Some AOAI Model have been retirements. about entaoai HOT 8 CLOSED

Faced same problem, tried to switch to gpt-35-turbo-16k and facing issues.

from entaoai.

Deployment has been successful since I deleted the Davinci deployment code to resolve issues with replacing the AOAI model.

from entaoai.

which model did you replace it with?

from entaoai.

Deployment has been successful since I deleted the Davinci deployment code to resolve issues with replacing the AOAI model.

Would you mind creating pull request and fixing azuredeploy.json file? Happy to modify code if you can suggest the fix

from entaoai.

Deployment has been successful since I deleted the Davinci deployment code to resolve issues with replacing the AOAI model.

Would you mind creating pull request and fixing azuredeploy.json file? Happy to modify code if you can suggest the fix
Sure, I've modified the code, and hope you'll review it.

from entaoai.

Deployment has been successful since I deleted the Davinci deployment code to resolve issues with replacing the AOAI model.

Would you mind creating pull request and fixing azuredeploy.json file? Happy to modify code if you can suggest the fix
Sure, I've modified the code, and hope you'll review it.

I don't see pull request. Can you put your modified code here and I can update the repo

from entaoai.

Sorry about that.
I thought I had made a pull request, but I guess it wasn't requested.
I'm not very skilled with github.
I'll try to explain in the comments.
In the file below, I removed the following Davinci model from the deployment.
azuredeploy.json
{
"type": "Microsoft.CognitiveServices/accounts/deployments",
"apiVersion": "2022-12-01",
"name": "[concat(variables('aoaiSvcName'), '/davinci')]",
"dependsOn": [
"[resourceId('Microsoft.Resources/deploymentScripts','Wait5s')]"
],
"properties": {
"model": {
"format": "OpenAI",
"name": "text-davinci-003",
"version": "1"
},
"scaleSettings": {
"scaleType": "Standard"
},
"raiPolicyName": "Microsoft.Default"
}

And delete the following parts.
{
"name": "OpenAiDavinci",
"value": "davinci"
},

Please review this.

from entaoai.

Modified the deployment to remove the Davinci model usage and replace it with only gpt3.5 turbo, embedding and 3.5turbo with 16k model. All code using Davinci is also refactored

from entaoai.