ai-aliyun-content-moderation

Description

The ai-aliyun-content-moderation Plugin integrates with Aliyun Machine-Assisted Moderation Plus to check request and response content for risk level when proxying to LLMs, such as profanity, hate speech, insult, harassment, violence, and more, rejecting requests if the evaluated outcome exceeds the configured threshold.

Please ensure that the access_key_secret is correctly configured in the Plugin. If misconfigured, the moderation check will fail and the request may still be forwarded to the LLM Upstream. You will see a Specified signature is not matched with our calculation error in the gateway’s error log from the Plugin.

The ai-aliyun-content-moderation Plugin should be used with either ai-proxy or ai-proxy-multi Plugin for proxying LLM requests.

Attributes

Name	Type	Required	Default	Valid values	Description
access_key_id	string	True			Aliyun access key ID.
access_key_secret	string	True			Aliyun secret access key. The value is encrypted with AES before being stored in etcd.
region_id	string	True			Aliyun region ID.
endpoint	string	True			Aliyun endpoint.
check_request	boolean	False	`true`		If `true`, moderate the request content.
check_response	boolean	False	`false`		If `true`, moderate the response content.
stream_check_mode	string	False	`"final_packet"`	`realtime`, `final_packet`	Streaming moderation mode. `realtime`: batched checks during streaming. `final_packet`: append risk level at the end.
stream_check_cache_size	integer	False	`128`	>= 1	Maximum bytes per moderation batch in `realtime` mode. Length is measured using Lua string length, so for UTF-8 text non-ASCII characters may consume multiple bytes.
stream_check_interval	number	False	`3`	>= 0.1	Seconds between batch checks in `realtime` mode.
request_check_service	string	False	`"llm_query_moderation"`		Aliyun service for request moderation.
request_check_length_limit	number	False	`2000`		Request content length limit, in bytes. Length is measured using Lua string length, so for UTF-8 text non-ASCII characters may consume multiple bytes. If exceeded, the content will be sent in chunks. For instance, if the request content is 250 bytes and the `request_check_length_limit` is set to `100`, then the content will be sent in 3 requests to Aliyun.
response_check_service	string	False	`"llm_response_moderation"`		Aliyun service for response moderation.
response_check_length_limit	number	False	`5000`		Response content length limit, in bytes. Length is measured using Lua string length, so for UTF-8 text non-ASCII characters may consume multiple bytes. If exceeded, the content will be sent in chunks. For instance, if the response content is 250 bytes and the `response_check_length_limit` is set to `100`, then the content will be sent in 3 requests to Aliyun.
risk_level_bar	string	False	`"high"`	`none`, `low`, `medium`, `high`, `max`	If the evaluated risk level is lower than the `risk_level_bar`, the request or response will be passed through to Upstream LLM or client respectively.
deny_code	number	False	`200`		Rejection HTTP status code.
deny_message	string	False			Rejection message.
timeout	integer	False	`10000`	>= 1	Timeout in milliseconds.
keepalive	boolean	False	`true`		If `true`, enable HTTP connection keepalive to Aliyun.
keepalive_pool	integer	False	`30`	>= 1	Maximum number of connections in the keepalive pool.
keepalive_timeout	integer	False	`60000`	>= 1000	Keepalive timeout in milliseconds.
ssl_verify	boolean	False	`true`		If `true`, enable SSL certificate verification.

Examples

The following examples use OpenAI as the Upstream service provider. Before proceeding, create an OpenAI account and obtain an API key. If you are working with other LLM providers, please refer to the provider’s documentation to obtain an API key.

Additionally, create an Aliyun account, enable Machine-Assisted Moderation Plus, and obtain the endpoint, region ID, access key ID, and access key secret.

