AI Proxy: OpenAI SDK: Use an unsupported LLM model - Plugin

OpenAI SDK: Use an unsupported LLM modelv3.6+

Kong Gateway can attempt to support models that aren’t pre-configured with format transformers or are untested.

For this plugin to work properly, you need a Gateway Route with the following configuration:
routes:
 - name: openai-any
   paths:
     - "~/openai/(?<op_path>[^#?]+)"
   methods:
     - POST

Caution: The following use cases are unsupported but may work depending on your setup. Use at your own discretion.

When setting up for unsupported models, you must configure the route_type to preserve mode. This approach ensures that the request and response are passed through without any transformations.

For example, using the following configuration with multipart/form-data formatting, you can POST a file for transcription using the Whisper-2 transcription model:

  curl --location 'http://localhost:8000/openai/v1/audio/transcriptions' \
      --form 'model=whisper-2' \
      --form 'file=@"me_saying_hello.m4a"'

The response comes back unaltered:

  {
    "text": "Hello!"
  }

Prerequisites

OpenAI account

Environment variables

OPENAI_API_KEY: The API key used to authenticate requests to OpenAI.

Set up the plugin

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    config:
      route_type: preserve
      auth:
        header_name: Authorization
        header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: whisper-2
        options:
          upstream_path: "$(uri_captures.op_path)"

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",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
  labels:
    global: 'true'
config:
  route_type: preserve
  auth:
    header_name: Authorization
    header_value: Bearer $OPENAI_API_KEY
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: whisper-2
    options:
      upstream_path: '$(uri_captures.op_path)'
plugin: ai-proxy
" | 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" "my_ai_proxy" {
  enabled = true

  config = {
    route_type = "preserve"

    auth = {
      header_name = "Authorization"
      header_value = "Bearer var.openai_api_key"
    }

    logging = {
      log_statistics = true
      log_payloads = false
    }

    model = {
      provider = "openai"
      name = "whisper-2"

      options = {
        upstream_path = "$(uri_captures.op_path)"
      }
    }
  }

  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 "openai_api_key" {
  type = string
}

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    service: serviceName|Id
    config:
      route_type: preserve
      auth:
        header_name: Authorization
        header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: whisper-2
        options:
          upstream_path: "$(uri_captures.op_path)"

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-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
  route_type: preserve
  auth:
    header_name: Authorization
    header_value: Bearer $OPENAI_API_KEY
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: whisper-2
    options:
      upstream_path: '$(uri_captures.op_path)'
plugin: ai-proxy
" | 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

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" "my_ai_proxy" {
  enabled = true

  config = {
    route_type = "preserve"

    auth = {
      header_name = "Authorization"
      header_value = "Bearer var.openai_api_key"
    }

    logging = {
      log_statistics = true
      log_payloads = false
    }

    model = {
      provider = "openai"
      name = "whisper-2"

      options = {
        upstream_path = "$(uri_captures.op_path)"
      }
    }
  }

  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 "openai_api_key" {
  type = string
}

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    route: routeName|Id
    config:
      route_type: preserve
      auth:
        header_name: Authorization
        header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: whisper-2
        options:
          upstream_path: "$(uri_captures.op_path)"

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-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
  route_type: preserve
  auth:
    header_name: Authorization
    header_value: Bearer $OPENAI_API_KEY
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: whisper-2
    options:
      upstream_path: '$(uri_captures.op_path)'
plugin: ai-proxy
" | 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

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

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" "my_ai_proxy" {
  enabled = true

  config = {
    route_type = "preserve"

    auth = {
      header_name = "Authorization"
      header_value = "Bearer var.openai_api_key"
    }

    logging = {
      log_statistics = true
      log_payloads = false
    }

    model = {
      provider = "openai"
      name = "whisper-2"

      options = {
        upstream_path = "$(uri_captures.op_path)"
      }
    }
  }

  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 "openai_api_key" {
  type = string
}

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    consumer: consumerName|Id
    config:
      route_type: preserve
      auth:
        header_name: Authorization
        header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: whisper-2
        options:
          upstream_path: "$(uri_captures.op_path)"

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-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
  route_type: preserve
  auth:
    header_name: Authorization
    header_value: Bearer $OPENAI_API_KEY
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: whisper-2
    options:
      upstream_path: '$(uri_captures.op_path)'
plugin: ai-proxy
" | kubectl apply -f -

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

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

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" "my_ai_proxy" {
  enabled = true

  config = {
    route_type = "preserve"

    auth = {
      header_name = "Authorization"
      header_value = "Bearer var.openai_api_key"
    }

    logging = {
      log_statistics = true
      log_payloads = false
    }

    model = {
      provider = "openai"
      name = "whisper-2"

      options = {
        upstream_path = "$(uri_captures.op_path)"
      }
    }
  }

  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 "openai_api_key" {
  type = string
}

Add this section to your declarative configuration file:

_format_version: "3.0"
plugins:
  - name: ai-proxy
    consumer_group: consumerGroupName|Id
    config:
      route_type: preserve
      auth:
        header_name: Authorization
        header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
      logging:
        log_statistics: true
        log_payloads: false
      model:
        provider: openai
        name: whisper-2
        options:
          upstream_path: "$(uri_captures.op_path)"

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-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "preserve",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "logging": {
          "log_statistics": true,
          "log_payloads": false
        },
        "model": {
          "provider": "openai",
          "name": "whisper-2",
          "options": {
            "upstream_path": "$(uri_captures.op_path)"
          }
        }
      }
    }
    '

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-proxy
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
config:
  route_type: preserve
  auth:
    header_name: Authorization
    header_value: Bearer $OPENAI_API_KEY
  logging:
    log_statistics: true
    log_payloads: false
  model:
    provider: openai
    name: whisper-2
    options:
      upstream_path: '$(uri_captures.op_path)'
plugin: ai-proxy
" | kubectl apply -f -

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

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

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" "my_ai_proxy" {
  enabled = true

  config = {
    route_type = "preserve"

    auth = {
      header_name = "Authorization"
      header_value = "Bearer var.openai_api_key"
    }

    logging = {
      log_statistics = true
      log_payloads = false
    }

    model = {
      provider = "openai"
      name = "whisper-2"

      options = {
        upstream_path = "$(uri_captures.op_path)"
      }
    }
  }

  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 "openai_api_key" {
  type = string
}

AI Proxy

OpenAI SDK: Use an unsupported LLM modelv3.6+

Prerequisites

Environment variables

Set up the plugin

Help us make these docs great!

Still need help