Skip to content

ai-prompt-template.md

Latest commit

 

History

History
602 lines (530 loc) · 18.8 KB

ai-prompt-template.md

File metadata and controls

602 lines (530 loc) · 18.8 KB
title ai-prompt-template
keywords
Apache APISIX
API Gateway
Plugin
ai-prompt-template
description The ai-prompt-template plugin supports pre-configuring prompt templates that only accept user inputs in designated template variables, in a fill-in-the-blank fashion.

import Tabs from '@theme/Tabs'; import TabItem from '@theme/TabItem';

Description

The ai-prompt-template Plugin supports pre-configuring prompt templates that only accept user inputs in designated template variables, in a "fill in the blank" fashion. It simplifies access to LLM providers, such as OpenAI and Anthropic, by letting you define reusable prompt structures.

Plugin Attributes

Name Type Required Default Valid values Description
templates array True An array of template objects.
templates.name string True Name of the template. When requesting the Route, the request should include the template name that corresponds to the configured template.
templates.template object True Template specification.
templates.template.model string False Name of the LLM model, such as gpt-4 or gpt-3.5. See your LLM provider API documentation for more available models.
templates.template.messages array[object] False Template message specification.
templates.template.messages.role string True [system, user, assistant] Role of the message.
templates.template.messages.content string True Content of the message (prompt). Use {{variable_name}} syntax to define template variables that will be filled from the request body.

Examples

The following examples use OpenAI as the Upstream service provider. Before proceeding, create an OpenAI account and an API key. You can optionally save the key to an environment variable:

export OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>

If you are working with other LLM providers, please refer to the provider's documentation to obtain an API key.

:::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')

:::

Configure a Template for Open Questions in Custom Complexity

The following example demonstrates how to use the ai-prompt-template Plugin to configure a template that can be used to answer open questions and accepts user-specified response complexity.

Create a Route to the chat completion endpoint with pre-configured prompt templates. The ai-proxy Plugin is used to configure the OpenAI API key and model. The ai-prompt-template Plugin defines a template named "QnA with complexity" with two template variables: complexity controls the answer detail level, and prompt accepts the user question.

curl "http://127.0.0.1:9180/apisix/admin/routes/1" -X PUT \
  -H "X-API-KEY: ${admin_key}" \
  -d '{
    "uri": "/openai-chat",
    "methods": ["POST"],
    "plugins": {
      "ai-proxy": {
        "provider": "openai",
        "auth": {
          "header": {
            "Authorization": "Bearer '"$OPENAI_API_KEY"'"
          }
        },
        "options": {
          "model": "gpt-4"
        }
      },
      "ai-prompt-template": {
        "templates": [
          {
            "name": "QnA with complexity",
            "template": {
              "model": "gpt-4",
              "messages": [
                {
                  "role": "system",
                  "content": "Answer in {{complexity}}."
                },
                {
                  "role": "user",
                  "content": "Explain {{prompt}}."
                }
              ]
            }
          }
        ]
      }
    }
  }'

Create a Route with the ai-prompt-template and ai-proxy Plugins. The ai-proxy Plugin configures the OpenAI API key and model. The ai-prompt-template Plugin defines a template named "QnA with complexity" with two template variables: complexity controls the answer detail level, and prompt accepts the user question.

services:
  - name: prompt-template-service
    routes:
      - name: prompt-template-route
        uris:
          - /openai-chat
        methods:
          - POST
        plugins:
          ai-proxy:
            provider: openai
            auth:
              header:
                Authorization: "Bearer ${OPENAI_API_KEY}"
            options:
              model: gpt-4
          ai-prompt-template:
            templates:
              - name: "QnA with complexity"
                template:
                  model: gpt-4
                  messages:
                    - role: system
                      content: "Answer in {{complexity}}."
                    - role: user
                      content: "Explain {{prompt}}."

Synchronize the configuration to the gateway:

adc sync -f adc.yaml

Create a Route with the ai-prompt-template and ai-proxy Plugins. The ai-prompt-template Plugin defines a template named "QnA with complexity" with two template variables: complexity controls the answer detail level, and prompt accepts the user question.

