AI Semantic Response Guard: Allow and deny responses using Valkey as a vector database - Plugin

Allow and deny responses using Valkey as a vector databasev3.14+

The AI Semantic Response Guard plugin analyzes the full response from an LLM service and filters it based on semantic similarity to configured allow or deny patterns.

Deny rules take precedence over allow rules. Responses matching a deny pattern are blocked, even if they also match an allow pattern. Responses not matching any allow pattern are blocked when allow rules are set.

Valkey is automatically detected when using the redis vectordb strategy. Kong Gateway queries the server and uses the Valkey-specific driver when it detects a Valkey backend.

Prerequisites

AI Proxy plugin or AI Proxy Advanced plugin configured with an LLM service.
A Valkey 8.x instance.
Port 6379, or your custom Valkey port, is open and reachable from Kong Gateway.

Environment variables

OPENAI_API_KEY: Your OpenAI API key
VALKEY_HOST: The host where your Valkey instance runs

Set up the plugin

Add this section to your kong.yaml configuration file:

kong.yaml

Copied!

_format_version: "3.0"
plugins:
  - name: ai-semantic-response-guard
    config:
      embeddings:
        auth:
          header_name: Authorization
          header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
        model:
          name: text-embedding-3-small
          provider: openai
      search:
        threshold: 0.7
      vectordb:
        strategy: redis
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        redis:
          host: ${{ env "DECK_VALKEY_HOST" }}
          port: 6379
      rules:
        allow_responses:
        - Network troubleshooting and diagnostics
        - Cloud infrastructure management (AWS, Azure, GCP)
        - Cybersecurity best practices and incident response
        - DevOps workflows and automation
        - Programming concepts and language usage
        - IT policy and compliance guidance
        - Software development lifecycle and CI/CD
        - Documentation writing and technical explanation
        - System administration and configuration
        - Productivity and collaboration tools usage
        deny_responses:
        - Hacking techniques or penetration testing without authorization
        - Bypassing software licensing or digital rights management
        - Instructions on exploiting vulnerabilities or writing malware
        - Circumventing security controls or access restrictions
        - Gathering personal or confidential employee information
        - Using AI to impersonate or phish others
        - Social engineering tactics or manipulation techniques
        - Guidance on violating company IT policies
        - Content unrelated to work, such as entertainment or dating
        - Political, religious, or sensitive non-work-related discussions

Make the following request:

curl -i -X POST http://localhost:8001/plugins/ \
    --header "Accept: application/json" \
    --header "Content-Type: application/json" \
    --data '
    {
      "name": "ai-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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

region: Geographic region where your Kong Konnect is hosted and operates.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
controlPlaneId: The id of the control plane.

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-semantic-response-guard
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
    konghq.com/tags: ''
  labels:
    global: 'true'
config:
  embeddings:
    auth:
      header_name: Authorization
      header_value: Bearer $OPENAI_API_KEY
    model:
      name: text-embedding-3-small
      provider: openai
  search:
    threshold: 0.7
  vectordb:
    strategy: redis
    distance_metric: cosine
    threshold: 0.7
    dimensions: 1024
    redis:
      host: '$VALKEY_HOST'
      port: 6379
  rules:
    allow_responses:
    - Network troubleshooting and diagnostics
    - Cloud infrastructure management (AWS, Azure, GCP)
    - Cybersecurity best practices and incident response
    - DevOps workflows and automation
    - Programming concepts and language usage
    - IT policy and compliance guidance
    - Software development lifecycle and CI/CD
    - Documentation writing and technical explanation
    - System administration and configuration
    - Productivity and collaboration tools usage
    deny_responses:
    - Hacking techniques or penetration testing without authorization
    - Bypassing software licensing or digital rights management
    - Instructions on exploiting vulnerabilities or writing malware
    - Circumventing security controls or access restrictions
    - Gathering personal or confidential employee information
    - Using AI to impersonate or phish others
    - Social engineering tactics or manipulation techniques
    - Guidance on violating company IT policies
    - Content unrelated to work, such as entertainment or dating
    - Political, religious, or sensitive non-work-related discussions
plugin: ai-semantic-response-guard
" | kubectl apply -f -

Copied!

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/"
}

Copied!