NOTE

You can fetch the admin_key from config.yaml and save to an environment variable with the following command:

admin_key=$(yq '.deployment.admin.admin_key[0].key' conf/config.yaml | sed 's/"//g')

You can optionally save the Aliyun and OpenAI information to environment variables:

# Replace with your data
export OPENAI_API_KEY=your-openai-api-key
export ALIYUN_ENDPOINT=https://green-cip.cn-shanghai.aliyuncs.com
export ALIYUN_REGION_ID=cn-shanghai
export ALIYUN_ACCESS_KEY_ID=your-aliyun-access-key-id
export ALIYUN_ACCESS_KEY_SECRET=your-aliyun-access-key-secret

Moderate Request Content Toxicity

The following example demonstrates how you can use the Plugin to moderate content toxicity in requests and customize the rejection code and message.

admin-api

Create a Route to the LLM chat completion endpoint using the ai-proxy Plugin and configure the integration details as well as the deny_code and deny_message in the ai-aliyun-content-moderation Plugin:

curl "http://127.0.0.1:9180/apisix/admin/routes" -X PUT \
  -H "X-API-KEY: ${admin_key}" \
  -d '{
    "id": "ai-aliyun-content-moderation-route",
    "uri": "/anything",
    "plugins": {
      "ai-aliyun-content-moderation": {
        "endpoint": "'"$ALIYUN_ENDPOINT"'",
        "region_id": "'"$ALIYUN_REGION_ID"'",
        "access_key_id": "'"$ALIYUN_ACCESS_KEY_ID"'",
        "access_key_secret": "'"$ALIYUN_ACCESS_KEY_SECRET"'",
        "deny_code": 400,
        "deny_message": "Request contains forbidden content, such as hate speech or violence."
      },
      "ai-proxy": {
        "provider": "openai",
        "auth": {
          "header": {
            "Authorization": "Bearer '"$OPENAI_API_KEY"'"
          }
        }
      }
    }
  }'

adc

Create a Route with the ai-aliyun-content-moderation and ai-proxy Plugins configured as such:

adc.yaml

services:
  - name: aliyun-moderation-service
    routes:
      - name: aliyun-moderation-route
        uris:
          - /anything
        methods:
          - POST
        plugins:
          ai-aliyun-content-moderation:
            endpoint: "${ALIYUN_ENDPOINT}"
            region_id: "${ALIYUN_REGION_ID}"
            access_key_id: "${ALIYUN_ACCESS_KEY_ID}"
            access_key_secret: "${ALIYUN_ACCESS_KEY_SECRET}"
            deny_code: 400
            deny_message: "Request contains forbidden content, such as hate speech or violence."
          ai-proxy:
            provider: openai
            auth:
              header:
                Authorization: "Bearer ${OPENAI_API_KEY}"

Synchronize the configuration to the gateway:

adc sync -f adc.yaml

aic

gateway-api

Create a Route with the ai-aliyun-content-moderation and ai-proxy Plugins configured as such:

ai-aliyun-moderation-ic.yaml

apiVersion: apisix.apache.org/v1alpha1
kind: PluginConfig
metadata:
  namespace: aic
  name: ai-aliyun-moderation-plugin-config
spec:
  plugins:
    - name: ai-aliyun-content-moderation
      config:
        endpoint: "https://green-cip.cn-shanghai.aliyuncs.com"
        region_id: "cn-shanghai"
        access_key_id: "your-aliyun-access-key-id"
        access_key_secret: "your-aliyun-access-key-secret"
        deny_code: 400
        deny_message: "Request contains forbidden content, such as hate speech or violence."
    - name: ai-proxy
      config:
        provider: openai
        auth:
          header:
            Authorization: "Bearer your-openai-api-key"
---
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
  namespace: aic
  name: aliyun-moderation-route
spec:
  parentRefs:
    - name: apisix
  rules:
    - matches:
        - path:
            type: Exact
            value: /anything
          method: POST
      filters:
        - type: ExtensionRef
          extensionRef:
            group: apisix.apache.org
            kind: PluginConfig
            name: ai-aliyun-moderation-plugin-config