apiVersion: apisix.apache.org/v1alpha1
kind: PluginConfig
metadata:
  namespace: aic
  name: ai-prompt-template-plugin-config
spec:
  plugins:
    - name: ai-prompt-template
      config:
        templates:
          - name: "QnA with complexity"
            template:
              model: gpt-4
              messages:
                - role: system
                  content: "Answer in {{complexity}}."
                - role: user
                  content: "Explain {{prompt}}."
    - name: ai-proxy
      config:
        provider: openai
        auth:
          header:
            Authorization: "Bearer your-api-key"
        options:
          model: gpt-4
---
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
  namespace: aic
  name: prompt-template-route
spec:
  parentRefs:
    - name: apisix
  rules:
    - matches:
        - path:
            type: Exact
            value: /openai-chat
          method: POST
      filters:
        - type: ExtensionRef
          extensionRef:
            group: apisix.apache.org
            kind: PluginConfig
            name: ai-prompt-template-plugin-config

Create a Route with the ai-prompt-template and ai-proxy Plugins. The ai-prompt-template Plugin defines a template named "QnA with complexity" with two template variables: complexity controls the answer detail level, and prompt accepts the user question.

apiVersion: apisix.apache.org/v2
kind: ApisixRoute
metadata:
  namespace: aic
  name: prompt-template-route
spec:
  ingressClassName: apisix
  http:
    - name: prompt-template-route
      match:
        paths:
          - /openai-chat
        methods:
          - POST
      plugins:
        - name: ai-prompt-template
          enable: true
          config:
            templates:
              - name: "QnA with complexity"
                template:
                  model: gpt-4
                  messages:
                    - role: system
                      content: "Answer in {{complexity}}."
                    - role: user
                      content: "Explain {{prompt}}."
        - name: ai-proxy
          enable: true
          config:
            provider: openai
            auth:
              header:
                Authorization: "Bearer your-api-key"
            options:
              model: gpt-4

Apply the configuration to your cluster:

kubectl apply -f ai-prompt-template-ic.yaml

The Route should now be available to respond to a variety of questions with different levels of user-specified complexity.

Send a POST request to the Route with a sample question and desired answer complexity in the request body:

curl "http://127.0.0.1:9080/openai-chat" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "template_name": "QnA with complexity",
    "complexity": "brief",
    "prompt": "quick sort"
  }'

You should receive a response similar to the following:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Quick sort is a highly efficient sorting algorithm that uses a divide-and-conquer approach to arrange elements in a list or array in order. Here's a brief explanation:\n\n1. **Choose a Pivot**: Select an element from the list as a 'pivot'. Common methods include choosing the first element, the last element, the middle element, or a random element.\n\n2. **Partitioning**: Rearrange the elements in the list such that all elements less than the pivot are moved before it, and all elements greater than the pivot are moved after it. The pivot is now in its final position.\n\n3. **Recursively Apply**: Recursively apply the same process to the sub-lists of elements to the left and right of the pivot.\n\nThe base case of the recursion is lists of size zero or one, which are already sorted.\n\nQuick sort has an average-case time complexity of O(n log n), making it suitable for large datasets. However, its worst-case time complexity is O(n^2), which occurs when the smallest or largest element is always chosen as the pivot. This can be mitigated by using good pivot selection strategies or randomization.",
        "role": "assistant"
      }
    }
  ],
  "created": 1723194057,
  "id": "chatcmpl-9uFmTYN4tfwaXZjyOQwcp0t5law4x",
  "model": "gpt-4o-2024-05-13",
  "object": "chat.completion",
  "system_fingerprint": "fp_abc28019ad",
  "usage": {
    "completion_tokens": 234,
    "prompt_tokens": 18,
    "total_tokens": 252
  }
}

Configure Multiple Templates

The following example demonstrates how you can configure multiple templates on the same Route. When requesting the Route, users will be able to pass custom inputs to different templates by specifying the template name.

The example continues with the last example. Update the Plugin with another template:

Update the Route with an additional template named "echo" that simply echoes back the user input:

curl "http://127.0.0.1:9180/apisix/admin/routes/1" -X PATCH \
  -H "X-API-KEY: ${admin_key}" \
  -d '{
    "plugins": {
      "ai-prompt-template": {
        "templates": [
          {
            "name": "QnA with complexity",
            "template": {
              "model": "gpt-4",
              "messages": [
                {
                  "role": "system",
                  "content": "Answer in {{complexity}}."
                },
                {
                  "role": "user",
                  "content": "Explain {{prompt}}."
                }
              ]
            }
          },
          {
            "name": "echo",
            "template": {
              "model": "gpt-4",
              "messages": [
                {
                  "role": "user",
                  "content": "Echo {{prompt}}."
                }
              ]
            }
          }
        ]
      }
    }
  }'

Update the Route configuration with an additional template named "echo" that simply echoes back the user input:

services:
  - name: prompt-template-service
    routes:
      - name: prompt-template-route
        uris:
          - /openai-chat
        methods:
          - POST
        plugins:
          ai-proxy:
            provider: openai
            auth:
              header:
                Authorization: "Bearer ${OPENAI_API_KEY}"
            options:
              model: gpt-4
          ai-prompt-template:
            templates:
              - name: "QnA with complexity"
                template:
                  model: gpt-4
                  messages:
                    - role: system
                      content: "Answer in {{complexity}}."
                    - role: user
                      content: "Explain {{prompt}}."
              - name: "echo"
                template:
                  model: gpt-4
                  messages:
                    - role: user
                      content: "Echo {{prompt}}."

