OpenAI SDK: Multi-deployment chat routingv3.8+
Use separate Routes to map Azure OpenAI SDK requests to specific deployments of GPT-3.5 and GPT-4.
Using OpenAI SDK with the AI Proxy Advanced plugin, you can configure multiple Routes in Kong Gateway to represent different Azure OpenAI deployments.
Each Route maps a unique path segment (such as azure-gpt-3-5 or azure-gpt-4) to the corresponding deployment ID and model name.
This setup allows you to use a single Azure-compatible OpenAI SDK client to switch between deployments by changing only the base URL.
For example:
client = OpenAI(
base_url="http://127.0.0.1:8000/openai/deployments/azure-gpt-3-5"
)
Or:
client = OpenAI(
base_url="http://127.0.0.1:8000/openai/deployments/azure-gpt-4"
)
Kong Gateway reads the deployment path, maps it to the appropriate Azure deployment ID and model, and handles authentication automatically.
For this configuration to work properly, you need a Route with the following configuration:
routes: - name: azure-chat-gpt-3-5 paths: - "~/openai/deployments/azure-gpt-3-5/chat/completions$" methods: - POSTand:
routes: - name: azure-chat-gpt-4 paths: - "~/openai/deployments/azure-gpt-4/chat/completions$" methods: - POST
Prerequisites
- Azure account
Environment variables
-
AZURE_API_KEY: The API key to authenticate requests to Azure.
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-proxy-advanced
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
Make the following request:
curl -i -X POST http://localhost:8001/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make the following request:
curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/plugins/ \
--header "accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $KONNECT_TOKEN" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongClusterPlugin
metadata:
name: ai-proxy-advanced
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
labels:
global: 'true'
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
plugin: ai-proxy-advanced
" | kubectl apply -f -
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$KONNECT_TOKEN"
server_url = "https://us.api.konghq.com/"
}
Add the following to your Terraform configuration to create a Konnect Gateway Plugin:
resource "konnect_gateway_plugin_ai_proxy_advanced" "my_ai_proxy_advanced" {
enabled = true
config = [
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-35-turbo"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-3-5"
}
}
} ]
},
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-4"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-4"
}
}
} ]
} ]
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
}
This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.
variable "azure_api_key" {
type = string
}
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-proxy-advanced
service: serviceName|Id
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
Make sure to replace the following placeholders with your own values:
-
serviceName|Id: Theidornameof the service the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/services/{serviceName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
serviceName|Id: Theidornameof the service the plugin configuration will target.
Make the following request:
curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/services/{serviceId}/plugins/ \
--header "accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $KONNECT_TOKEN" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
serviceId: Theidof the service the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-proxy-advanced
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
plugin: ai-proxy-advanced
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the service resource:
kubectl annotate -n kong service SERVICE_NAME konghq.com/plugins=ai-proxy-advanced
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$KONNECT_TOKEN"
server_url = "https://us.api.konghq.com/"
}
Add the following to your Terraform configuration to create a Konnect Gateway Plugin:
resource "konnect_gateway_plugin_ai_proxy_advanced" "my_ai_proxy_advanced" {
enabled = true
config = [
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-35-turbo"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-3-5"
}
}
} ]
},
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-4"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-4"
}
}
} ]
} ]
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
service = {
id = konnect_gateway_service.my_service.id
}
}
This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.
variable "azure_api_key" {
type = string
}
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-proxy-advanced
route: routeName|Id
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
Make sure to replace the following placeholders with your own values:
-
routeName|Id: Theidornameof the route the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/routes/{routeName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
routeName|Id: Theidornameof the route the plugin configuration will target.
Make the following request:
curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/routes/{routeId}/plugins/ \
--header "accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $KONNECT_TOKEN" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
routeId: Theidof the route the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-proxy-advanced
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
plugin: ai-proxy-advanced
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the httproute or ingress resource:
kubectl annotate -n kong httproute konghq.com/plugins=ai-proxy-advanced
kubectl annotate -n kong ingress konghq.com/plugins=ai-proxy-advanced
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$KONNECT_TOKEN"
server_url = "https://us.api.konghq.com/"
}
Add the following to your Terraform configuration to create a Konnect Gateway Plugin:
resource "konnect_gateway_plugin_ai_proxy_advanced" "my_ai_proxy_advanced" {
enabled = true
config = [
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-35-turbo"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-3-5"
}
}
} ]
},
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-4"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-4"
}
}
} ]
} ]
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
route = {
id = konnect_gateway_route.my_route.id
}
}
This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.
variable "azure_api_key" {
type = string
}
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-proxy-advanced
consumer: consumerName|Id
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
Make sure to replace the following placeholders with your own values:
-
consumerName|Id: Theidornameof the consumer the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/consumers/{consumerName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
consumerName|Id: Theidornameof the consumer the plugin configuration will target.