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_semantic_response_guard" "my_ai_semantic_response_guard" {
  enabled = true

  config = {

    embeddings = {

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

      model = {
        name = "text-embedding-3-small"
        provider = "openai"
      }
    }

    search = {
      threshold = 0.7
    }

    vectordb = {
      strategy = "redis"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      redis = {
        host = var.valkey_host
        port = 6379
      }
    }

    rules = {
      allow_responses = ["Network troubleshooting and diagnostics", "Cloud infrastructure management (AWS, Azure, GCP)", "Cybersecurity best practices and incident response", "DevOps workflows and automation", "Programming concepts and language usage", "IT policy and compliance guidance", "Software development lifecycle and CI/CD", "Documentation writing and technical explanation", "System administration and configuration", "Productivity and collaboration tools usage"]
      deny_responses = ["Hacking techniques or penetration testing without authorization", "Bypassing software licensing or digital rights management", "Instructions on exploiting vulnerabilities or writing malware", "Circumventing security controls or access restrictions", "Gathering personal or confidential employee information", "Using AI to impersonate or phish others", "Social engineering tactics or manipulation techniques", "Guidance on violating company IT policies", "Content unrelated to work, such as entertainment or dating", "Political, religious, or sensitive non-work-related discussions"]
    }
  }
  tags = []

  control_plane_id = konnect_gateway_control_plane.my_konnect_cp.id
}

Copied!

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 "valkey_host" {
  type = string
}

Copied!

Add this section to your kong.yaml configuration file:

kong.yaml

Copied!

_format_version: "3.0"
plugins:
  - name: ai-semantic-response-guard
    service: serviceName|Id
    config:
      embeddings:
        auth:
          header_name: Authorization
          header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
        model:
          name: text-embedding-3-small
          provider: openai
      search:
        threshold: 0.7
      vectordb:
        strategy: redis
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        redis:
          host: ${{ env "DECK_VALKEY_HOST" }}
          port: 6379
      rules:
        allow_responses:
        - Network troubleshooting and diagnostics
        - Cloud infrastructure management (AWS, Azure, GCP)
        - Cybersecurity best practices and incident response
        - DevOps workflows and automation
        - Programming concepts and language usage
        - IT policy and compliance guidance
        - Software development lifecycle and CI/CD
        - Documentation writing and technical explanation
        - System administration and configuration
        - Productivity and collaboration tools usage
        deny_responses:
        - Hacking techniques or penetration testing without authorization
        - Bypassing software licensing or digital rights management
        - Instructions on exploiting vulnerabilities or writing malware
        - Circumventing security controls or access restrictions
        - Gathering personal or confidential employee information
        - Using AI to impersonate or phish others
        - Social engineering tactics or manipulation techniques
        - Guidance on violating company IT policies
        - Content unrelated to work, such as entertainment or dating
        - Political, religious, or sensitive non-work-related discussions

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-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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

region: Geographic region where your Kong Konnect is hosted and operates.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
controlPlaneId: The id of the control plane.
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-semantic-response-guard
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
    konghq.com/tags: ''
config:
  embeddings:
    auth:
      header_name: Authorization
      header_value: Bearer $OPENAI_API_KEY
    model:
      name: text-embedding-3-small
      provider: openai
  search:
    threshold: 0.7
  vectordb:
    strategy: redis
    distance_metric: cosine
    threshold: 0.7
    dimensions: 1024
    redis:
      host: '$VALKEY_HOST'
      port: 6379
  rules:
    allow_responses:
    - Network troubleshooting and diagnostics
    - Cloud infrastructure management (AWS, Azure, GCP)
    - Cybersecurity best practices and incident response
    - DevOps workflows and automation
    - Programming concepts and language usage
    - IT policy and compliance guidance
    - Software development lifecycle and CI/CD
    - Documentation writing and technical explanation
    - System administration and configuration
    - Productivity and collaboration tools usage
    deny_responses:
    - Hacking techniques or penetration testing without authorization
    - Bypassing software licensing or digital rights management
    - Instructions on exploiting vulnerabilities or writing malware
    - Circumventing security controls or access restrictions
    - Gathering personal or confidential employee information
    - Using AI to impersonate or phish others
    - Social engineering tactics or manipulation techniques
    - Guidance on violating company IT policies
    - Content unrelated to work, such as entertainment or dating
    - Political, religious, or sensitive non-work-related discussions
plugin: ai-semantic-response-guard
" | kubectl apply -f -

Copied!