Synchronize the configuration to the gateway:

adc sync -f adc.yaml

Update the PluginConfig with an additional template named "echo" that simply echoes back the user input:

apiVersion: apisix.apache.org/v1alpha1
kind: PluginConfig
metadata:
  namespace: aic
  name: ai-prompt-template-plugin-config
spec:
  plugins:
    - name: ai-prompt-template
      config:
        templates:
          - name: "QnA with complexity"
            template:
              model: gpt-4
              messages:
                - role: system
                  content: "Answer in {{complexity}}."
                - role: user
                  content: "Explain {{prompt}}."
          - name: "echo"
            template:
              model: gpt-4
              messages:
                - role: user
                  content: "Echo {{prompt}}."
    - name: ai-proxy
      config:
        provider: openai
        auth:
          header:
            Authorization: "Bearer your-api-key"
        options:
          model: gpt-4
---
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
  namespace: aic
  name: prompt-template-route
spec:
  parentRefs:
    - name: apisix
  rules:
    - matches:
        - path:
            type: Exact
            value: /openai-chat
          method: POST
      filters:
        - type: ExtensionRef
          extensionRef:
            group: apisix.apache.org
            kind: PluginConfig
            name: ai-prompt-template-plugin-config

Update the ApisixRoute with an additional template named "echo" that simply echoes back the user input:

apiVersion: apisix.apache.org/v2
kind: ApisixRoute
metadata:
  namespace: aic
  name: prompt-template-route
spec:
  ingressClassName: apisix
  http:
    - name: prompt-template-route
      match:
        paths:
          - /openai-chat
        methods:
          - POST
      plugins:
        - name: ai-prompt-template
          enable: true
          config:
            templates:
              - name: "QnA with complexity"
                template:
                  model: gpt-4
                  messages:
                    - role: system
                      content: "Answer in {{complexity}}."
                    - role: user
                      content: "Explain {{prompt}}."
              - name: "echo"
                template:
                  model: gpt-4
                  messages:
                    - role: user
                      content: "Echo {{prompt}}."
        - name: ai-proxy
          enable: true
          config:
            provider: openai
            auth:
              header:
                Authorization: "Bearer your-api-key"
            options:
              model: gpt-4

Apply the configuration to your cluster:

kubectl apply -f ai-prompt-template-multi-ic.yaml

You should now be able to use both templates through the same Route.

Send a POST request to the Route and use the first template:

curl "http://127.0.0.1:9080/openai-chat" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "template_name": "QnA with complexity",
    "complexity": "brief",
    "prompt": "quick sort"
  }'

You should receive a response similar to the following:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Quick sort is a highly efficient sorting algorithm that uses a divide-and-conquer approach to arrange elements in a list or array in order. Here's a brief explanation:\n\n1. **Choose a Pivot**: Select an element from the list as a 'pivot'. Common methods include choosing the first element, the last element, the middle element, or a random element.\n\n2. **Partitioning**: Rearrange the elements in the list such that all elements less than the pivot are moved before it, and all elements greater than the pivot are moved after it. The pivot is now in its final position.\n\n3. **Recursively Apply**: Recursively apply the same process to the sub-lists of elements to the left and right of the pivot.\n\nThe base case of the recursion is lists of size zero or one, which are already sorted.\n\nQuick sort has an average-case time complexity of O(n log n), making it suitable for large datasets. However, its worst-case time complexity is O(n^2), which occurs when the smallest or largest element is always chosen as the pivot. This can be mitigated by using good pivot selection strategies or randomization.",
        "role": "assistant"
      }
    }
  ],
  ...
}

Send a POST request to the Route and use the second template:

curl "http://127.0.0.1:9080/openai-chat" -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "template_name": "echo",
    "prompt": "hello APISIX"
  }'

You should receive a response similar to the following:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "hello APISIX",
        "role": "assistant"
      }
    }
  ],
  ...
}