
112+
## Configure your application
113+
114+
For this exercise, you'll complete some key parts of the application to enable using your Azure OpenAI resource.
115+
116+
1. In the code editor, expand the language folder for your preferred language.
117+
118+
2. Open the configuration file for your language.
119+
120+
- **C#**: `appsettings.json`
121+
- **Python**: `.env`
122+
123+
3. Update the configuration values to include the **endpoint** and **key** from the Azure OpenAI resource you created, as well as the name of your deployment, `35turbo`. Save the file.
124+
125+
4. Navigate to the folder for your preferred language and install the necessary packages.
126+
127+
**C#**
128+
129+
```bash
130+
cd CSharp
131+
dotnet add package Azure.AI.OpenAI --version 1.0.0-beta.5
132+
```
133+
134+
**Python**
135+
136+
```bash
137+
cd Python
138+
pip install python-dotenv
139+
pip install openai
140+
```
141+
142+
5. Select the code file in this folder for your language and add the necessary libraries.
143+
144+
**C#**
145+
146+
`Program.cs`
147+
148+
```csharp
149+
// Add Azure OpenAI package
150+
using Azure.AI.OpenAI;
151+
```
152+
153+
**Python**
154+
155+
`code-generation.py`
156+
157+
```python
158+
# Add OpenAI import
159+
import openai
160+
```
161+
162+
6. Add the necessary code for configuring the client.
163+
164+
**C#**
165+
166+
```csharp
167+
// Initialize the Azure OpenAI client
168+
OpenAIClient client = new OpenAIClient(new Uri(oaiEndpoint), new AzureKeyCredential(oaiKey));
169+
```
170+
171+
**Python**
172+
173+
```python
174+
# Set OpenAI configuration settings
175+
openai.api_type = "azure"
176+
openai.api_base = azure_oai_endpoint
177+
openai.api_version = "2023-05-15"
178+
openai.api_key = azure_oai_key
179+
```
180+
181+
7. In the function that calls the Azure OpenAI model, add the code to format and send the request to the model.
182+
183+
**C#**
184+
185+
```csharp
186+
// Create chat completion options
187+
var chatCompletionsOptions = new ChatCompletionsOptions()
188+
{
189+
Messages =
190+
{
191+
new ChatMessage(ChatRole.System, systemPrompt),
192+
new ChatMessage(ChatRole.User, userPrompt)
193+
},
194+
Temperature = 0.7f,
195+
MaxTokens = 1000,
196+
};
197+
198+
// Get response from Azure OpenAI
199+
Response<ChatCompletions> response = await client.GetChatCompletionsAsync(
200+
oaiModelName,
201+
chatCompletionsOptions
202+
);
203+
204+
ChatCompletions completions = response.Value;
205+
string completion = completions.Choices[0].Message.Content;
206+
```
207+
208+
**Python**
209+
210+
```python
211+
# Build the messages array
212+
messages =[
213+
{"role": "system", "content": system_message},
214+
{"role": "user", "content": user_message},
215+
]
216+
217+
# Call the Azure OpenAI model
218+
response = openai.ChatCompletion.create(
219+
engine=model,
220+
messages=messages,
221+
temperature=0.7,
222+
max_tokens=1000
223+
)
224+
```
225+
226+
## Run your application
227+
228+
Now that your app has been configured, run it to try generating code for each use case. The use case is numbered in the app, and can be run in any order.
229+
230+
> **Note**: Some users may experience rate limiting if calling the model too frequently. If you hit an error about a token rate limit, wait for a minute then try again.
231+
232+
1. In the code editor, expand the `sample-code` folder and briefly observe the function and the app for your language. These files will be used for the tasks in the app.
233+
1. In the Cloud Shell bash terminal, navigate to the folder for your preferred language.
234+
1. Run the application.
235+
236+
- **C#**: `dotnet run`
237+
- **Python**: `python code-generation.py`
238+
239+
1. Choose option **1** to add comments to your code. Note, the response might take a few seconds for each of these tasks.
240+
1. The results will be put into `result/app.txt`. Open that file up, and compare it to the function file in `sample-code`.
241+
1. Next, choose option **2** to write unit tests for that same function.
242+
1. The results will replace what was in `result/app.txt`, and details four unit tests for that function.
243+
1. Next, choose option **3** to fix bugs in an app for playing Go Fish.
244+
1. The results will replace what was in `result/app.txt`, and should have very similar code with a few things corrected.
245+
246+
- **C#**: Fixes are made on line 30 and 59
247+
- **Python**: Fixes are made on line 18 and 31
248+
249+
The app for Go Fish in `sample-code` can be run, if you replace the lines with bugs with the response from Azure OpenAI. If you run it without the fixes, it will not work correctly.
250+
251+
It's important to note that even though the code for this Go Fish app was corrected for some syntax, it's not a strictly accurate representation of the game. If you look closely, there are issues with not checking if the deck is empty when drawing cards, not removing pairs from the players hand when they get a pair, and a few other bugs that require understanding of card games to realize. This is a great example of how useful generative AI models can be to assist with code generation, but can't be trusted as correct and need to be verified by the developer.
252+
253+
If you would like to see the full response from Azure OpenAI, you can set the `printFullResponse` variable to `True`, and rerun the app.
254+
255+
## Clean up
256+
257+
When you're done with your Azure OpenAI resource, remember to delete the deployment or the entire resource in the [Azure portal](https://portal.azure.com/?azure-portal=true).