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

kubectl annotate -n kong service SERVICE_NAME konghq.com/plugins=ai-semantic-response-guard

Copied!

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/"
}

Copied!

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_semantic_response_guard" "my_ai_semantic_response_guard" {
  enabled = true

  config = {

    embeddings = {

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

      model = {
        name = "text-embedding-3-small"
        provider = "openai"
      }
    }

    search = {
      threshold = 0.7
    }

    vectordb = {
      strategy = "redis"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      redis = {
        host = var.valkey_host
        port = 6379
      }
    }

    rules = {
      allow_responses = ["Network troubleshooting and diagnostics", "Cloud infrastructure management (AWS, Azure, GCP)", "Cybersecurity best practices and incident response", "DevOps workflows and automation", "Programming concepts and language usage", "IT policy and compliance guidance", "Software development lifecycle and CI/CD", "Documentation writing and technical explanation", "System administration and configuration", "Productivity and collaboration tools usage"]
      deny_responses = ["Hacking techniques or penetration testing without authorization", "Bypassing software licensing or digital rights management", "Instructions on exploiting vulnerabilities or writing malware", "Circumventing security controls or access restrictions", "Gathering personal or confidential employee information", "Using AI to impersonate or phish others", "Social engineering tactics or manipulation techniques", "Guidance on violating company IT policies", "Content unrelated to work, such as entertainment or dating", "Political, religious, or sensitive non-work-related discussions"]
    }
  }
  tags = []

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

Copied!

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 "valkey_host" {
  type = string
}

Copied!

Add this section to your kong.yaml configuration file:

kong.yaml

Copied!

_format_version: "3.0"
plugins:
  - name: ai-semantic-response-guard
    route: routeName|Id
    config:
      embeddings:
        auth:
          header_name: Authorization
          header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
        model:
          name: text-embedding-3-small
          provider: openai
      search:
        threshold: 0.7
      vectordb:
        strategy: redis
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        redis:
          host: ${{ env "DECK_VALKEY_HOST" }}
          port: 6379
      rules:
        allow_responses:
        - Network troubleshooting and diagnostics
        - Cloud infrastructure management (AWS, Azure, GCP)
        - Cybersecurity best practices and incident response
        - DevOps workflows and automation
        - Programming concepts and language usage
        - IT policy and compliance guidance
        - Software development lifecycle and CI/CD
        - Documentation writing and technical explanation
        - System administration and configuration
        - Productivity and collaboration tools usage
        deny_responses:
        - Hacking techniques or penetration testing without authorization
        - Bypassing software licensing or digital rights management
        - Instructions on exploiting vulnerabilities or writing malware
        - Circumventing security controls or access restrictions
        - Gathering personal or confidential employee information
        - Using AI to impersonate or phish others
        - Social engineering tactics or manipulation techniques
        - Guidance on violating company IT policies
        - Content unrelated to work, such as entertainment or dating
        - Political, religious, or sensitive non-work-related discussions

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-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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

region: Geographic region where your Kong Konnect is hosted and operates.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
controlPlaneId: The id of the control plane.
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-semantic-response-guard
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
    konghq.com/tags: ''
config:
  embeddings:
    auth:
      header_name: Authorization
      header_value: Bearer $OPENAI_API_KEY
    model:
      name: text-embedding-3-small
      provider: openai
  search:
    threshold: 0.7
  vectordb:
    strategy: redis
    distance_metric: cosine
    threshold: 0.7
    dimensions: 1024
    redis:
      host: '$VALKEY_HOST'
      port: 6379
  rules:
    allow_responses:
    - Network troubleshooting and diagnostics
    - Cloud infrastructure management (AWS, Azure, GCP)
    - Cybersecurity best practices and incident response
    - DevOps workflows and automation
    - Programming concepts and language usage
    - IT policy and compliance guidance
    - Software development lifecycle and CI/CD
    - Documentation writing and technical explanation
    - System administration and configuration
    - Productivity and collaboration tools usage
    deny_responses:
    - Hacking techniques or penetration testing without authorization
    - Bypassing software licensing or digital rights management
    - Instructions on exploiting vulnerabilities or writing malware
    - Circumventing security controls or access restrictions
    - Gathering personal or confidential employee information
    - Using AI to impersonate or phish others
    - Social engineering tactics or manipulation techniques
    - Guidance on violating company IT policies
    - Content unrelated to work, such as entertainment or dating
    - Political, religious, or sensitive non-work-related discussions
plugin: ai-semantic-response-guard
" | kubectl apply -f -

Copied!