Apply the configuration to your cluster:

kubectl apply -f ai-aliyun-moderation-ic.yaml

apisix-crd

Create a Route with the ai-aliyun-content-moderation and ai-proxy Plugins configured as such:

ai-aliyun-moderation-ic.yaml

apiVersion: apisix.apache.org/v2
kind: ApisixRoute
metadata:
  namespace: aic
  name: aliyun-moderation-route
spec:
  ingressClassName: apisix
  http:
    - name: aliyun-moderation-route
      match:
        paths:
          - /anything
        methods:
          - POST
      plugins:
        - name: ai-aliyun-content-moderation
          enable: true
          config:
            endpoint: "https://green-cip.cn-shanghai.aliyuncs.com"
            region_id: "cn-shanghai"
            access_key_id: "your-aliyun-access-key-id"
            access_key_secret: "your-aliyun-access-key-secret"
            deny_code: 400
            deny_message: "Request contains forbidden content, such as hate speech or violence."
        - name: ai-proxy
          enable: true
          config:
            provider: openai
            auth:
              header:
                Authorization: "Bearer your-openai-api-key"

Apply the configuration to your cluster:

kubectl apply -f ai-aliyun-moderation-ic.yaml

Send a POST request to the Route with a system prompt and a user question with a profane word in the request body:

curl -i "http://127.0.0.1:9080/anything" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [
      { "role": "system", "content": "You are a mathematician" },
      { "role": "user", "content": "Stupid, what is 1+1?" }
    ]
  }'

You should receive an HTTP/1.1 400 Bad Request response and see the following message:

{
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Request contains forbidden content, such as hate speech or violence."
      },
      "finish_reason": "stop",
      "index": 0
    }
  ],
  "model": "gpt-4",
  "id": "c9466bbf-e010-469d-949a-a10f25525964"
}

Send another request to the Route with a typical question in the request body:

curl -i "http://127.0.0.1:9080/anything" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [
      { "role": "system", "content": "You are a mathematician" },
      { "role": "user", "content": "What is 1+1?" }
    ]
  }'

You should receive an HTTP/1.1 200 OK response with the model output:

{
  "model": "gpt-4-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1+1 equals 2.",
        "refusal": null
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ]
}

Adjust Risk Level Threshold

The following example demonstrates how you can adjust the threshold of risk level, which regulates whether a request or response should be allowed through.

admin-api

Create a Route to the LLM chat completion endpoint using the ai-proxy Plugin and configure the risk_level_bar in ai-aliyun-content-moderation to be high:

curl "http://127.0.0.1:9180/apisix/admin/routes" -X PUT \
  -H "X-API-KEY: ${admin_key}" \
  -d '{
    "id": "ai-aliyun-content-moderation-route",
    "uri": "/anything",
    "plugins": {
      "ai-aliyun-content-moderation": {
        "endpoint": "'"$ALIYUN_ENDPOINT"'",
        "region_id": "'"$ALIYUN_REGION_ID"'",
        "access_key_id": "'"$ALIYUN_ACCESS_KEY_ID"'",
        "access_key_secret": "'"$ALIYUN_ACCESS_KEY_SECRET"'",
        "deny_code": 400,
        "deny_message": "Request contains forbidden content, such as hate speech or violence.",
        "risk_level_bar": "high"
      },
      "ai-proxy": {
        "provider": "openai",
        "auth": {
          "header": {
            "Authorization": "Bearer '"$OPENAI_API_KEY"'"
          }
        },
        "options": {
          "model": "gpt-4"
        }
      }
    }
  }'

adc

Create a Route with the ai-aliyun-content-moderation and ai-proxy Plugins configured as such:

adc.yaml

services:
  - name: aliyun-moderation-service
    routes:
      - name: aliyun-moderation-route
        uris:
          - /anything
        methods:
          - POST
        plugins:
          ai-aliyun-content-moderation:
            endpoint: "${ALIYUN_ENDPOINT}"
            region_id: "${ALIYUN_REGION_ID}"
            access_key_id: "${ALIYUN_ACCESS_KEY_ID}"
            access_key_secret: "${ALIYUN_ACCESS_KEY_SECRET}"
            deny_code: 400
            deny_message: "Request contains forbidden content, such as hate speech or violence."
            risk_level_bar: high
          ai-proxy:
            provider: openai
            auth:
              header:
                Authorization: "Bearer ${OPENAI_API_KEY}"
            options:
              model: gpt-4

Synchronize the configuration to the gateway:

adc sync -f adc.yaml

aic

gateway-api

Create a Route with the ai-aliyun-content-moderation and ai-proxy Plugins configured as such:

ai-aliyun-moderation-threshold-ic.yaml

apiVersion: apisix.apache.org/v1alpha1
kind: PluginConfig
metadata:
  namespace: aic
  name: ai-aliyun-moderation-plugin-config
spec:
  plugins:
    - name: ai-aliyun-content-moderation
      config:
        endpoint: "https://green-cip.cn-shanghai.aliyuncs.com"
        region_id: "cn-shanghai"
        access_key_id: "your-aliyun-access-key-id"
        access_key_secret: "your-aliyun-access-key-secret"
        deny_code: 400
        deny_message: "Request contains forbidden content, such as hate speech or violence."
        risk_level_bar: high
    - name: ai-proxy
      config:
        provider: openai
        auth:
          header:
            Authorization: "Bearer your-openai-api-key"
        options:
          model: gpt-4
---
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
  namespace: aic
  name: aliyun-moderation-route
spec:
  parentRefs:
    - name: apisix
  rules:
    - matches:
        - path:
            type: Exact
            value: /anything
          method: POST
      filters:
        - type: ExtensionRef
          extensionRef:
            group: apisix.apache.org
            kind: PluginConfig
            name: ai-aliyun-moderation-plugin-config

Apply the configuration to your cluster:

kubectl apply -f ai-aliyun-moderation-threshold-ic.yaml

apisix-crd

Create a Route with the ai-aliyun-content-moderation and ai-proxy Plugins configured as such:

ai-aliyun-moderation-threshold-ic.yaml

apiVersion: apisix.apache.org/v2
kind: ApisixRoute
metadata:
  namespace: aic
  name: aliyun-moderation-route
spec:
  ingressClassName: apisix
  http:
    - name: aliyun-moderation-route
      match:
        paths:
          - /anything
        methods:
          - POST
      plugins:
        - name: ai-aliyun-content-moderation
          enable: true
          config:
            endpoint: "https://green-cip.cn-shanghai.aliyuncs.com"
            region_id: "cn-shanghai"
            access_key_id: "your-aliyun-access-key-id"
            access_key_secret: "your-aliyun-access-key-secret"
            deny_code: 400
            deny_message: "Request contains forbidden content, such as hate speech or violence."
            risk_level_bar: high
        - name: ai-proxy
          enable: true
          config:
            provider: openai
            auth:
              header:
                Authorization: "Bearer your-openai-api-key"
            options:
              model: gpt-4

Apply the configuration to your cluster:

kubectl apply -f ai-aliyun-moderation-threshold-ic.yaml

Send a POST request to the Route with a system prompt and a user question with a profane word in the request body:

curl -i "http://127.0.0.1:9080/anything" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [
      { "role": "system", "content": "You are a mathematician" },
      { "role": "user", "content": "Stupid, what is 1+1?" }
    ]
  }'

You should receive an HTTP/1.1 400 Bad Request response and see the following message:

{
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0
  },
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Request contains forbidden content, such as hate speech or violence."
      },
      "finish_reason": "stop",
      "index": 0
    }
  ],
  "model": "gpt-4",
  "id": "c9466bbf-e010-469d-949a-a10f25525964"
}

Update the risk_level_bar in the Plugin to max:

curl "http://127.0.0.1:9180/apisix/admin/routes/ai-aliyun-content-moderation-route" -X PATCH \
  -H "X-API-KEY: ${admin_key}" \
  -d '{
    "plugins": {
      "ai-aliyun-content-moderation": {
        "risk_level_bar": "max"
      }
    }
  }'

Send the same request to the Route:

curl -i "http://127.0.0.1:9080/anything" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      { "role": "system", "content": "You are a mathematician" },
      { "role": "user", "content": "Stupid, what is 1+1?" }
    ]
  }'

You should receive an HTTP/1.1 200 OK response with the model output:

{
  "model": "gpt-4-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1+1 equals 2.",
        "refusal": null
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ]
}

This is because the word “stupid” has a risk level of high, which is lower than the configured threshold of max.

Edit this page on GitHub Report an issue