ai-prompt-decorator-API Gateway(API Gateway)-阿里云帮助中心

Running attributes

Plug-in execution stage: default stage. Plug-in execution priority: 450.

Configuration description

Field	Data type	Required	Default value	Description
`prepend`	array of message object	optional	-	Messages prepended to the initial input.
`append`	array of message object	optional	-	Messages appended to the initial input.

A message object contains the following parameters.

Field	Data type	Required	Default value	Description
`role`	string	Yes	-	The message role, such as `system` or `user`.
`content`	string	Yes	-	The message text.

Sample configuration:

prepend:
- role: system
  content: "Answer the question in English."
append:
- role: user
  content: "Each time you answer a question, try to ask a rhetorical question."

Request with the preceding configuration:

curl http://localhost/test \
-H "content-type: application/json" \
-d '{
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "user",
      "content": "Who are you?"
    }
  ]
}

Processed request after the plug-in runs:

curl http://localhost/test \
-H "content-type: application/json" \
-d '{
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "system",
      content: "Answer the question in English."
    },
    {
      "role": "user",
      "content": "Who are you?"
    },
    {
      "role": "user",
      content: "Each time you answer a question, try to ask a rhetorical question."
    }
  ]
}

Include user geographic locations with the ai-prompt and geo-ip plug-ins

To include user geographic locations in LLM requests, enable both the geo-ip plug-in and the ai-prompt plug-in. The geo-ip plug-in must have a higher priority than the ai-prompt plug-in in the same processing stage so that it resolves the user's location from the IP address before the prompt is assembled. For example, in the default phase, the geo-ip plug-in priority is 1000 and the ai-prompt plug-in priority is 500.

Sample geo-ip plug-in configuration:

ipProtocal: "ipv4"

Sample ai-prompt plug-in configuration:

prepend:
- role: system
  content: "The current geographic location of the user is: country:${geo-country}, province:${geo-province}, city:${geo-city}"
append:
- role: user
  content: "Each time you answer a question, try to ask a rhetorical question."

Request with the preceding configurations:

curl http://localhost/test \
-H "content-type: application/json" \
-H "x-forwarded-for: 87.254.207.100,4.5.6.7" \
-d '{
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather like today?"
    }
  ]
}'

Processed request after both plug-ins run:

curl http://localhost/test \
-H "content-type: application/json" \
-H "x-forwarded-for: 87.254.207.100,4.5.6.7" \
-d '{
  "model": "gpt-3.5-turbo",
  "messages": [
    {
      "role": "system",
      content: "The current geographic location of the user is: country: China, province: Beijing, city: Beijing"
    },
    {
      "role": "user",
      "content": "What is the weather like today?"
    },
    {
      "role": "user",
      content: "Each time you answer a question, try to ask a rhetorical question."
    }
  ]
}'