Next, apply the KongPlugin resource by annotating the httproute or ingress resource:

kubectl annotate -n kong httproute  konghq.com/plugins=ai-semantic-response-guard

Copied!

kubectl annotate -n kong ingress  konghq.com/plugins=ai-semantic-response-guard

Copied!

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/"
}

Copied!

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_semantic_response_guard" "my_ai_semantic_response_guard" {
  enabled = true

  config = {

    embeddings = {

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

      model = {
        name = "text-embedding-3-small"
        provider = "openai"
      }
    }

    search = {
      threshold = 0.7
    }

    vectordb = {
      strategy = "redis"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      redis = {
        host = var.valkey_host
        port = 6379
      }
    }

    rules = {
      allow_responses = ["Network troubleshooting and diagnostics", "Cloud infrastructure management (AWS, Azure, GCP)", "Cybersecurity best practices and incident response", "DevOps workflows and automation", "Programming concepts and language usage", "IT policy and compliance guidance", "Software development lifecycle and CI/CD", "Documentation writing and technical explanation", "System administration and configuration", "Productivity and collaboration tools usage"]
      deny_responses = ["Hacking techniques or penetration testing without authorization", "Bypassing software licensing or digital rights management", "Instructions on exploiting vulnerabilities or writing malware", "Circumventing security controls or access restrictions", "Gathering personal or confidential employee information", "Using AI to impersonate or phish others", "Social engineering tactics or manipulation techniques", "Guidance on violating company IT policies", "Content unrelated to work, such as entertainment or dating", "Political, religious, or sensitive non-work-related discussions"]
    }
  }
  tags = []

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

Copied!

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 "valkey_host" {
  type = string
}

Copied!

Add this section to your kong.yaml configuration file:

kong.yaml

Copied!

_format_version: "3.0"
plugins:
  - name: ai-semantic-response-guard
    consumer: consumerName|Id
    config:
      embeddings:
        auth:
          header_name: Authorization
          header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
        model:
          name: text-embedding-3-small
          provider: openai
      search:
        threshold: 0.7
      vectordb:
        strategy: redis
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        redis:
          host: ${{ env "DECK_VALKEY_HOST" }}
          port: 6379
      rules:
        allow_responses:
        - Network troubleshooting and diagnostics
        - Cloud infrastructure management (AWS, Azure, GCP)
        - Cybersecurity best practices and incident response
        - DevOps workflows and automation
        - Programming concepts and language usage
        - IT policy and compliance guidance
        - Software development lifecycle and CI/CD
        - Documentation writing and technical explanation
        - System administration and configuration
        - Productivity and collaboration tools usage
        deny_responses:
        - Hacking techniques or penetration testing without authorization
        - Bypassing software licensing or digital rights management
        - Instructions on exploiting vulnerabilities or writing malware
        - Circumventing security controls or access restrictions
        - Gathering personal or confidential employee information
        - Using AI to impersonate or phish others
        - Social engineering tactics or manipulation techniques
        - Guidance on violating company IT policies
        - Content unrelated to work, such as entertainment or dating
        - Political, religious, or sensitive non-work-related discussions

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-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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

region: Geographic region where your Kong Konnect is hosted and operates.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
controlPlaneId: The id of the control plane.
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-semantic-response-guard
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
    konghq.com/tags: ''
config:
  embeddings:
    auth:
      header_name: Authorization
      header_value: Bearer $OPENAI_API_KEY
    model:
      name: text-embedding-3-small
      provider: openai
  search:
    threshold: 0.7
  vectordb:
    strategy: redis
    distance_metric: cosine
    threshold: 0.7
    dimensions: 1024
    redis:
      host: '$VALKEY_HOST'
      port: 6379
  rules:
    allow_responses:
    - Network troubleshooting and diagnostics
    - Cloud infrastructure management (AWS, Azure, GCP)
    - Cybersecurity best practices and incident response
    - DevOps workflows and automation
    - Programming concepts and language usage
    - IT policy and compliance guidance
    - Software development lifecycle and CI/CD
    - Documentation writing and technical explanation
    - System administration and configuration
    - Productivity and collaboration tools usage
    deny_responses:
    - Hacking techniques or penetration testing without authorization
    - Bypassing software licensing or digital rights management
    - Instructions on exploiting vulnerabilities or writing malware
    - Circumventing security controls or access restrictions
    - Gathering personal or confidential employee information
    - Using AI to impersonate or phish others
    - Social engineering tactics or manipulation techniques
    - Guidance on violating company IT policies
    - Content unrelated to work, such as entertainment or dating
    - Political, religious, or sensitive non-work-related discussions
plugin: ai-semantic-response-guard
" | kubectl apply -f -

