Configure the AI Prompt Compressor pluginv3.11+
Configure the AI Prompt Compressor plugin
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-prompt-compressor
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
Make the following request:
curl -i -X POST http://localhost:8001/plugins/ \
--header "Accept: application/json" \
--header "Content-Type: application/json" \
--data '
{
"name": "ai-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
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 $KONNECT_TOKEN" \
--data '
{
"name": "ai-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongClusterPlugin
metadata:
name: ai-prompt-compressor
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
labels:
global: 'true'
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
plugin: ai-prompt-compressor
" | kubectl apply -f -
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_prompt_compressor" "my_ai_prompt_compressor" {
enabled = true
config = {
compressor_type = "rate"
compressor_url = "http://compress-service:8080"
keepalive_timeout = 60000
log_text_data = false
stop_on_error = true
timeout = 10000
compression_ranges = [
{
min_tokens = 20
max_tokens = 100
value = 0.8
},
{
min_tokens = 100
max_tokens = 1000000
value = 0.3
} ]
}
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
}
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-prompt-compressor
service: serviceName|Id
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
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-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
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 $KONNECT_TOKEN" \
--data '
{
"name": "ai-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
serviceId: Theidof the service the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-prompt-compressor
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
plugin: ai-prompt-compressor
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the service resource:
kubectl annotate -n kong service SERVICE_NAME konghq.com/plugins=ai-prompt-compressor
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_prompt_compressor" "my_ai_prompt_compressor" {
enabled = true
config = {
compressor_type = "rate"
compressor_url = "http://compress-service:8080"
keepalive_timeout = 60000
log_text_data = false
stop_on_error = true
timeout = 10000
compression_ranges = [
{
min_tokens = 20
max_tokens = 100
value = 0.8
},
{
min_tokens = 100
max_tokens = 1000000
value = 0.3
} ]
}
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
service = {
id = konnect_gateway_service.my_service.id
}
}
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-prompt-compressor
route: routeName|Id
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
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-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
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 $KONNECT_TOKEN" \
--data '
{
"name": "ai-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
routeId: Theidof the route the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-prompt-compressor
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
plugin: ai-prompt-compressor
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the httproute or ingress resource:
kubectl annotate -n kong httproute konghq.com/plugins=ai-prompt-compressor
kubectl annotate -n kong ingress konghq.com/plugins=ai-prompt-compressor
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_prompt_compressor" "my_ai_prompt_compressor" {
enabled = true
config = {
compressor_type = "rate"
compressor_url = "http://compress-service:8080"
keepalive_timeout = 60000
log_text_data = false
stop_on_error = true
timeout = 10000
compression_ranges = [
{
min_tokens = 20
max_tokens = 100
value = 0.8
},
{
min_tokens = 100
max_tokens = 1000000
value = 0.3
} ]
}
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
route = {
id = konnect_gateway_route.my_route.id
}
}
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-prompt-compressor
consumer: consumerName|Id
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
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-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
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 $KONNECT_TOKEN" \
--data '
{
"name": "ai-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
consumerId: Theidof the consumer the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-prompt-compressor
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
plugin: ai-prompt-compressor
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the KongConsumer resource:
kubectl annotate -n kong CONSUMER_NAME konghq.com/plugins=ai-prompt-compressor
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_prompt_compressor" "my_ai_prompt_compressor" {
enabled = true
config = {
compressor_type = "rate"
compressor_url = "http://compress-service:8080"
keepalive_timeout = 60000
log_text_data = false
stop_on_error = true
timeout = 10000
compression_ranges = [
{
min_tokens = 20
max_tokens = 100
value = 0.8
},
{
min_tokens = 100
max_tokens = 1000000
value = 0.3
} ]
}
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
consumer = {
id = konnect_gateway_consumer.my_consumer.id
}
}
Add this section to your declarative configuration file:
_format_version: "3.0"
plugins:
- name: ai-prompt-compressor
consumer_group: consumerGroupName|Id
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
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-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
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 $KONNECT_TOKEN" \
--data '
{
"name": "ai-prompt-compressor",
"config": {
"compressor_type": "rate",
"compressor_url": "http://compress-service:8080",
"keepalive_timeout": 60000,
"log_text_data": false,
"stop_on_error": true,
"timeout": 10000,
"compression_ranges": [
{
"min_tokens": 20,
"max_tokens": 100,
"value": 0.8
},
{
"min_tokens": 100,
"max_tokens": 1000000,
"value": 0.3
}
]
}
}
'
Make sure to replace the following placeholders with your own values:
-
region: Geographic region where your Kong Konnect is hosted and operates. -
controlPlaneId: Theidof the control plane. -
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account. -
consumerGroupId: Theidof the consumer group the plugin configuration will target.
See the Konnect API reference to learn about region-specific URLs and personal access tokens.
echo "
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
name: ai-prompt-compressor
namespace: kong
annotations:
kubernetes.io/ingress.class: kong
config:
compressor_type: rate
compressor_url: http://compress-service:8080
keepalive_timeout: 60000
log_text_data: false
stop_on_error: true
timeout: 10000
compression_ranges:
- min_tokens: 20
max_tokens: 100
value: 0.8
- min_tokens: 100
max_tokens: 1000000
value: 0.3
plugin: ai-prompt-compressor
" | kubectl apply -f -
Next, apply the KongPlugin resource by annotating the KongConsumerGroup resource:
kubectl annotate -n kong CONSUMERGROUP_NAME konghq.com/plugins=ai-prompt-compressor
Prerequisite: Configure your Personal Access Token
terraform {
required_providers {
konnect = {
source = "kong/konnect"
}
}
}
provider "konnect" {
personal_access_token = "$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_prompt_compressor" "my_ai_prompt_compressor" {
enabled = true
config = {
compressor_type = "rate"
compressor_url = "http://compress-service:8080"
keepalive_timeout = 60000
log_text_data = false
stop_on_error = true
timeout = 10000
compression_ranges = [
{
min_tokens = 20
max_tokens = 100
value = 0.8
},
{
min_tokens = 100
max_tokens = 1000000
value = 0.3
} ]
}
control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
consumer_group = {
id = konnect_gateway_consumer_group.my_consumer_group.id
}
}