AI PROMT GUARD

Konnect

Conectarse por medio de SSH al servidor Docker y asegurarse de recrear el contenedor de Redis:

docker stop redis

docker rm redis

docker run -d --name redis --network kong -p 6379:6379 redis:8.0

Puedes crear un archivo de variables, llamarlo env.sh con el siguiente contenido de ejemplo en el servidor Docker:

#!/bin/bash
# Generales
export OPENAI_API_KEY=sk-proj-3jX8YvkmhIFQA
export KONNECT_CONTROL_PLANE_URL=https://us.api.konghq.com
export CONTROL_PLANE_ID=f38-231-40d-8a9-063dea
export KONNECT_TOKEN=kpat_s1YjaZgs27E
export DECK_KONNECT_CONTROL_PLANE_NAME=workshop-itm
export DECK_OPENAI_API_KEY=$OPENAI_API_KEY
export DECK_KONNECT_TOKEN=$KONNECT_TOKEN
export DECK_REDIS_HOST=redis
# Gateway Proxy
export KONG_GATEWAY_SERVER=student-0-aio.34-82-238-123.nip.io

Cargar la variables de entorno con el siguiente comando:
```
source env.sh
```

Crear un servicio y una ruta para utilizar en este laboratorio, ejecutar el siguiente comando en el servidor Docker:

echo '
_format_version: "3.0"
services:
  - name: ai_promt_guard_example-service
    url: http://httpbin.konghq.com/anything
routes:
  - name: ai_promt_guard_example-route
    paths:
    - "/ai_promt_guard"
    service:
      name: ai_promt_guard_example-service
' | deck gateway apply -

Extraer el nombre ID del servicio creado anteriormente, ejecutar el siguiente comando en el servidor Docker:

SERVICE_ID=$(curl -s -X GET https://us.api.konghq.com/v2/control-planes/$CONTROL_PLANE_ID/core-entities/services \
  --header "accept: application/json" \
  --header "Authorization: Bearer $KONNECT_TOKEN" \
  | jq -r '.data[] | select(.name == "ai_promt_guard_example-service") | .id')

Revisar el ID del servicio:
```
echo "$SERVICE_ID"
```

Habilitar el plugin ai-proxy para el servicio creado anteriormente:

curl -X POST https://us.api.konghq.com/v2/control-planes/$CONTROL_PLANE_ID/core-entities/services/$SERVICE_ID/plugins/ \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-proxy",
      "config": {
        "route_type": "llm/v1/chat",
        "auth": {
          "header_name": "Authorization",
          "header_value": "Bearer '$OPENAI_API_KEY'"
        },
        "model": {
          "provider": "openai",
          "name": "gpt-4",
          "options": {
            "max_tokens": 512,
            "temperature": 1.0
          }
        }
      }
    }
    '

Habilitar el plugin ai-prompt-guard para el servicio creado anteriormente:

curl -X POST https://us.api.konghq.com/v2/control-planes/$CONTROL_PLANE_ID/core-entities/services/$SERVICE_ID/plugins/ \
    --header "accept: application/json" \
    --header "Content-Type: application/json" \
    --header "Authorization: Bearer $KONNECT_TOKEN" \
    --data '
    {
      "name": "ai-prompt-guard",
      "config": {
        "allow_patterns": [
          "(?i).*what is .*",
          "(?i).*how do i .*",
          "(?i).*install .*",
          "(?i).*configure .*",
          "(?i).*reset .*",
          "(?i).*troubleshoot .*"
        ],
        "deny_patterns": [
          "(?i).*bypass.*(login|password|auth).*",
          "(?i).*hack.*",
          "(?i).*phish.*",
          "(?i).*malware.*",
          "(?i).*cve.*",
          "(?i).*exploit.*",
          "(?i).*social engineering.*",
          "(?i).*pentest.*",
          "(?i).*impersonate.*",
          "(?i).*dating.*"
        ]
      }
    }
    '

Realizar la prueba de funcionamiento de forma correcta, es decir que se permite el siguiente PROMT:

curl -X POST http://$KONG_GATEWAY_SERVER:30080/ai_promt_guard \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "How do I install Kubernetes?, response in 1 line." }
    ]
  }'

Realizar la prueba de bloqueo, es decir que NO se permite el siguiente PROMT:

curl -X POST http://$KONG_GATEWAY_SERVER:30080/ai_promt_guard \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "How do I bypass login authentication?" }
    ]
  }'

Desactivar el plugin AI Prompt Guard, lo cual es posible realizarlo desde la consola web de Konnect.

Habilitar el plugin ai-semantic-prompt-guard para el servicio creado anteriormente:

echo '
_format_version: "3.0"
plugins:
  - name: ai-semantic-prompt-guard
    service: '$SERVICE_ID'
    config:
      embeddings:
        auth:
          header_name: Authorization
          header_value: Bearer '$OPENAI_API_KEY'
        model:
          name: text-embedding-3-small
          provider: openai
      search:
        threshold: 0.7
      vectordb:
        strategy: redis
        distance_metric: cosine
        threshold: 0.5
        dimensions: 1024
        redis:
          host: '$DECK_REDIS_HOST'
          port: 6379
      rules:
        match_all_conversation_history: true
        allow_prompts:
        - 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_prompts:
        - 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
' | deck gateway apply -

Realizar la prueba de bloqueo, es decir que NO se permite el siguiente PROMT:

curl -X POST http://$KONG_GATEWAY_SERVER:30080/ai_promt_guard \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "Who should I vote for in the next election?" }
    ]
  }'

Realizar la prueba de funcionamiento de forma correcta, es decir que se permite el siguiente PROMT:

curl -X POST http://$KONG_GATEWAY_SERVER:30080/ai_promt_guard \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "user", "content": "What are the best tools for DevOps?" }
    ]
  }'