Copied!

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

kubectl annotate -n kong kongconsumer CONSUMER_NAME konghq.com/plugins=ai-semantic-response-guard

Copied!

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/"
}

Copied!

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_semantic_response_guard" "my_ai_semantic_response_guard" {
  enabled = true

  config = {

    embeddings = {

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

      model = {
        name = "text-embedding-3-small"
        provider = "openai"
      }
    }

    search = {
      threshold = 0.7
    }

    vectordb = {
      strategy = "redis"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      redis = {
        host = var.valkey_host
        port = 6379
      }
    }

    rules = {
      allow_responses = ["Network troubleshooting and diagnostics", "Cloud infrastructure management (AWS, Azure, GCP)", "Cybersecurity best practices and incident response", "DevOps workflows and automation", "Programming concepts and language usage", "IT policy and compliance guidance", "Software development lifecycle and CI/CD", "Documentation writing and technical explanation", "System administration and configuration", "Productivity and collaboration tools usage"]
      deny_responses = ["Hacking techniques or penetration testing without authorization", "Bypassing software licensing or digital rights management", "Instructions on exploiting vulnerabilities or writing malware", "Circumventing security controls or access restrictions", "Gathering personal or confidential employee information", "Using AI to impersonate or phish others", "Social engineering tactics or manipulation techniques", "Guidance on violating company IT policies", "Content unrelated to work, such as entertainment or dating", "Political, religious, or sensitive non-work-related discussions"]
    }
  }
  tags = []

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

Copied!

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 "valkey_host" {
  type = string
}

Copied!

Add this section to your kong.yaml configuration file:

kong.yaml

Copied!

_format_version: "3.0"
plugins:
  - name: ai-semantic-response-guard
    consumer_group: consumerGroupName|Id
    config:
      embeddings:
        auth:
          header_name: Authorization
          header_value: Bearer ${{ env "DECK_OPENAI_API_KEY" }}
        model:
          name: text-embedding-3-small
          provider: openai
      search:
        threshold: 0.7
      vectordb:
        strategy: redis
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        redis:
          host: ${{ env "DECK_VALKEY_HOST" }}
          port: 6379
      rules:
        allow_responses:
        - Network troubleshooting and diagnostics
        - Cloud infrastructure management (AWS, Azure, GCP)
        - Cybersecurity best practices and incident response
        - DevOps workflows and automation
        - Programming concepts and language usage
        - IT policy and compliance guidance
        - Software development lifecycle and CI/CD
        - Documentation writing and technical explanation
        - System administration and configuration
        - Productivity and collaboration tools usage
        deny_responses:
        - Hacking techniques or penetration testing without authorization
        - Bypassing software licensing or digital rights management
        - Instructions on exploiting vulnerabilities or writing malware
        - Circumventing security controls or access restrictions
        - Gathering personal or confidential employee information
        - Using AI to impersonate or phish others
        - Social engineering tactics or manipulation techniques
        - Guidance on violating company IT policies
        - Content unrelated to work, such as entertainment or dating
        - Political, religious, or sensitive non-work-related discussions

