Skip to content
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.

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

Adding docs and files for deploying an Azure OpenAI instance via Bicep file #324

Merged
merged 7 commits into from
Jan 15, 2025

Conversation

StevenBucher98
Copy link
Collaborator

PR Summary

Added a simple bicep file to deploy a new Azure AI Service account and an Azure AI deployment to be used for the openai-gpt agent. The file will only need minor modifications for users specific names and values. Instructions also include how to get the necessary endpoint and keys for configuring the agent with their new deployment.

PR Context

This PR helps add details on how to make an Azure OpenAI Deployment easily from the command line.

Copy link

@Copilot Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copilot reviewed 1 out of 2 changed files in this pull request and generated 1 comment.

Files not reviewed (1)
  • docs/development/AzureOAIDeployment/main.bicep: Language not supported
Comments suppressed due to low confidence (3)

docs/development/AzureOAIDeployment/DeployingAzureOAI.md:48

  • The model version 'turbo-2024-04-09' might be outdated soon. Users should be advised to check for the latest version.
param modelversion string = 'turbo-2024-04-09'

docs/development/AzureOAIDeployment/DeployingAzureOAI.md:3

  • The word 'manage-ability' should be 'manageability'.
manage-ability

docs/development/AzureOAIDeployment/DeployingAzureOAI.md:124

  • The word 'expertize' should be 'expertise'.
expertize

Tip: Leave feedback on Copilot's review comments with the 👎 and 👍 buttons to help improve review quality. Learn more

docs/development/AzureOAIDeployment/DeployingAzureOAI.md Outdated Show resolved Hide resolved
Copy link
Member

@daxian-dbw daxian-dbw left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Looks good overall!


Now that you have the endpoint and key of the deployment, you can open up the `openai-gpt` agent and run `/agent config` to edit the json configuration file with all the details of the deployment. The example below shows the default system prompt and the fields that need to be updated.

```json
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

try jsonc instead as there are comments in the json.

Comment on lines 75 to 85
#### Using Azure CLI

```sh
az deployment group create --resource-group <resource group name> --template-file ./main.bicep
```

#### Using Azure PowerShell

```powershell
New-AzResourceGroupDeployment -ResourceGroupName <resource group name> -TemplateFile ./main.bicep
```
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The sections below simply list the AzPS and AzCLI commands in their own code block, maybe do that for this section too and get rid of the Using Azure CLI/Using Azure PowerShell sub-sections?

}
}

resource gpt4oMiniDeployment 'Microsoft.CognitiveServices/accounts/deployments@2024-10-01' = {
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The name here is gpt4omini, may be change to gpt4 according to the default parameter values used in the file?

@daxian-dbw daxian-dbw merged commit 80bccd7 into main Jan 15, 2025
4 checks passed
@daxian-dbw daxian-dbw deleted the aoaideploymentbicep branch January 15, 2025 05:12
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants