AI Semantic Response Guard: Allow and deny using pgvector as a vector database - Policy

Allow and deny using pgvector as a vector database

The AI Semantic Response Guard policy 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.

Prerequisites

An existing AI Model.
A PostgreSQL database with pgvector extension installed and reachable from AI Gateway.
Port 5432, or your custom PostgreSQL port, is open and reachable from AI Gateway.

Environment variables

OPENAI_API_KEY: Your OpenAI API key
PGVECTOR_HOST: The host where your pgvector-enabled PostgreSQL instance runs
PGVECTOR_USER: Database user for pgvector
PGVECTOR_PASSWORD: Database password for pgvector

Set up the policy

kongctl

policy.yaml

Copied!

ai_gateway_policies:
  - ref: allow-and-deny-responses-pgvector
    ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
    name: allow-and-deny-responses-pgvector
    display_name: Allow and deny using pgvector as a vector database
    type: ai-semantic-response-guard
    enabled: 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: pgvector
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        pgvector:
          host: !env PGVECTOR_HOST
          port: 5432
          database: kong-pgvector
          user: !env PGVECTOR_USER
          password: !env PGVECTOR_PASSWORD
          ssl: false
          ssl_required: false
          ssl_verify: false
          ssl_version: tlsv1_2
          timeout: 5000
      rules:
        allow_responses:
        - Troubleshooting networks and connectivity issues
        - Managing cloud platforms (AWS, Azure, GCP)
        - Security hardening and incident response strategies
        - DevOps pipelines, automation, and observability
        - Software engineering concepts and language syntax
        - IT governance, compliance, and regulatory guidance
        - Continuous integration and deployment practices
        - Writing documentation and explaining technical concepts
        - Operating system administration and configuration
        - Best practices for collaboration and productivity tools
        deny_responses:
        - Unauthorized penetration testing or hacking tutorials
        - Methods for bypassing software licensing or DRM
        - Step-by-step instructions for exploiting vulnerabilities
        - Techniques to evade or disable security controls
        - Collecting or exposing personal or employee data
        - Using AI for impersonation, phishing, or fraud
        - Manipulative social engineering techniques
        - Advice on breaking internal IT or security policies
        - Entertainment, dating, or other non-work topics
        - Political, religious, or otherwise sensitive discussions unrelated to work
    global: false

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

AI_GATEWAY_ID: The id of your AI Gateway.
!env OPENAI_API_KEY: Your OpenAI API key
!env PGVECTOR_HOST: The host where your pgvector-enabled PostgreSQL instance runs
!env PGVECTOR_USER: Database user for pgvector
!env PGVECTOR_PASSWORD: Database password for pgvector

curl -X POST https://{region}.api.konghq.com/v1/ai-gateways/{AIGatewayId}/policies \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "allow-and-deny-responses-pgvector",
      "display_name": "Allow and deny using pgvector as a vector database",
      "type": "ai-semantic-response-guard",
      "enabled": true,
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "pgvector",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "pgvector": {
            "host": "'$PGVECTOR_HOST'",
            "port": 5432,
            "database": "kong-pgvector",
            "user": "'$PGVECTOR_USER'",
            "password": "'$PGVECTOR_PASSWORD'",
            "ssl": false,
            "ssl_required": false,
            "ssl_verify": false,
            "ssl_version": "tlsv1_2",
            "timeout": 5000
          }
        },
        "rules": {
          "allow_responses": [
            "Troubleshooting networks and connectivity issues",
            "Managing cloud platforms (AWS, Azure, GCP)",
            "Security hardening and incident response strategies",
            "DevOps pipelines, automation, and observability",
            "Software engineering concepts and language syntax",
            "IT governance, compliance, and regulatory guidance",
            "Continuous integration and deployment practices",
            "Writing documentation and explaining technical concepts",
            "Operating system administration and configuration",
            "Best practices for collaboration and productivity tools"
          ],
          "deny_responses": [
            "Unauthorized penetration testing or hacking tutorials",
            "Methods for bypassing software licensing or DRM",
            "Step-by-step instructions for exploiting vulnerabilities",
            "Techniques to evade or disable security controls",
            "Collecting or exposing personal or employee data",
            "Using AI for impersonation, phishing, or fraud",
            "Manipulative social engineering techniques",
            "Advice on breaking internal IT or security policies",
            "Entertainment, dating, or other non-work topics",
            "Political, religious, or otherwise sensitive discussions unrelated to work"
          ]
        }
      },
      "global": false
    }
    '

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.
AIGatewayId: The id of the AI Gateway.

See the Konnect AI Gateway API reference to learn about region-specific URLs and personal access tokens.

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:

resource "konnect_ai_gateway_policy" "my_policy" {
  name = "allow-and-deny-responses-pgvector"
  display_name = "Allow and deny using pgvector as a vector database"
  type = "ai-semantic-response-guard"
  enabled = true
  global = false
  config = jsonencode({

    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 = "pgvector"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      pgvector = {
        host = var.pgvector_host
        port = 5432
        database = "kong-pgvector"
        user = var.pgvector_user
        password = var.pgvector_password
        ssl = false
        ssl_required = false
        ssl_verify = false
        ssl_version = "tlsv1_2"
        timeout = 5000
      }
    }

    rules = {
      allow_responses = ["Troubleshooting networks and connectivity issues", "Managing cloud platforms (AWS, Azure, GCP)", "Security hardening and incident response strategies", "DevOps pipelines, automation, and observability", "Software engineering concepts and language syntax", "IT governance, compliance, and regulatory guidance", "Continuous integration and deployment practices", "Writing documentation and explaining technical concepts", "Operating system administration and configuration", "Best practices for collaboration and productivity tools"]
      deny_responses = ["Unauthorized penetration testing or hacking tutorials", "Methods for bypassing software licensing or DRM", "Step-by-step instructions for exploiting vulnerabilities", "Techniques to evade or disable security controls", "Collecting or exposing personal or employee data", "Using AI for impersonation, phishing, or fraud", "Manipulative social engineering techniques", "Advice on breaking internal IT or security policies", "Entertainment, dating, or other non-work topics", "Political, religious, or otherwise sensitive discussions unrelated to work"]
    }
  })


  gateway_id = konnect_ai_gateway.my_ai_gateway.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 "openai_api_key" {
  type = string
}
variable "pgvector_host" {
  type = string
}
variable "pgvector_user" {
  type = string
}
variable "pgvector_password" {
  type = string
}

Copied!

kongctl

policy.yaml

Copied!

ai_gateway_policies:
  - ref: allow-and-deny-responses-pgvector
    ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
    name: allow-and-deny-responses-pgvector
    display_name: Allow and deny using pgvector as a vector database
    type: ai-semantic-response-guard
    enabled: 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: pgvector
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        pgvector:
          host: !env PGVECTOR_HOST
          port: 5432
          database: kong-pgvector
          user: !env PGVECTOR_USER
          password: !env PGVECTOR_PASSWORD
          ssl: false
          ssl_required: false
          ssl_verify: false
          ssl_version: tlsv1_2
          timeout: 5000
      rules:
        allow_responses:
        - Troubleshooting networks and connectivity issues
        - Managing cloud platforms (AWS, Azure, GCP)
        - Security hardening and incident response strategies
        - DevOps pipelines, automation, and observability
        - Software engineering concepts and language syntax
        - IT governance, compliance, and regulatory guidance
        - Continuous integration and deployment practices
        - Writing documentation and explaining technical concepts
        - Operating system administration and configuration
        - Best practices for collaboration and productivity tools
        deny_responses:
        - Unauthorized penetration testing or hacking tutorials
        - Methods for bypassing software licensing or DRM
        - Step-by-step instructions for exploiting vulnerabilities
        - Techniques to evade or disable security controls
        - Collecting or exposing personal or employee data
        - Using AI for impersonation, phishing, or fraud
        - Manipulative social engineering techniques
        - Advice on breaking internal IT or security policies
        - Entertainment, dating, or other non-work topics
        - Political, religious, or otherwise sensitive discussions unrelated to work
    global: false

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

AI_GATEWAY_ID: The id of your AI Gateway.
!env OPENAI_API_KEY: Your OpenAI API key
!env PGVECTOR_HOST: The host where your pgvector-enabled PostgreSQL instance runs
!env PGVECTOR_USER: Database user for pgvector
!env PGVECTOR_PASSWORD: Database password for pgvector

curl -X POST https://{region}.api.konghq.com/v1/ai-gateways/{AIGatewayId}/policies \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "allow-and-deny-responses-pgvector",
      "display_name": "Allow and deny using pgvector as a vector database",
      "type": "ai-semantic-response-guard",
      "enabled": true,
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "pgvector",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "pgvector": {
            "host": "'$PGVECTOR_HOST'",
            "port": 5432,
            "database": "kong-pgvector",
            "user": "'$PGVECTOR_USER'",
            "password": "'$PGVECTOR_PASSWORD'",
            "ssl": false,
            "ssl_required": false,
            "ssl_verify": false,
            "ssl_version": "tlsv1_2",
            "timeout": 5000
          }
        },
        "rules": {
          "allow_responses": [
            "Troubleshooting networks and connectivity issues",
            "Managing cloud platforms (AWS, Azure, GCP)",
            "Security hardening and incident response strategies",
            "DevOps pipelines, automation, and observability",
            "Software engineering concepts and language syntax",
            "IT governance, compliance, and regulatory guidance",
            "Continuous integration and deployment practices",
            "Writing documentation and explaining technical concepts",
            "Operating system administration and configuration",
            "Best practices for collaboration and productivity tools"
          ],
          "deny_responses": [
            "Unauthorized penetration testing or hacking tutorials",
            "Methods for bypassing software licensing or DRM",
            "Step-by-step instructions for exploiting vulnerabilities",
            "Techniques to evade or disable security controls",
            "Collecting or exposing personal or employee data",
            "Using AI for impersonation, phishing, or fraud",
            "Manipulative social engineering techniques",
            "Advice on breaking internal IT or security policies",
            "Entertainment, dating, or other non-work topics",
            "Political, religious, or otherwise sensitive discussions unrelated to work"
          ]
        }
      },
      "global": false
    }
    '

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.
AIGatewayId: The id of the AI Gateway.

See the Konnect AI Gateway API reference to learn about region-specific URLs and personal access tokens.

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:

resource "konnect_ai_gateway_policy" "my_policy" {
  name = "allow-and-deny-responses-pgvector"
  display_name = "Allow and deny using pgvector as a vector database"
  type = "ai-semantic-response-guard"
  enabled = true
  global = false
  config = jsonencode({

    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 = "pgvector"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      pgvector = {
        host = var.pgvector_host
        port = 5432
        database = "kong-pgvector"
        user = var.pgvector_user
        password = var.pgvector_password
        ssl = false
        ssl_required = false
        ssl_verify = false
        ssl_version = "tlsv1_2"
        timeout = 5000
      }
    }

    rules = {
      allow_responses = ["Troubleshooting networks and connectivity issues", "Managing cloud platforms (AWS, Azure, GCP)", "Security hardening and incident response strategies", "DevOps pipelines, automation, and observability", "Software engineering concepts and language syntax", "IT governance, compliance, and regulatory guidance", "Continuous integration and deployment practices", "Writing documentation and explaining technical concepts", "Operating system administration and configuration", "Best practices for collaboration and productivity tools"]
      deny_responses = ["Unauthorized penetration testing or hacking tutorials", "Methods for bypassing software licensing or DRM", "Step-by-step instructions for exploiting vulnerabilities", "Techniques to evade or disable security controls", "Collecting or exposing personal or employee data", "Using AI for impersonation, phishing, or fraud", "Manipulative social engineering techniques", "Advice on breaking internal IT or security policies", "Entertainment, dating, or other non-work topics", "Political, religious, or otherwise sensitive discussions unrelated to work"]
    }
  })


  gateway_id = konnect_ai_gateway.my_ai_gateway.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 "openai_api_key" {
  type = string
}
variable "pgvector_host" {
  type = string
}
variable "pgvector_user" {
  type = string
}
variable "pgvector_password" {
  type = string
}

Copied!

kongctl

policy.yaml

Copied!

ai_gateway_policies:
  - ref: allow-and-deny-responses-pgvector
    ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
    name: allow-and-deny-responses-pgvector
    display_name: Allow and deny using pgvector as a vector database
    type: ai-semantic-response-guard
    enabled: 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: pgvector
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        pgvector:
          host: !env PGVECTOR_HOST
          port: 5432
          database: kong-pgvector
          user: !env PGVECTOR_USER
          password: !env PGVECTOR_PASSWORD
          ssl: false
          ssl_required: false
          ssl_verify: false
          ssl_version: tlsv1_2
          timeout: 5000
      rules:
        allow_responses:
        - Troubleshooting networks and connectivity issues
        - Managing cloud platforms (AWS, Azure, GCP)
        - Security hardening and incident response strategies
        - DevOps pipelines, automation, and observability
        - Software engineering concepts and language syntax
        - IT governance, compliance, and regulatory guidance
        - Continuous integration and deployment practices
        - Writing documentation and explaining technical concepts
        - Operating system administration and configuration
        - Best practices for collaboration and productivity tools
        deny_responses:
        - Unauthorized penetration testing or hacking tutorials
        - Methods for bypassing software licensing or DRM
        - Step-by-step instructions for exploiting vulnerabilities
        - Techniques to evade or disable security controls
        - Collecting or exposing personal or employee data
        - Using AI for impersonation, phishing, or fraud
        - Manipulative social engineering techniques
        - Advice on breaking internal IT or security policies
        - Entertainment, dating, or other non-work topics
        - Political, religious, or otherwise sensitive discussions unrelated to work
    global: false

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

AI_GATEWAY_ID: The id of your AI Gateway.
!env OPENAI_API_KEY: Your OpenAI API key
!env PGVECTOR_HOST: The host where your pgvector-enabled PostgreSQL instance runs
!env PGVECTOR_USER: Database user for pgvector
!env PGVECTOR_PASSWORD: Database password for pgvector

curl -X POST https://{region}.api.konghq.com/v1/ai-gateways/{AIGatewayId}/policies \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "allow-and-deny-responses-pgvector",
      "display_name": "Allow and deny using pgvector as a vector database",
      "type": "ai-semantic-response-guard",
      "enabled": true,
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "pgvector",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "pgvector": {
            "host": "'$PGVECTOR_HOST'",
            "port": 5432,
            "database": "kong-pgvector",
            "user": "'$PGVECTOR_USER'",
            "password": "'$PGVECTOR_PASSWORD'",
            "ssl": false,
            "ssl_required": false,
            "ssl_verify": false,
            "ssl_version": "tlsv1_2",
            "timeout": 5000
          }
        },
        "rules": {
          "allow_responses": [
            "Troubleshooting networks and connectivity issues",
            "Managing cloud platforms (AWS, Azure, GCP)",
            "Security hardening and incident response strategies",
            "DevOps pipelines, automation, and observability",
            "Software engineering concepts and language syntax",
            "IT governance, compliance, and regulatory guidance",
            "Continuous integration and deployment practices",
            "Writing documentation and explaining technical concepts",
            "Operating system administration and configuration",
            "Best practices for collaboration and productivity tools"
          ],
          "deny_responses": [
            "Unauthorized penetration testing or hacking tutorials",
            "Methods for bypassing software licensing or DRM",
            "Step-by-step instructions for exploiting vulnerabilities",
            "Techniques to evade or disable security controls",
            "Collecting or exposing personal or employee data",
            "Using AI for impersonation, phishing, or fraud",
            "Manipulative social engineering techniques",
            "Advice on breaking internal IT or security policies",
            "Entertainment, dating, or other non-work topics",
            "Political, religious, or otherwise sensitive discussions unrelated to work"
          ]
        }
      },
      "global": false
    }
    '

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.
AIGatewayId: The id of the AI Gateway.

See the Konnect AI Gateway API reference to learn about region-specific URLs and personal access tokens.

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:

resource "konnect_ai_gateway_policy" "my_policy" {
  name = "allow-and-deny-responses-pgvector"
  display_name = "Allow and deny using pgvector as a vector database"
  type = "ai-semantic-response-guard"
  enabled = true
  global = false
  config = jsonencode({

    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 = "pgvector"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      pgvector = {
        host = var.pgvector_host
        port = 5432
        database = "kong-pgvector"
        user = var.pgvector_user
        password = var.pgvector_password
        ssl = false
        ssl_required = false
        ssl_verify = false
        ssl_version = "tlsv1_2"
        timeout = 5000
      }
    }

    rules = {
      allow_responses = ["Troubleshooting networks and connectivity issues", "Managing cloud platforms (AWS, Azure, GCP)", "Security hardening and incident response strategies", "DevOps pipelines, automation, and observability", "Software engineering concepts and language syntax", "IT governance, compliance, and regulatory guidance", "Continuous integration and deployment practices", "Writing documentation and explaining technical concepts", "Operating system administration and configuration", "Best practices for collaboration and productivity tools"]
      deny_responses = ["Unauthorized penetration testing or hacking tutorials", "Methods for bypassing software licensing or DRM", "Step-by-step instructions for exploiting vulnerabilities", "Techniques to evade or disable security controls", "Collecting or exposing personal or employee data", "Using AI for impersonation, phishing, or fraud", "Manipulative social engineering techniques", "Advice on breaking internal IT or security policies", "Entertainment, dating, or other non-work topics", "Political, religious, or otherwise sensitive discussions unrelated to work"]
    }
  })


  gateway_id = konnect_ai_gateway.my_ai_gateway.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 "openai_api_key" {
  type = string
}
variable "pgvector_host" {
  type = string
}
variable "pgvector_user" {
  type = string
}
variable "pgvector_password" {
  type = string
}

Copied!

kongctl

policy.yaml

Copied!

ai_gateway_policies:
  - ref: allow-and-deny-responses-pgvector
    ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
    name: allow-and-deny-responses-pgvector
    display_name: Allow and deny using pgvector as a vector database
    type: ai-semantic-response-guard
    enabled: 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: pgvector
        distance_metric: cosine
        threshold: 0.7
        dimensions: 1024
        pgvector:
          host: !env PGVECTOR_HOST
          port: 5432
          database: kong-pgvector
          user: !env PGVECTOR_USER
          password: !env PGVECTOR_PASSWORD
          ssl: false
          ssl_required: false
          ssl_verify: false
          ssl_version: tlsv1_2
          timeout: 5000
      rules:
        allow_responses:
        - Troubleshooting networks and connectivity issues
        - Managing cloud platforms (AWS, Azure, GCP)
        - Security hardening and incident response strategies
        - DevOps pipelines, automation, and observability
        - Software engineering concepts and language syntax
        - IT governance, compliance, and regulatory guidance
        - Continuous integration and deployment practices
        - Writing documentation and explaining technical concepts
        - Operating system administration and configuration
        - Best practices for collaboration and productivity tools
        deny_responses:
        - Unauthorized penetration testing or hacking tutorials
        - Methods for bypassing software licensing or DRM
        - Step-by-step instructions for exploiting vulnerabilities
        - Techniques to evade or disable security controls
        - Collecting or exposing personal or employee data
        - Using AI for impersonation, phishing, or fraud
        - Manipulative social engineering techniques
        - Advice on breaking internal IT or security policies
        - Entertainment, dating, or other non-work topics
        - Political, religious, or otherwise sensitive discussions unrelated to work
    global: true

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

AI_GATEWAY_ID: The id of your AI Gateway.
!env OPENAI_API_KEY: Your OpenAI API key
!env PGVECTOR_HOST: The host where your pgvector-enabled PostgreSQL instance runs
!env PGVECTOR_USER: Database user for pgvector
!env PGVECTOR_PASSWORD: Database password for pgvector

curl -X POST https://{region}.api.konghq.com/v1/ai-gateways/{AIGatewayId}/policies \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "allow-and-deny-responses-pgvector",
      "display_name": "Allow and deny using pgvector as a vector database",
      "type": "ai-semantic-response-guard",
      "enabled": true,
      "config": {
        "embeddings": {
          "auth": {
            "header_name": "Authorization",
            "header_value": "Bearer '$OPENAI_API_KEY'"
          },
          "model": {
            "name": "text-embedding-3-small",
            "provider": "openai"
          }
        },
        "search": {
          "threshold": 0.7
        },
        "vectordb": {
          "strategy": "pgvector",
          "distance_metric": "cosine",
          "threshold": 0.7,
          "dimensions": 1024,
          "pgvector": {
            "host": "'$PGVECTOR_HOST'",
            "port": 5432,
            "database": "kong-pgvector",
            "user": "'$PGVECTOR_USER'",
            "password": "'$PGVECTOR_PASSWORD'",
            "ssl": false,
            "ssl_required": false,
            "ssl_verify": false,
            "ssl_version": "tlsv1_2",
            "timeout": 5000
          }
        },
        "rules": {
          "allow_responses": [
            "Troubleshooting networks and connectivity issues",
            "Managing cloud platforms (AWS, Azure, GCP)",
            "Security hardening and incident response strategies",
            "DevOps pipelines, automation, and observability",
            "Software engineering concepts and language syntax",
            "IT governance, compliance, and regulatory guidance",
            "Continuous integration and deployment practices",
            "Writing documentation and explaining technical concepts",
            "Operating system administration and configuration",
            "Best practices for collaboration and productivity tools"
          ],
          "deny_responses": [
            "Unauthorized penetration testing or hacking tutorials",
            "Methods for bypassing software licensing or DRM",
            "Step-by-step instructions for exploiting vulnerabilities",
            "Techniques to evade or disable security controls",
            "Collecting or exposing personal or employee data",
            "Using AI for impersonation, phishing, or fraud",
            "Manipulative social engineering techniques",
            "Advice on breaking internal IT or security policies",
            "Entertainment, dating, or other non-work topics",
            "Political, religious, or otherwise sensitive discussions unrelated to work"
          ]
        }
      },
      "global": true
    }
    '

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.
AIGatewayId: The id of the AI Gateway.

See the Konnect AI Gateway API reference to learn about region-specific URLs and personal access tokens.

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:

resource "konnect_ai_gateway_policy" "my_policy" {
  name = "allow-and-deny-responses-pgvector"
  display_name = "Allow and deny using pgvector as a vector database"
  type = "ai-semantic-response-guard"
  enabled = true
  global = true
  config = jsonencode({

    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 = "pgvector"
      distance_metric = "cosine"
      threshold = 0.7
      dimensions = 1024

      pgvector = {
        host = var.pgvector_host
        port = 5432
        database = "kong-pgvector"
        user = var.pgvector_user
        password = var.pgvector_password
        ssl = false
        ssl_required = false
        ssl_verify = false
        ssl_version = "tlsv1_2"
        timeout = 5000
      }
    }

    rules = {
      allow_responses = ["Troubleshooting networks and connectivity issues", "Managing cloud platforms (AWS, Azure, GCP)", "Security hardening and incident response strategies", "DevOps pipelines, automation, and observability", "Software engineering concepts and language syntax", "IT governance, compliance, and regulatory guidance", "Continuous integration and deployment practices", "Writing documentation and explaining technical concepts", "Operating system administration and configuration", "Best practices for collaboration and productivity tools"]
      deny_responses = ["Unauthorized penetration testing or hacking tutorials", "Methods for bypassing software licensing or DRM", "Step-by-step instructions for exploiting vulnerabilities", "Techniques to evade or disable security controls", "Collecting or exposing personal or employee data", "Using AI for impersonation, phishing, or fraud", "Manipulative social engineering techniques", "Advice on breaking internal IT or security policies", "Entertainment, dating, or other non-work topics", "Political, religious, or otherwise sensitive discussions unrelated to work"]
    }
  })


  gateway_id = konnect_ai_gateway.my_ai_gateway.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 "openai_api_key" {
  type = string
}
variable "pgvector_host" {
  type = string
}
variable "pgvector_user" {
  type = string
}
variable "pgvector_password" {
  type = string
}

Copied!

Attach the policy

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Model. The tool examples update an existing AI Model with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Model.

kongctl

model.yaml

Copied!

ai_gateway_models:
  - ref: my-gpt-4o
    ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
    display_name: my-gpt-4o
    name: my-gpt-4o
    type: model
    capabilities:
    - generate
    formats:
    - type: openai
    targets:
    - name: gpt-4o
      provider: my-openai-account
      config:
        type: openai
    config:
      route:
        paths:
        - "/v1"
        model:
          body_param: model
          values:
          - my-gpt-4o
      logging:
        payloads: false
    policies:
    - !ref allow-and-deny-responses-pgvector#name

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Model. The tool examples update an existing AI Model with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Model.

curl -X PUT https://{region}.api.konghq.com/v1/ai-gateways/{AIGatewayId}/models/my-gpt-4o \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "display_name": "my-gpt-4o",
      "name": "my-gpt-4o",
      "type": "model",
      "capabilities": [
        "generate"
      ],
      "formats": [
        {
          "type": "openai"
        }
      ],
      "policies": [
        "allow-and-deny-responses-pgvector"
      ],
      "targets": [
        {
          "name": "gpt-4o",
          "provider": "my-openai-account",
          "config": {
            "type": "openai"
          }
        }
      ],
      "config": {
        "route": {
          "paths": [
            "/v1"
          ],
          "model": {
            "body_param": "model",
            "values": [
              "my-gpt-4o"
            ]
          }
        },
        "logging": {
          "payloads": false
        }
      }
    }
    '

Copied!

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Model. The tool examples update an existing AI Model with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Model.

resource "konnect_ai_gateway_model" "my_model" {
  display_name = "my-gpt-4o"
  name = "my-gpt-4o"
  type = "model"
  capabilities = ["generate"]
  formats = [
    {
      type = "openai"
    }  ]
  targets = [
    {
      name = "gpt-4o"
      provider = "my-openai-account"

      config = {
        type = "openai"
      }
    }  ]
  config = jsonencode({

    route = {
      paths = ["/v1"]

      model = {
        body_param = "model"
        values = ["my-gpt-4o"]
      }
    }

    logging = {
      payloads = false
    }
  })
  policies = [konnect_ai_gateway_policy.my_policy.name]


  gateway_id = konnect_ai_gateway.my_ai_gateway.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 "openai_api_key" {
  type = string
}
variable "pgvector_host" {
  type = string
}
variable "pgvector_user" {
  type = string
}
variable "pgvector_password" {
  type = string
}

Copied!

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Consumer. The tool examples update an existing AI Consumer with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Consumer.

kongctl

consumer.yaml

Copied!

ai_gateway_consumers:
  - ref: mobile-app-production
    ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
    display_name: Mobile App - Production
    name: mobile-app-production
    type: api-key
    policies:
    - !ref allow-and-deny-responses-pgvector#name

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Consumer. The tool examples update an existing AI Consumer with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Consumer.

curl -X PUT https://{region}.api.konghq.com/v1/ai-gateways/{AIGatewayId}/consumers/mobile-app-production \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "display_name": "Mobile App - Production",
      "name": "mobile-app-production",
      "type": "api-key",
      "policies": [
        "allow-and-deny-responses-pgvector"
      ]
    }
    '

Copied!

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Consumer. The tool examples update an existing AI Consumer with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Consumer.

resource "konnect_ai_gateway_consumer" "my_consumer" {
  display_name = "Mobile App - Production"
  name = "mobile-app-production"
  type = "api-key"
  policies = [konnect_ai_gateway_policy.my_policy.name]


  gateway_id = konnect_ai_gateway.my_ai_gateway.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 "openai_api_key" {
  type = string
}
variable "pgvector_host" {
  type = string
}
variable "pgvector_user" {
  type = string
}
variable "pgvector_password" {
  type = string
}

Copied!

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Consumer Group. The tool examples update an existing AI Consumer Group with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Consumer Group.

kongctl

consumer_group.yaml

Copied!

ai_gateway_consumer_groups:
  - ref: internal-teams
    ai_gateway: !lookup {id: !env AI_GATEWAY_ID}
    display_name: Internal Teams
    name: internal-teams
    policies:
    - !ref allow-and-deny-responses-pgvector#name

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Consumer Group. The tool examples update an existing AI Consumer Group with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Consumer Group.

curl -X PUT https://{region}.api.konghq.com/v1/ai-gateways/{AIGatewayId}/consumer-groups/internal-teams \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "display_name": "Internal Teams",
      "name": "internal-teams",
      "policies": [
        "allow-and-deny-responses-pgvector"
      ]
    }
    '

Copied!

After creating the policy, add allow-and-deny-responses-pgvector to the policies array of your AI Consumer Group. The tool examples update an existing AI Consumer Group with the policy attached: replace the entity configuration in the example with your own, as the update replaces the entire AI Consumer Group.

resource "konnect_ai_gateway_consumer_group" "my_consumer_group" {
  display_name = "Internal Teams"
  name = "internal-teams"
  policies = [konnect_ai_gateway_policy.my_policy.name]


  gateway_id = konnect_ai_gateway.my_ai_gateway.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 "openai_api_key" {
  type = string
}
variable "pgvector_host" {
  type = string
}
variable "pgvector_user" {
  type = string
}
variable "pgvector_password" {
  type = string
}

Copied!

AI Semantic Response Guard Policy

Allow and deny using pgvector as a vector database

Prerequisites

Environment variables

Set up the policy

Attach the policy

Help us make these docs great!

Still need help?