New Codespace Creation error 400 (400 Bad Request) with error: InsufficientQuota:

[ediaz-caio]

New code space error

Error: creating Deployment (Subscription: ""
│ Resource Group Name: "infoasst-test"
│ Account Name: "infoasst-aoai"
│ Deployment Name: "text-embedding-ada-002"): performing CreateOrUpdate: unexpected status 400 (400 Bad Request) with error: InsufficientQuota: This operation require 240 new capacity in quota Tokens Per Minute (thousands) - Text-Embedding-Ada-002, which is bigger than the current available capacity 0. The current quota usage is 240 and the quota limit is 240 for quota Tokens Per Minute (thousands) - Text-Embedding-Ada-002.
│
│ with module.openaiServices.azurerm_cognitive_deployment.deployment[1],
│ on core/ai/openaiservices/openaiservices.tf line 27, in resource "azurerm_cognitive_deployment" "deployment":
│ 27: resource "azurerm_cognitive_deployment" "deployment" {
│
│ creating Deployment (Subscription: ""
│ Resource Group Name: "infoasst-test"
│ Account Name: "infoasst-aoai"
│ Deployment Name: "text-embedding-ada-002"): performing CreateOrUpdate: unexpected status 400 (400 Bad Request) with error: InsufficientQuota: This operation require 240 new capacity in quota Tokens Per Minute
│ (thousands) - Text-Embedding-Ada-002, which is bigger than the current available capacity 0. The current quota usage is 240 and the quota limit is 240 for quota Tokens Per Minute (thousands) - Text-Embedding-Ada-002.
╵
make: *** [Makefile:22: infrastructure] Error 1

[dayland]

This is a quota issue with your Azure OpenAI services. Azure Open AI quota is subscription wide, meaning if you have more than one instance of Azure OpenAI and/or more than one deployment of the same base model, the TPM quota is the combination across all instances in a subscription. This can lead to quota limits being consumed as reported in the error you provided. Please check to see how many instance you have deployed and total consumed quota for the "text-embeddings-ada-02" model.

You can reduce existing deployed instances, delete unused deployments, or request a quota increase in the Azure Portal. Also be aware that deleted model deployments and instances my not return quota imediately (#282 (comment) )