‎Labfiles/04-code-generation/CSharp/CSharp.csproj

Lines changed: 21 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,21 @@
1+
<Project Sdk="Microsoft.NET.Sdk">
2+
3+
<PropertyGroup>
4+
<OutputType>Exe</OutputType>
5+
<TargetFramework>net7.0</TargetFramework>
6+
<ImplicitUsings>enable</ImplicitUsings>
7+
<Nullable>enable</Nullable>
8+
</PropertyGroup>
9+
10+
<ItemGroup>
11+
<PackageReference Include="Microsoft.Extensions.Configuration" Version="7.0.0" />
12+
<PackageReference Include="Microsoft.Extensions.Configuration.Json" Version="7.0.0" />
13+
</ItemGroup>
14+
15+
<ItemGroup>
16+
<None Update="appsettings.json">
17+
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
18+
</None>
19+
</ItemGroup>
20+
21+
</Project>

‎Labfiles/04-code-generation/CSharp/Program.cs

Lines changed: 88 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,88 @@
1+
// Implicit using statements are included
2+
using System.Text;
3+
using System.Text.Json;
4+
using Microsoft.Extensions.Configuration;
5+
using Microsoft.Extensions.Configuration.Json;
6+
using Azure;
7+
8+
// Add Azure OpenAI package
9+
10+
// Build a config object and retrieve user settings.
11+
IConfiguration config = new ConfigurationBuilder()
12+
.AddJsonFile("appsettings.json")
13+
.Build();
14+
string? oaiEndpoint = config["AzureOAIEndpoint"];
15+
string? oaiKey = config["AzureOAIKey"];
16+
string? oaiModelName = config["AzureOAIDeploymentName"];
17+
18+
string command;
19+
bool printFullResponse = false;
20+
21+
do {
22+
Console.WriteLine("\n1: Add comments to my function\n" +
23+
"2: Write unit tests for my function\n" +
24+
"3: Fix my Go Fish game\n" +
25+
"\"quit\" to exit the program\n\n" +
26+
"Enter a number to select a task:");
27+
28+
command = Console.ReadLine() ?? "";
29+
30+
switch (command) {
31+
case "1":
32+
string functionFile = System.IO.File.ReadAllText("../sample-code/function/function.cs");
33+
string commentPrompt = "Add comments to the following function. Return only the commented code.\n---\n" + functionFile;
34+
35+
await GetResponseFromOpenAI(commentPrompt);
36+
break;
37+
case "2":
38+
functionFile = System.IO.File.ReadAllText("../sample-code/function/function.cs");
39+
string unitTestPrompt = "Write four unit tests for the following function.\n---\n" + functionFile;
40+
41+
await GetResponseFromOpenAI(unitTestPrompt);
42+
break;
43+
case "3":
44+
string goFishFile = System.IO.File.ReadAllText("../sample-code/go-fish/go-fish.cs");
45+
string goFishPrompt = "Fix the code below for an app to play Go Fish with the user. Return only the corrected code.\n---\n" + goFishFile;
46+
47+
await GetResponseFromOpenAI(goFishPrompt);
48+
break;
49+
case "quit":
50+
Console.WriteLine("Exiting program...");
51+
break;
52+
default:
53+
Console.WriteLine("Invalid input. Please try again.");
54+
break;
55+
}
56+
} while (command != "quit");
57+
58+
async Task GetResponseFromOpenAI(string prompt)
59+
{
60+
Console.WriteLine("\nCalling Azure OpenAI to generate code...\n\n");
61+
62+
if(string.IsNullOrEmpty(oaiEndpoint) || string.IsNullOrEmpty(oaiKey) || string.IsNullOrEmpty(oaiModelName) )
63+
{
64+
Console.WriteLine("Please check your appsettings.json file for missing or incorrect values.");
65+
return;
66+
}
67+
68+
// Initialize the Azure OpenAI client
69+
70+
// Define chat prompts
71+
string systemPrompt = "You are a helpful AI assistant that helps programmers write code.";
72+
string userPrompt = prompt;
73+
74+
// Create chat completion options
75+
76+
77+
// Write full response to console, if requested
78+
if (printFullResponse)
79+
{
80+
Console.WriteLine($"\nFull response: {JsonSerializer.Serialize(completions, new JsonSerializerOptions { WriteIndented = true })}\n\n");
81+
}
82+
83+
// Write the file.
84+
System.IO.File.WriteAllText("result/app.txt", completion);
85+
86+
// Write response to console
87+
Console.WriteLine($"\nResponse written to results/app.txt\n\n");
88+
}

‎Labfiles/04-code-generation/CSharp/appsettings.json

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,5 @@
1+
{
2+
"AzureOAIEndpoint": "",
3+
"AzureOAIKey": "",
4+
"AzureOAIDeploymentName": ""
5+
}

‎Labfiles/04-code-generation/CSharp/result/app.txt

Whitespace-only changes.

‎Labfiles/04-code-generation/Python/.env

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
AZURE_OAI_ENDPOINT=
2+
AZURE_OAI_KEY=
3+
AZURE_OAI_DEPLOYMENT=

0 commit comments

Comments
 (0)