AI Prompt Decorator: Create a complex chat history - Plugin

Create a complex chat historyv3.6+

Creates a detailed chat history by configuring the plugin to prepend and append multiple messages, allowing any user to continue the conversation.

For a full walkthrough, see Guide survey classification behavior using the AI Prompt Decorator plugin.

Prerequisites

AI Proxy plugin configured with an LLM service

Set up the plugin

Add this section to your kong.yaml configuration file:

_format_version: "3.0"
plugins:
  - name: ai-prompt-decorator
    config:
      prompts:
        prepend:
        - role: system
          content: You are data scientist, specialising in survey analytics.
        - role: user
          content: Classify this test result set as positive, negative, or neutral.
        - role: assistant
          content: These tests are NEUTRAL.
        append:
        - role: user
          content: Do not mention any real participant names in your justification.

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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of 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-decorator
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
  labels:
    global: 'true'
config:
  prompts:
    prepend:
    - role: system
      content: You are data scientist, specialising in survey analytics.
    - role: user
      content: Classify this test result set as positive, negative, or neutral.
    - role: assistant
      content: These tests are NEUTRAL.
    append:
    - role: user
      content: Do not mention any real participant names in your justification.
plugin: ai-prompt-decorator
" | 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_decorator" "my_ai_prompt_decorator" {
  enabled = true

  config = {

    prompts = {
      prepend = [
        {
          role = "system"
          content = "You are data scientist, specialising in survey analytics."
        }, 

        {
          role = "user"
          content = "Classify this test result set as positive, negative, or neutral."
        }, 

        {
          role = "assistant"
          content = "These tests are NEUTRAL."
        }      ]
      append = [
        {
          role = "user"
          content = "Do not mention any real participant names in your justification."
        }      ]
    }
  }

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
}

Add this section to your kong.yaml configuration file:

_format_version: "3.0"
plugins:
  - name: ai-prompt-decorator
    service: serviceName|Id
    config:
      prompts:
        prepend:
        - role: system
          content: You are data scientist, specialising in survey analytics.
        - role: user
          content: Classify this test result set as positive, negative, or neutral.
        - role: assistant
          content: These tests are NEUTRAL.
        append:
        - role: user
          content: Do not mention any real participant names in your justification.

Make sure to replace the following placeholders with your own values:

serviceName|Id: The id or name of 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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

serviceName|Id: The id or name of 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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
serviceId: The id of 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-decorator
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
  prompts:
    prepend:
    - role: system
      content: You are data scientist, specialising in survey analytics.
    - role: user
      content: Classify this test result set as positive, negative, or neutral.
    - role: assistant
      content: These tests are NEUTRAL.
    append:
    - role: user
      content: Do not mention any real participant names in your justification.
plugin: ai-prompt-decorator
" | 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-decorator

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_decorator" "my_ai_prompt_decorator" {
  enabled = true

  config = {

    prompts = {
      prepend = [
        {
          role = "system"
          content = "You are data scientist, specialising in survey analytics."
        }, 

        {
          role = "user"
          content = "Classify this test result set as positive, negative, or neutral."
        }, 

        {
          role = "assistant"
          content = "These tests are NEUTRAL."
        }      ]
      append = [
        {
          role = "user"
          content = "Do not mention any real participant names in your justification."
        }      ]
    }
  }

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
  service = {
    id = konnect_gateway_service.my_service.id
  }
}

Add this section to your kong.yaml configuration file:

_format_version: "3.0"
plugins:
  - name: ai-prompt-decorator
    route: routeName|Id
    config:
      prompts:
        prepend:
        - role: system
          content: You are data scientist, specialising in survey analytics.
        - role: user
          content: Classify this test result set as positive, negative, or neutral.
        - role: assistant
          content: These tests are NEUTRAL.
        append:
        - role: user
          content: Do not mention any real participant names in your justification.

Make sure to replace the following placeholders with your own values:

routeName|Id: The id or name of 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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

routeName|Id: The id or name of 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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
routeId: The id of 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-decorator
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
  prompts:
    prepend:
    - role: system
      content: You are data scientist, specialising in survey analytics.
    - role: user
      content: Classify this test result set as positive, negative, or neutral.
    - role: assistant
      content: These tests are NEUTRAL.
    append:
    - role: user
      content: Do not mention any real participant names in your justification.
plugin: ai-prompt-decorator
" | 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-decorator

kubectl annotate -n kong ingress  konghq.com/plugins=ai-prompt-decorator

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_decorator" "my_ai_prompt_decorator" {
  enabled = true

  config = {

    prompts = {
      prepend = [
        {
          role = "system"
          content = "You are data scientist, specialising in survey analytics."
        }, 

        {
          role = "user"
          content = "Classify this test result set as positive, negative, or neutral."
        }, 

