OpenAI
Azure OpenAI Service provides REST API access to OpenAI's powerful language models including GPT-4, GPT-3, Codex, and Embeddings models.
Example yaml file:
apiVersion: azure.boundless.software/v1alpha1
kind: OpenAI
metadata:
name: openai-sample
spec:
provider:
region: "eastus"
resourceGroup: "my-resource-group"
deployments:
gpt4:
version: "0301"
model: "gpt-4"
type: "model"
tokenRateLimit: 5000
embedding:
version: "2"
model: "text-embedding-ada-002"
type: "embedding"
networking:
privateAccessOnly: true
ipRules:
- "203.0.113.0/24"
subnetIDs:
- "/subscriptions/00000000-0000-0000-0000-000000000000/resourceGroups/myResourceGroup/providers/Microsoft.Network/virtualNetworks/myVNet/subnets/mySubnet"
privateEndpoints:
- subnetID: "/subscriptions/00000000-0000-0000-0000-000000000000/resourceGroups/myResourceGroup/providers/Microsoft.Network/virtualNetworks/myVNet/subnets/mySubnet"
location: "eastus"
tags:
environment: "production"
department: "ai"
Name | Type | Description |
---|
provider* | AzureProviderSpec | The provider for the OpenAI resource. |
resourceGroup* | string | The resource group for the OpenAI resource. |
deployments | map[string]DeploymentSpec | The deployments for the OpenAI resource. |
networking | NetworkingSpec | The networking configuration for the OpenAI resource. |
privateEndpoints | []PrivateEndpointSpec | The private endpoints for the OpenAI resource. |
tags | map[string]*string | Tags to apply to the OpenAI resource. |
NetworkingSpec
Name | Type | Description |
---|
privateAccessOnly | bool | Whether to restrict access to private networks only. |
ipRules | []string | The IP ranges allowed to access the OpenAI resource. |
subnetIDs | []string | The subnet IDs for the OpenAI resource to be accessed from. |
DeploymentSpec
Name | Type | Description |
---|
version | string | The version of the deployment. |
model | string | The model of the deployment. |
type | string | The type of the deployment. |
tokenRateLimit | int32 | The token rate limit of the deployment. |
PrivateEndpointSpec
Name | Type | Description |
---|
subnetID* | string | The subnet ID for the private endpoint. |
location* | string | The location of the subnet. |
DeploymentStatus
Name | Type | Description |
---|
condition | metav1.Condition | The condition of the deployment. |
id | string | The ID of the deployment. |
version | string | The version of the deployment. |
model | string | The model of the deployment. |
type | string | The type of the deployment. |
tokenRateLimit | int32 | The token rate limit of the deployment. |
Outputs
Name | Type | Description |
---|
condition | metav1.Condition | Current condition of the OpenAI resource. |
resourceGroup | string | The resource group of the OpenAI resource. |
deployments | map[string]DeploymentStatus | Status of the deployments. |
privateEndpoints | map[string]PrivateEndpointStatus | Status of the private endpoints. |
networking | NetworkingStatus | Status of the networking configuration. |
location | string | The location of the OpenAI resource. |
name | string | The name of the OpenAI resource. |
id | string | The ID of the OpenAI resource. |
endpoint | string | The endpoints of the OpenAI resource. |
keys | KeysStatus | The keys of the OpenAI resource. |
NetworkingStatus
Name | Type | Description |
---|
privateAccessOnly | bool | Whether access is restricted to private networks. |
ipRules | []string | The IP ranges allowed to access the resource. |
subnetIDs | []string | The subnet IDs for resource access. |
KeysStatus
Name | Type | Description |
---|
primaryKey | string | The primary key of the OpenAI resource. |
secondaryKey | string | The secondary key of the OpenAI resource. |