Make the following request:
curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/consumers/{consumerId}/plugins/ \
--header "accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $KONNECT_TOKEN" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
consumerId: Theidof the consumer the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-proxy-advanced
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
plugin: ai-proxy-advanced
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the KongConsumer resource:
kubectl annotate -n kong CONSUMER_NAME konghq.com/plugins=ai-proxy-advanced
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$KONNECT_TOKEN"
server_url = "https://us.api.konghq.com/"
}
Add the following to your Terraform configuration to create a Konnect Gateway Plugin:
resource "konnect_gateway_plugin_ai_proxy_advanced" "my_ai_proxy_advanced" {
enabled = true
config = [
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-35-turbo"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-3-5"
}
}
} ]
},
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-4"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-4"
}
}
} ]
} ]
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
consumer = {
id = konnect_gateway_consumer.my_consumer.id
}
}
This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.
variable "azure_api_key" {
type = string
}
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-proxy-advanced
consumer_group: consumerGroupName|Id
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: "${azure_key}"
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
Make sure to replace the following placeholders with your own values:
-
consumerGroupName|Id: Theidornameof the consumer group the plugin configuration will target.
Make the following request:
curl -i -X POST http://localhost:8001/consumer_groups/{consumerGroupName|Id}/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
consumerGroupName|Id: Theidornameof the consumer group the plugin configuration will target.
Make the following request:
curl -X POST https://{region}.api.konghq.com/v2/control-planes/{controlPlaneId}/core-entities/consumer_groups/{consumerGroupId}/plugins/ \
--header "accept: application/json" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer $KONNECT_TOKEN" \
--data '
{
"name": "ai-proxy-advanced",
"config": [
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-35-turbo",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-3-5"
}
}
}
]
},
{
"targets": [
{
"route_type": "llm/v1/chat",
"auth": {
"header_name": "api-key",
"header_value": "${azure_key}"
},
"logging": {
"log_statistics": true,
"log_payloads": false
},
"model": {
"provider": "azure",
"name": "gpt-4",
"options": {
"azure_instance": "my-openai-instace",
"azure_deployment_id": "my-gpt-4"
}
}
}
]
}
]
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
consumerGroupId: Theidof the consumer group the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-proxy-advanced
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-35-turbo
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-3-5
- targets:
- route_type: llm/v1/chat
auth:
header_name: api-key
header_value: '${azure_key}'
logging:
log_statistics: true
log_payloads: false
model:
provider: azure
name: gpt-4
options:
azure_instance: my-openai-instace
azure_deployment_id: my-gpt-4
plugin: ai-proxy-advanced
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the KongConsumerGroup resource:
kubectl annotate -n kong CONSUMERGROUP_NAME konghq.com/plugins=ai-proxy-advanced
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$KONNECT_TOKEN"
server_url = "https://us.api.konghq.com/"
}
Add the following to your Terraform configuration to create a Konnect Gateway Plugin:
resource "konnect_gateway_plugin_ai_proxy_advanced" "my_ai_proxy_advanced" {
enabled = true
config = [
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-35-turbo"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-3-5"
}
}
} ]
},
{
targets = [
{
route_type = "llm/v1/chat"
auth = {
header_name = "api-key"
header_value = "${azure_key}"
}
logging = {
log_statistics = true
log_payloads = false
}
model = {
provider = "azure"
name = "gpt-4"
options = {
azure_instance = "my-openai-instace"
azure_deployment_id = "my-gpt-4"
}
}
} ]
} ]
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
consumer_group = {
id = konnect_gateway_consumer_group.my_consumer_group.id
}
}
This example requires the following variables to be added to your manifest. You can specify values at runtime by setting TF_VAR_name=value.
variable "azure_api_key" {
type = string
}