        {
          role = "assistant"
          content = "These tests are NEUTRAL."
        }      ]
      append = [
        {
          role = "user"
          content = "Do not mention any real participant names in your justification."
        }      ]
    }
  }

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
  route = {
    id = konnect_gateway_route.my_route.id
  }
}

Add this section to your kong.yaml configuration file:

_format_version: "3.0"
plugins:
  - name: ai-prompt-decorator
    consumer: consumerName|Id
    config:
      prompts:
        prepend:
        - role: system
          content: You are data scientist, specialising in survey analytics.
        - role: user
          content: Classify this test result set as positive, negative, or neutral.
        - role: assistant
          content: These tests are NEUTRAL.
        append:
        - role: user
          content: Do not mention any real participant names in your justification.

Make sure to replace the following placeholders with your own values:

consumerName|Id: The id or name of 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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

consumerName|Id: The id or name of 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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
consumerId: The id of 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-decorator
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
  prompts:
    prepend:
    - role: system
      content: You are data scientist, specialising in survey analytics.
    - role: user
      content: Classify this test result set as positive, negative, or neutral.
    - role: assistant
      content: These tests are NEUTRAL.
    append:
    - role: user
      content: Do not mention any real participant names in your justification.
plugin: ai-prompt-decorator
" | kubectl apply -f -

Next, apply the KongPlugin resource by annotating the KongConsumer resource:

kubectl annotate -n kong  CONSUMER_NAME konghq.com/plugins=ai-prompt-decorator

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_decorator" "my_ai_prompt_decorator" {
  enabled = true

  config = {

    prompts = {
      prepend = [
        {
          role = "system"
          content = "You are data scientist, specialising in survey analytics."
        }, 

        {
          role = "user"
          content = "Classify this test result set as positive, negative, or neutral."
        }, 

        {
          role = "assistant"
          content = "These tests are NEUTRAL."
        }      ]
      append = [
        {
          role = "user"
          content = "Do not mention any real participant names in your justification."
        }      ]
    }
  }

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
  consumer = {
    id = konnect_gateway_consumer.my_consumer.id
  }
}

Add this section to your kong.yaml configuration file:

_format_version: "3.0"
plugins:
  - name: ai-prompt-decorator
    consumer_group: consumerGroupName|Id
    config:
      prompts:
        prepend:
        - role: system
          content: You are data scientist, specialising in survey analytics.
        - role: user
          content: Classify this test result set as positive, negative, or neutral.
        - role: assistant
          content: These tests are NEUTRAL.
        append:
        - role: user
          content: Do not mention any real participant names in your justification.

Make sure to replace the following placeholders with your own values:

consumerGroupName|Id: The id or name of 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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

consumerGroupName|Id: The id or name of 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-decorator",
      "config": {
        "prompts": {
          "prepend": [
            {
              "role": "system",
              "content": "You are data scientist, specialising in survey analytics."
            },
            {
              "role": "user",
              "content": "Classify this test result set as positive, negative, or neutral."
            },
            {
              "role": "assistant",
              "content": "These tests are NEUTRAL."
            }
          ],
          "append": [
            {
              "role": "user",
              "content": "Do not mention any real participant names in your justification."
            }
          ]
        }
      }
    }
    '

Make sure to replace the following placeholders with your own values:

region: Geographic region where your Kong Konnect is hosted and operates.
controlPlaneId: The id of the control plane.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
consumerGroupId: The id of 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-decorator
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
  prompts:
    prepend:
    - role: system
      content: You are data scientist, specialising in survey analytics.
    - role: user
      content: Classify this test result set as positive, negative, or neutral.
    - role: assistant
      content: These tests are NEUTRAL.
    append:
    - role: user
      content: Do not mention any real participant names in your justification.
plugin: ai-prompt-decorator
" | kubectl apply -f -

Next, apply the KongPlugin resource by annotating the KongConsumerGroup resource:

kubectl annotate -n kong  CONSUMERGROUP_NAME konghq.com/plugins=ai-prompt-decorator

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_decorator" "my_ai_prompt_decorator" {
  enabled = true

  config = {

    prompts = {
      prepend = [
        {
          role = "system"
          content = "You are data scientist, specialising in survey analytics."
        }, 

        {
          role = "user"
          content = "Classify this test result set as positive, negative, or neutral."
        }, 

        {
          role = "assistant"
          content = "These tests are NEUTRAL."
        }      ]
      append = [
        {
          role = "user"
          content = "Do not mention any real participant names in your justification."
        }      ]
    }
  }

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
  consumer_group = {
    id = konnect_gateway_consumer_group.my_consumer_group.id
  }
}

AI Prompt Decorator

Create a complex chat historyv3.6+

Prerequisites

Set up the plugin

Help us make these docs great!

Still need help