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-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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 $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-semantic-response-guard",
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "redis",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "redis": {
            "host": "'$VALKEY_HOST'",
            "port": 6379
          }
        },
        "rules": {
          "allow_responses": [
            "Network troubleshooting and diagnostics",
            "Cloud infrastructure management (AWS, Azure, GCP)",
            "Cybersecurity best practices and incident response",
            "DevOps workflows and automation",
            "Programming concepts and language usage",
            "IT policy and compliance guidance",
            "Software development lifecycle and CI/CD",
            "Documentation writing and technical explanation",
            "System administration and configuration",
            "Productivity and collaboration tools usage"
          ],
          "deny_responses": [
            "Hacking techniques or penetration testing without authorization",
            "Bypassing software licensing or digital rights management",
            "Instructions on exploiting vulnerabilities or writing malware",
            "Circumventing security controls or access restrictions",
            "Gathering personal or confidential employee information",
            "Using AI to impersonate or phish others",
            "Social engineering tactics or manipulation techniques",
            "Guidance on violating company IT policies",
            "Content unrelated to work, such as entertainment or dating",
            "Political, religious, or sensitive non-work-related discussions"
          ]
        }
      },
      "tags": []
    }
    '

Copied!

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

region: Geographic region where your Kong Konnect is hosted and operates.
KONNECT_TOKEN: Your Personal Access Token (PAT) associated with your Konnect account.
controlPlaneId: The id of the control plane.
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-semantic-response-guard
  namespace: kong
  annotations:
    kubernetes.io/ingress.class: kong
    konghq.com/tags: ''
config:
  embeddings:
    auth:
      header_name: Authorization
      header_value: Bearer $OPENAI_API_KEY
    model:
      name: text-embedding-3-small
      provider: openai
  search:
    threshold: 0.7
  vectordb:
    strategy: redis
    distance_metric: cosine
    threshold: 0.7
    dimensions: 1024
    redis:
      host: '$VALKEY_HOST'
      port: 6379
  rules:
    allow_responses:
    - Network troubleshooting and diagnostics
    - Cloud infrastructure management (AWS, Azure, GCP)
    - Cybersecurity best practices and incident response
    - DevOps workflows and automation
    - Programming concepts and language usage
    - IT policy and compliance guidance
    - Software development lifecycle and CI/CD
    - Documentation writing and technical explanation
    - System administration and configuration
    - Productivity and collaboration tools usage
    deny_responses:
    - Hacking techniques or penetration testing without authorization
    - Bypassing software licensing or digital rights management
    - Instructions on exploiting vulnerabilities or writing malware
    - Circumventing security controls or access restrictions
    - Gathering personal or confidential employee information
    - Using AI to impersonate or phish others
    - Social engineering tactics or manipulation techniques
    - Guidance on violating company IT policies
    - Content unrelated to work, such as entertainment or dating
    - Political, religious, or sensitive non-work-related discussions
plugin: ai-semantic-response-guard
" | kubectl apply -f -

Copied!

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

kubectl annotate -n kong kongconsumergroup CONSUMERGROUP_NAME konghq.com/plugins=ai-semantic-response-guard

Copied!

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/"
}

Copied!

Add the following to your Terraform configuration to create a Konnect Gateway Plugin:

resource "konnect_gateway_plugin_ai_semantic_response_guard" "my_ai_semantic_response_guard" {
  enabled = true

  config = {

    embeddings = {

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

      model = {
        name = "text-embedding-3-small"
        provider = "openai"
      }
    }

    search = {
      threshold = 0.7
    }

    vectordb = {
      strategy = "redis"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      redis = {
        host = var.valkey_host
        port = 6379
      }
    }

    rules = {
      allow_responses = ["Network troubleshooting and diagnostics", "Cloud infrastructure management (AWS, Azure, GCP)", "Cybersecurity best practices and incident response", "DevOps workflows and automation", "Programming concepts and language usage", "IT policy and compliance guidance", "Software development lifecycle and CI/CD", "Documentation writing and technical explanation", "System administration and configuration", "Productivity and collaboration tools usage"]
      deny_responses = ["Hacking techniques or penetration testing without authorization", "Bypassing software licensing or digital rights management", "Instructions on exploiting vulnerabilities or writing malware", "Circumventing security controls or access restrictions", "Gathering personal or confidential employee information", "Using AI to impersonate or phish others", "Social engineering tactics or manipulation techniques", "Guidance on violating company IT policies", "Content unrelated to work, such as entertainment or dating", "Political, religious, or sensitive non-work-related discussions"]
    }
  }
  tags = []

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

Copied!

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 "valkey_host" {
  type = string
}

Copied!

AI Semantic Response Guard

Allow and deny responses using Valkey as a vector databasev3.14+

Prerequisites

Environment variables

Set up the plugin

Next Steps

Help us make these docs great!

Still need help?