Skip to content

update openai deployment instructions #419

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Nov 19, 2025
+17 −12
Merged

update openai deployment instructions #419

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 13 additions & 8 deletions docs/development/AzureOAIDeployment/DeployingAzureOAI.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,10 +43,10 @@ param customDomainName string = '<Insert own unique domain name>'
param modeldeploymentname string = '<Insert own deployment name>'
@description('The model being deployed')
param model string = 'gpt-4'
param model string = 'gpt-4o'
@description('Version of the model being deployed')
param modelversion string = 'turbo-2024-04-09'
param modelversion string = '2024-11-20'
@description('Capacity for specific model used')
param capacity int = 80
Expand All @@ -60,8 +60,13 @@ param location string = resourceGroup().location
param sku string = 'S0'
```

> **Note:** The `customDomainName` parameter is not a full domain URL. It's a unique subdomain prefix
> that Azure will use to create your OpenAI endpoint. For example, if you set `customDomainName` to
> `mycompany-openai`, your endpoint will be `https://mycompany-openai.openai.azure.com/`. This name
> must be globally unique across all Azure OpenAI services.
The above is defaulted to use your resource groups location as the location for the account and
`gpt-4` version `turbo-2024-04-09`. You can modify this based on the particular model you feel best
`gpt-4o` version `2024-11-20`. You can modify this based on the particular model you feel best
fits your needs. You can find more information on available models at
[Azure OpenAI Service models][03]. Additionally, you may need to modify the capacity of the
deployment based on what model you use, you can find more information at
Expand All @@ -78,9 +83,9 @@ instance! Simply use either Azure CLI or Azure PowerShell to deploy the bicep fi
az deployment group create --resource-group <resource group name> --template-file ./main.bicep

// Get the endpoint and key of the deployment
az cognitiveservices account show --name <account name> --resource-group <resource group name> | jq -r .properties.endpoint
az cognitiveservices account show --name <account name> --resource-group <resource group name> --query "properties.endpoint" -o tsv

az cognitiveservices account keys list --name <account name> --resource-group <resource group name> | jq -r .key1
az cognitiveservices account keys list --name <account name> --resource-group <resource group name> --query "key1" -o tsv
```

#### Using Azure PowerShell
Expand All @@ -105,18 +110,18 @@ example below shows the default system prompt and the fields that need to be upd
// Declare GPT instances.
"GPTs": [
{
"Name": "ps-az-gpt4",
"Name": "ps-az-gpt4o",
"Description": "<insert description here>",
"Endpoint": "<insert endpoint here>",
"Deployment": "<insert deployment name here>",
"ModelName": "gpt-4",
"ModelName": "gpt-4o",
"Key": "<insert key here>",
"SystemPrompt": "1. You are a helpful and friendly assistant with expertise in PowerShell scripting and command line.\n2. Assume user is using the operating system `osx` unless otherwise specified.\n3. Use the `code block` syntax in markdown to encapsulate any part in responses that is code, YAML, JSON or XML, but not table.\n4. When encapsulating command line code, use '```powershell' if it's PowerShell command; use '```sh' if it's non-PowerShell CLI command.\n5. When generating CLI commands, never ever break a command into multiple lines. Instead, always list all parameters and arguments of the command on the same line.\n6. Please keep the response concise but to the point. Do not overexplain."
}
],
// Specify the default GPT instance to use for user query.
// For example: "ps-az-gpt4"
"Active": "ps-az-gpt4"
"Active": "ps-az-gpt4o"
}
```

Expand Down
8 changes: 4 additions & 4 deletions docs/development/AzureOAIDeployment/main.bicep
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,10 @@ param customDomainName string = '<Insert own unique domain name>'
param modeldeploymentname string = '<Insert own deployment name>'

@description('The model being deployed')
param model string = 'gpt-4'
param model string = 'gpt-4o'

@description('Version of the model being deployed')
param modelversion string = 'turbo-2024-04-09'
param modelversion string = '2024-11-20'

@description('Capacity for specific model used')
param capacity int = 80
Expand All @@ -24,7 +24,7 @@ param location string = resourceGroup().location
])
param sku string = 'S0'

resource openAIService 'Microsoft.CognitiveServices/accounts@2024-10-01' = {
resource openAIService 'Microsoft.CognitiveServices/accounts@2025-10-01-preview' = {
name: aiserviceaccountname
location: location
identity: {
Expand All @@ -39,7 +39,7 @@ resource openAIService 'Microsoft.CognitiveServices/accounts@2024-10-01' = {
}
}

resource azopenaideployment 'Microsoft.CognitiveServices/accounts/deployments@2024-10-01' = {
resource azopenaideployment 'Microsoft.CognitiveServices/accounts/deployments@2025-10-01-preview' = {
parent: openAIService
name: modeldeploymentname
properties: {
Expand Down